new

Get trending papers in your email inbox!

Subscribe

Daily Papers

byAK and the research community

Nov 19

Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving

The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests. LLM serving platforms today define response-latency service-level objectives, even though requests within the same service can differ by orders of magnitude in input length, generation length, execution cost, and the availability of reusable KV-cache state. As a result, requests governed by the same service level objective have different urgency: after accounting for the time required to execute them, some have substantial latency headroom while others have almost none. We define this headroom---the difference between a request's service level objective and its predicted remaining service time---as its per-request latency budget. We present Cascade, an LLM serving system that estimates and continuously updates this budget from request characteristics, KV-cache state, and current system load. Unlike prior SLO-aware schedulers that use deadlines to govern request ordering alone, Cascade uses a single per-request budget to jointly coordinate request scheduling and KV-cache management across the memory hierarchy. Its scheduler prioritizes requests with little remaining budget, while its memory manager uses the same budget to decide whether non-resident KV state should be restored or prefetched from a deeper tier, retained in HBM, or recomputed. By directing queueing and data-movement overhead toward requests that can absorb it, Cascade improves SLO-satisfied goodput while preserving fairness across heterogeneous request classes. On production traces across three large language models, Cascade improves goodput by up to2.4x and reduces SLO violations by 40% relative to the default vLLM first-come, first-served scheduler.

  • 7 authors
·
Aug 5

Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads

Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art method for reducing LLM response latency, however GPU communications reduces combined token throughput. On the other hand, data parallelism (DP) obtains a higher throughput yet is slow in response latency. Best of both worlds does not exist, and it is not possible to combine TP and DP because of the KV cache variance across the parallelisms. We notice Sequence Parallelism (SP - Ulysses in training) has similar properties as DP but with KV cache invariance. We adapt SP to inference, and combine it with TP to get the best of both worlds. Our solution: Shift Parallelism. Shift Parallelism dynamically switches across TP and SP, and minimizes latency in low traffic without losing throughput in high traffic. The efficient GPU communications of Shift Parallelism yields up to i) 1.51x faster response in interactive workloads and ii) 50% higher throughput in batch workloads, compared to a TP-only solution. We evaluate Shift Parallelism with real-world production traces with dynamic traffic patterns as well as synthetic benchmarking patterns across models, context sizes, and arrival rates. All results affirm the same: Shift Parallelism has a better the latency vs. throughput tradeoff than TP or DP, and hence obtains low latency without degrading throughput in dynamic workloads.

  • 6 authors
·
Jan 25

Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution

Tool-augmented speech assistants typically serialize automatic speech recognition, large language model inference, and external tool execution. As a result, tool latency is incurred only after the user has finished speaking and the LLM has identified the required tool calls. We present speculative tool execution for on-device cascaded voice agents, which predicts tool requests from partial ASR hypotheses and initiates tool execution while speech is still being received, thereby reducing end-to-end response latency. Our approach introduces a Predictor module that anticipates tool calls during speech recognition, executes them speculatively, and caches the results. The cached outputs are then injected into the LLM prompt, enabling faster responses. Additionally, to mitigate errors caused by user self-corrections during speech, we employ a rule-based validation mechanism that selectively injects only valid cached results. As a final safeguard, the LLM retains the ability to issue tool calls directly, ensuring that the latency of our framework is upper-bounded by the baseline serial execution pipeline in the worst case. We evaluate our method using live measurements from a fully implemented Android voice assistant. Our approach reduces the median time-to-first-audio from 5.79,s to 4.60,s and decreases the standard deviation from 3.49,s to 2.81,s, resulting in more predictable response latency.

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation

Cybersecurity honeypots are deception tools for engaging attackers and gather intelligence, but traditional low or medium-interaction honeypots often rely on static, pre-scripted interactions that can be easily identified by skilled adversaries. This Report presents LLMHoney, an SSH honeypot that leverages Large Language Models (LLMs) to generate realistic, dynamic command outputs in real time. LLMHoney integrates a dictionary-based virtual file system to handle common commands with low latency while using LLMs for novel inputs, achieving a balance between authenticity and performance. We implemented LLMHoney using open-source LLMs and evaluated it on a testbed with 138 representative Linux commands. We report comprehensive metrics including accuracy (exact-match, Cosine Similarity, Jaro-Winkler Similarity, Levenshtein Similarity and BLEU score), response latency and memory overhead. We evaluate LLMHoney using multiple LLM backends ranging from 0.36B to 3.8B parameters, including both open-source models and a proprietary model(Gemini). Our experiments compare 13 different LLM variants; results show that Gemini-2.0 and moderately-sized models Qwen2.5:1.5B and Phi3:3.8B provide the most reliable and accurate responses, with mean latencies around 3 seconds, whereas smaller models often produce incorrect or out-of-character outputs. We also discuss how LLM integration improves honeypot realism and adaptability compared to traditional honeypots, as well as challenges such as occasional hallucinated outputs and increased resource usage. Our findings demonstrate that LLM-driven honeypots are a promising approach to enhance attacker engagement and collect richer threat intelligence.

  • 1 authors
·
Sep 1, 2025

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond proactively, fostering fluid, dynamic, and emotionally resonant interactions. We introduce Voila, a family of large voice-language foundation models that make a step towards this vision. Voila moves beyond traditional pipeline systems by adopting a new end-to-end architecture that enables full-duplex, low-latency conversations while preserving rich vocal nuances such as tone, rhythm, and emotion. It achieves a response latency of just 195 milliseconds, surpassing the average human response time. Its hierarchical multi-scale Transformer integrates the reasoning capabilities of large language models (LLMs) with powerful acoustic modeling, enabling natural, persona-aware voice generation -- where users can simply write text instructions to define the speaker's identity, tone, and other characteristics. Moreover, Voila supports over one million pre-built voices and efficient customization of new ones from brief audio samples as short as 10 seconds. Beyond spoken dialogue, Voila is designed as a unified model for a wide range of voice-based applications, including automatic speech recognition (ASR), Text-to-Speech (TTS), and, with minimal adaptation, multilingual speech translation. Voila is fully open-sourced to support open research and accelerate progress toward next-generation human-machine interactions.

  • 7 authors
·
May 5, 2025 4

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security risks related to response efficiency remain largely unexplored. In this paper, we introduce SlowBA, a novel backdoor attack that targets the responsiveness of VLM-based GUI agents. The key idea is to manipulate response latency by inducing excessively long reasoning chains under specific trigger patterns. To achieve this, we propose a two-stage reward-level backdoor injection (RBI) strategy that first aligns the long-response format and then learns trigger-aware activation through reinforcement learning. In addition, we design realistic pop-up windows as triggers that naturally appear in GUI environments, improving the stealthiness of the attack. Extensive experiments across multiple datasets and baselines demonstrate that SlowBA can significantly increase response length and latency while largely preserving task accuracy. The attack remains effective even with a small poisoning ratio and under several defense settings. These findings reveal a previously overlooked security vulnerability in GUI agents and highlight the need for defenses that consider both action correctness and response efficiency. Code can be found in https://github.com/tu-tuing/SlowBA.

  • 5 authors
·
Mar 9 3

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain prone to hallucinations due to limited factual grounding. While text-based dialogue systems address this challenge by integrating tools such as web search and knowledge graph APIs, we introduce the first approach to extend tool use directly into speech-in speech-out systems. A key challenge is that tool integration substantially increases response latency, disrupting conversational flow. To mitigate this, we propose Streaming Retrieval-Augmented Generation (Streaming RAG), a novel framework that reduces user-perceived latency by predicting tool queries in parallel with user speech, even before the user finishes speaking. Specifically, we develop a post-training pipeline that teaches the model when to issue tool calls during ongoing speech and how to generate spoken summaries that fuse audio queries with retrieved text results, thereby improving both accuracy and responsiveness. To evaluate our approach, we construct AudioCRAG, a benchmark created by converting queries from the publicly available CRAG dataset into speech form. Experimental results demonstrate that our streaming RAG approach increases QA accuracy by up to 200% relative (from 11.1% to 34.2% absolute) and further enhances user experience by reducing tool use latency by 20%. Importantly, our streaming RAG approach is modality-agnostic and can be applied equally to typed input, paving the way for more agentic, real-time AI assistants.

  • 17 authors
·
Oct 2, 2025

AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios

Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dimension of tool use, especially the impact of tool response latency, and are usually limited to single-task settings. In real-world applications, multiple tasks often need to be executed concurrently, and overall efficiency depends on whether an agent can use idle time while waiting for tool responses. We refer to this capability as asynchronous tool calling. To evaluate it, we propose AsyncTool, a benchmark for assessing LLM-based agents in interactive multi-task tool-use environments with delayed tool feedback. AsyncTool presents multiple heterogeneous tasks simultaneously and simulates realistic tool response latency during execution. Using a hybrid data evolution strategy, we construct a diverse asynchronous multitasking dataset that covers multiple scenarios and tool-use patterns. We evaluate models at the step, sub-task, and task levels, and introduce efficiency-oriented metrics to measure task coordination and completion efficiency. Extensive experiments show that delayed tool feedback poses substantial challenges to current agents and leads to clear performance degradation. Models that better coordinate task switching, dependency tracking, and state maintenance achieve stronger performance on AsyncTool. Our analysis identifies key failure modes of current tool-using agents and provides practical insights for designing future systems with stronger temporal reasoning and coordination capabilities.

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation, or video-generation modules, Wan-Streamer does not rely on external language, speech, avatar, or video-generation modules: perception, reasoning, generation, response timing, turn management, and cross-modal synchronization are learned jointly within one unified model, reducing pipeline latency and error accumulation. To support natural audio-visual responsiveness, we redesign the entire stack around streamability, including causal encoders, causal decoders, block-causal attention, and low-latency multimodal token scheduling, enabling streaming units as short as 160 ms at 25 fps. Wan-Streamer achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency when combined with 350 ms bidirectional network latency, supporting sub-second duplex audio-visual communication. These results position Wan-Streamer as a unified, end-to-end, multimodal interactive foundation model for low-latency streaming interaction.

Wan-AI Wan-AI
·
Jun 22 13

SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation

LLM inference for popular enterprise use cases, such as summarization, RAG, and code-generation, typically observes orders of magnitude longer prompt lengths than generation lengths. This characteristic leads to high cost of prefill and increased response latency. In this paper, we present SwiftKV, a novel model transformation and distillation procedure specifically designed to reduce the time and cost of processing prompt tokens while preserving high quality of generated tokens. SwiftKV combines three key mechanisms: i) SingleInputKV, which prefills later layers' KV cache using a much earlier layer's output, allowing prompt tokens to skip much of the model computation, ii) AcrossKV, which merges the KV caches of neighboring layers to reduce the memory footprint and support larger batch size for higher throughput, and iii) a knowledge-preserving distillation procedure that can adapt existing LLMs for SwiftKV with minimal accuracy impact and low compute and data requirement. For Llama-3.1-8B and 70B, SwiftKV reduces the compute requirement of prefill by 50% and the memory requirement of the KV cache by 62.5% while incurring minimum quality degradation across a wide range of tasks. In the end-to-end inference serving using an optimized vLLM implementation, SwiftKV realizes up to 2x higher aggregate throughput and 60% lower time per output token. It can achieve a staggering 560 TFlops/GPU of normalized inference throughput, which translates to 16K tokens/s for Llama-3.1-70B in 16-bit precision on 4x H100 GPUs.

  • 4 authors
·
Oct 4, 2024 2

SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models

Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting during the user's turn and can lead to high response latency while it waits to think. Consequently, thinking after receiving the full input is not suitable for speech-to-speech interaction, where real-time, low-latency exchange is important. We address this by noting that humans naturally "think while listening." In this paper, we propose SHANKS, a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to the user input. SHANKS streams the input speech in fixed-duration chunks and, as soon as a chunk is received, generates unspoken reasoning based on all previous speech and reasoning, while the user continues speaking. SHANKS uses this unspoken reasoning to decide whether to interrupt the user and to make tool calls to complete the task. We demonstrate that SHANKS enhances real-time user-SLM interaction in two scenarios: (1) when the user is presenting a step-by-step solution to a math problem, SHANKS can listen, reason, and interrupt when the user makes a mistake, achieving 37.1% higher interruption accuracy than a baseline that interrupts without thinking; and (2) in a tool-augmented dialogue, SHANKS can complete 56.9% of the tool calls before the user finishes their turn. Overall, SHANKS moves toward models that keep thinking throughout the conversation, not only after a turn ends. Animated illustrations of Shanks can be found at https://d223302.github.io/SHANKS/

  • 10 authors
·
Oct 8, 2025 2

UAF: A Unified Audio Front-end LLM for Full-Duplex Speech Interaction

Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from critical limitations, including accumulated latency, information loss, and error propagation across modules. To address these issues, recent efforts focus on the end-to-end audio large language models (LLMs) like GPT-4o, which primarily unify speech understanding and generation task. However, most of these models are inherently half-duplex, and rely on a suite of separate, task-specific front-end components, such as voice activity detection (VAD) and turn-taking detection (TD). In our development of speech assistant, we observed that optimizing the speech front-end is equally crucial as advancing the back-end unified model for achieving seamless, responsive interactions. To bridge this gap, we propose the first unified audio front-end LLM (UAF) tailored for full-duplex speech systems. Our model reformulates diverse audio front-end tasks into a single auto-regressive sequence prediction problem, including VAD, TD, speaker recognition (SR), automatic speech recognition (ASR) and question answer (QA). It takes streaming fixed-duration audio chunk (e.g., 600 ms) as input, leverages a reference audio prompt to anchor the target speaker at the beginning, and regressively generates discrete tokens encoding both semantic content and system-level state controls (e.g., interruption signals). Experiments demonstrate that our model achieves leading performance across multiple audio front-end tasks and significantly enhances response latency and interruption accuracy in real-world interaction scenarios.

  • 4 authors
·
Apr 29

Real-Time Reasoning Agents in Evolving Environments

Agents in the real world must make not only logical but also timely judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still unfolding. Despite advances in language model reasoning, existing approaches fail to account for this dynamic nature. We introduce real-time reasoning as a new problem formulation for agents in evolving environments and build Real-Time Reasoning Gym to demonstrate it. We study two paradigms for deploying language models in agents: (1) reactive agents, which employ language models with bounded reasoning computation for rapid responses, and (2) planning agents, which allow extended reasoning computation for complex problems. Our experiments show that even state-of-the-art models struggle with making logical and timely judgments in either paradigm. To address this limitation, we propose AgileThinker, which simultaneously engages both reasoning paradigms. AgileThinker consistently outperforms agents engaging only one reasoning paradigm as the task difficulty and time pressure rise, effectively balancing reasoning depth and response latency. Our work establishes real-time reasoning as a critical testbed for developing practical agents and provides a foundation for research in temporally constrained AI systems, highlighting a path toward real-time capable agents.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying test-time scaling methods incurs unacceptable response latency. To address this trade-off, we propose Video Streaming Thinking (VST), a novel paradigm for streaming video understanding. It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming. This design improves timely comprehension and coherent cognition while preserving real-time responsiveness by amortizing LLM reasoning latency over video playback. Furthermore, we introduce a comprehensive post-training pipeline that integrates VST-SFT, which structurally adapts the offline VideoLLM to causal streaming reasoning, and VST-RL, which provides end-to-end improvement through self-exploration in a multi-turn video interaction environment. Additionally, we devise an automated training-data synthesis pipeline that uses video knowledge graphs to generate high-quality streaming QA pairs, with an entity-relation grounded streaming Chain-of-Thought to enforce multi-evidence reasoning and sustained attention to the video stream. Extensive evaluations show that VST-7B performs strongly on online benchmarks, e.g. 79.5% on StreamingBench and 59.3% on OVO-Bench. Meanwhile, VST remains competitive on offline long-form or reasoning benchmarks. Compared with Video-R1, VST responds 15.7 times faster and achieves +5.4% improvement on VideoHolmes, demonstrating higher efficiency and strong generalization across diverse video understanding tasks. Code, data, and models will be released at https://github.com/1ranGuan/VST.

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow Matching, CosyVoice demonstrated high prosody naturalness, content consistency, and speaker similarity in speech in-context learning. Recently, significant progress has been made in multi-modal large language models (LLMs), where the response latency and real-time factor of speech synthesis play a crucial role in the interactive experience. Therefore, in this report, we present an improved streaming speech synthesis model, CosyVoice 2, which incorporates comprehensive and systematic optimizations. Specifically, we introduce finite-scalar quantization to improve the codebook utilization of speech tokens. For the text-speech LM, we streamline the model architecture to allow direct use of a pre-trained LLM as the backbone. In addition, we develop a chunk-aware causal flow matching model to support various synthesis scenarios, enabling both streaming and non-streaming synthesis within a single model. By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode. We invite readers to listen to the demos at https://funaudiollm.github.io/cosyvoice2.

  • 19 authors
·
Dec 13, 2024 2

Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is often used with Large Language Models (LLMs) to infuse domain knowledge or user-specific information. In RAG, given a user query, a retriever extracts chunks of relevant text from a knowledge base. These chunks are sent to an LLM as part of the input prompt. Typically, any given chunk is repeatedly retrieved across user questions. However, currently, for every question, attention-layers in LLMs fully compute the key values (KVs) repeatedly for the input chunks, as state-of-the-art methods cannot reuse KV-caches when chunks appear at arbitrary locations with arbitrary contexts. Naive reuse leads to output quality degradation. This leads to potentially redundant computations on expensive GPUs and increases latency. In this work, we propose Cache-Craft, a system for managing and reusing precomputed KVs corresponding to the text chunks (we call chunk-caches) in RAG-based systems. We present how to identify chunk-caches that are reusable, how to efficiently perform a small fraction of recomputation to fix the cache to maintain output quality, and how to efficiently store and evict chunk-caches in the hardware for maximizing reuse while masking any overheads. With real production workloads as well as synthetic datasets, we show that Cache-Craft reduces redundant computation by 51% over SOTA prefix-caching and 75% over full recomputation. Additionally, with continuous batching on a real production workload, we get a 1.6X speed up in throughput and a 2X reduction in end-to-end response latency over prefix-caching while maintaining quality, for both the LLaMA-3-8B and LLaMA-3-70B models.

  • 9 authors
·
Feb 5, 2025

Zep: A Temporal Knowledge Graph Architecture for Agent Memory

We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti -- a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep's capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep's effectiveness for deployment in real-world applications.

  • 5 authors
·
Jan 20, 2025

AI Flow at the Network Edge

Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and unprecedented potential. In the era of ubiquitous connectivity, leveraging communication networks to distribute intelligence is a transformative concept, envisioning AI-powered services accessible at the network edge. However, pushing large models from the cloud to resource-constrained environments faces critical challenges. Model inference on low-end devices leads to excessive latency and performance bottlenecks, while raw data transmission over limited bandwidth networks causes high communication overhead. This article presents AI Flow, a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers, making intelligence flow across networks. To facilitate cooperation among multiple computational nodes, the proposed framework explores a paradigm shift in the design of communication network systems from transmitting information flow to intelligence flow, where the goal of communications is task-oriented and folded into the inference process. Experimental results demonstrate the effectiveness of the proposed framework through an image captioning use case, showcasing the ability to reduce response latency while maintaining high-quality captions. This article serves as a position paper for identifying the motivation, challenges, and principles of AI Flow.

  • 2 authors
·
Nov 19, 2024

LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation

Real-time video generation via diffusion is essential for building general-purpose multimodal interactive AI systems. However, the simultaneous denoising of all video frames with bidirectional attention via an iterative process in diffusion models prevents real-time interaction. While existing distillation methods can make the model autoregressive and reduce sampling steps to mitigate this, they focus primarily on text-to-video generation, leaving the human-AI interaction unnatural and less efficient. This paper targets real-time interactive video diffusion conditioned on a multimodal context, including text, image, and audio, to bridge the gap. Given the observation that the leading on-policy distillation approach Self Forcing encounters challenges (visual artifacts like flickering, black frames, and quality degradation) with multimodal conditioning, we investigate an improved distillation recipe with emphasis on the quality of condition inputs as well as the initialization and schedule for the on-policy optimization. On benchmarks for multimodal-conditioned (audio, image, and text) avatar video generation including HDTF, AVSpeech, and CelebV-HQ, our distilled model matches the visual quality of the full-step, bidirectional baselines of similar or larger size with 20x less inference cost and latency. Further, we integrate our model with audio language models and long-form video inference technique Anchor-Heavy Identity Sinks to build LiveTalk, a real-time multimodal interactive avatar system. System-level evaluation on our curated multi-turn interaction benchmark shows LiveTalk outperforms state-of-the-art models (Sora2, Veo3) in multi-turn video coherence and content quality, while reducing response latency from 1 to 2 minutes to real-time generation, enabling seamless human-AI multimodal interaction.

  • 7 authors
·
Dec 29, 2025 3

Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios

As agent systems powered by large language models (LLMs) advance, improving the task performance of an autonomous agent, especially in context understanding, tool usage, and response generation, has become increasingly critical. Although prior studies have advanced the overall design of LLM-based agents, systematic optimization of their internal reasoning and tool-use pipelines remains underexplored. This paper introduces an agent framework grounded in real-world practical experience, with three key innovations: (1) an adaptive prompt generation strategy that aligns with the agent's state and task goals to improve reliability and robustness; (2) a context-aware tool orchestration module that performs tool categorization, semantic retrieval, and adaptive invocation based on user intent and context; and (3) a layered memory mechanism that integrates session memory, task history, and external summaries to improve relevance and efficiency through dynamic summarization and compression. An end-to-end framework named Jenius-Agent has been integrated with three key optimizations, including tools based on the Model Context Protocol (MCP), file input/output (I/O), and execution feedback. The experiments show a 20 percent improvement in task accuracy, along with a reduced token cost, response latency, and invocation failures. The framework is already deployed in Jenius (https://www.jenius.cn), providing a lightweight and scalable solution for robust, protocol-compatible autonomous agents.

  • 6 authors
·
Jan 5

FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill phase, where long-running requests monopolize resources and delay higher-priority ones, leading to widespread time-to-first-token (TTFT) SLO violations. While chunked prefill enables interruptibility, it introduces an inherent trade-off between responsiveness and throughput: reducing chunk size improves response latency but degrades computational efficiency, whereas increasing chunk size maximizes throughput but exacerbates blocking. This necessitates an adaptive preemption mechanism. However, dynamically balancing execution granularity against scheduling overheads remains a key challenge. In this paper, we propose FlowPrefill, a TTFT-goodput-optimized serving system that resolves this conflict by decoupling preemption granularity from scheduling frequency. To achieve adaptive prefill scheduling, FlowPrefill introduces two key innovations: 1) Operator-Level Preemption, which leverages operator boundaries to enable fine-grained execution interruption without the efficiency loss associated with fixed small chunking; and 2) Event-Driven Scheduling, which triggers scheduling decisions only upon request arrival or completion events, thereby supporting efficient preemption responsiveness while minimizing control-plane overhead. Evaluation on real-world production traces shows that FlowPrefill improves maximum goodput by up to 5.6times compared to state-of-the-art systems while satisfying heterogeneous SLOs.

  • 6 authors
·
Feb 18 2

Sustainable LLM Inference using Context-Aware Model Switching

Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference strategy where most systems route every request to the same large model, regardless of task complexity, leading to substantial and unnecessary energy waste. To address this issue, we propose a context-aware model switching approach that dynamically selects an appropriate language model based on query complexity. The proposed system uses a Context-Aware Model Switching for Energy-Efficient LLM Inference that combines caching for repeated queries, rulebased complexity scoring for fast and explainable decisions, machine learning classification to capture semantic intent, and a user-adaptive component that learns from interaction patterns over time. The proposed architecture was evaluated using real conversation workloads and three open-source language models (Gemma3 1B, Gemma3 4B and Qwen3 4B) with different computational costs, measuring energy consumption (via NVML GPU power telemetry), response latency, routing accuracy, and output quality (BERTScore F1) to reflect real-world usage conditions. Experimental results show that the model switching approach can reduce energy consumption by up to 67.5% compared to always using the largest model while maintaining a response quality of 93.6%. In addition, the response time for simple queries also improved significantly by approximately 68%. These results show that model switching inference offers a practical and scalable path toward more energy-efficient and sustainable AI systems, demonstrating that significant efficiency gains can be achieved without major sacrifices in response quality.

  • 6 authors
·
Feb 24

FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications

Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism. Existing serving systems and auto-parallelism compilers commit to limited transformations and fixed workload assumptions, so achieving high performance on a new application requires hand-crafting an efficient implementation. We present FlashRT, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi-GPU deployments that flexibly weigh target metrics like latency and throughput. Using a new chain-of-program paradigm, FlashRT directs a generic coding agent through a multi-pass transformation process where an agent transforms the reference into an intermediate representation (IR) to capture data dependencies and persistent-state scopes, validates this IR via a sequential interpreter, and performs static analyses to identify candidate transformations. Then, the agent iteratively implements, verifies, and benchmarks each candidate under a measurement-gated optimization loop to produce effective deployments that span different hardware budgets. Across various applications, including video world models and multimodal LLMs, FlashRT converts reference implementations into highly efficient deployments, delivering up to ~70x latency reduction and 2.8x throughput improvement on NVIDIA B200 GPUs. On AMD MI355X GPUs, FlashRT matches the peak latency reduction while increasing peak throughput improvement to 3.6x, demonstrating that agent-driven optimization can be more scalable on platforms with less mature expert optimization. In fact, for Qwen3-Omni text-to-audio inference, FlashRT reduces response latency by 65% compared to the expert vLLM-Omni implementation on AMD MI355X.

  • 6 authors
·
Jul 19 2

HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models

As human--AI interactions become more conversational, full-duplex speech language models capable of natural real-time dialogue are growing in importance. Beyond generating appropriate responses, these models must coordinate turn-taking, backchanneling, and floor management in real time. Reinforcement learning (RL) provides a way to refine these behaviors through direct feedback on interaction outcomes. However, existing RL methods either apply timing feedback to a token policy or optimize semantic content, leaving the joint improvement of timing and content unresolved. We introduce HiPLEX, an RL framework that factorizes a pretrained full-duplex text policy into a control policy that decides when to emit content and a conditional content policy that decides what to emit. The first factor selects among 'pad', 'epad', and 'con'. The second selects a token only when 'con' is chosen. This hierarchy describes conditional actions within each frame and uses the model's existing text head. We route timing advantages to the token-group factor through event-causal masks derived from generated speech episodes, and route an LLM-judge semantic advantage to the conditional content factor. Across three Moshi seeds on Full-Duplex-Bench v1, HiPLEX reduces takeover rates during natural user pauses and backchannel opportunities, and shortens post-interruption response latency relative to GRPO, while maintaining comparable judged interruption-response quality. On Moshi and PersonaPlex, HiPLEX better matches pooled human turn-timing and backchannel-rate marginals than GRPO.

DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization

Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long and redundant reasoning even for simple questions, which substantially increases computational cost and response latency. While existing methods incorporate length rewards to GRPO to promote concise reasoning, they incur significant performance degradation. We identify the root cause: when rewards for correct but long rollouts are penalized, GRPO's group-relative advantage function can assign them negative advantages, actively discouraging valid reasoning. To overcome this, we propose Decoupled Reward Policy Optimization (DRPO), a novel framework that decouples the length-based learning signal of correct rollouts from incorrect ones. DRPO ensures that reward signals for correct rollouts are normalized solely within the positive group, shielding them from interference by negative samples. The DRPO's objective is grounded in integrating an optimized positive data distribution, which maximizes length-based rewards under a KL regularization, into a discriminative objective. We derive a closed-form solution for this distribution, enabling efficient computation of the objective and its gradients using only on-policy data and importance weighting. Of independent interest, this formulation is general and can incorporate other preference rewards of positive data beyond length. Experiments on mathematical reasoning tasks demonstrate DRPO's significant superiority over six efficient reasoning baselines. Notably, with a 1.5B model, our method achieves 77\% length reduction with only 1.1\% performance loss on simple questions like GSM8k dataset, while the follow-up baseline sacrifices 4.3\% for 68\% length reduction.

  • 4 authors
·
Oct 6, 2025

Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference

With the rapid advancement of artificial intelligence technologies such as ChatGPT, AI agents, and video generation, contemporary mobile systems have begun integrating these AI capabilities on local devices to enhance privacy and reduce response latency. To meet the computational demands of AI tasks, current mobile SoCs are equipped with diverse AI accelerators, including GPUs and Neural Processing Units (NPUs). However, there has not been a comprehensive characterization of these heterogeneous processors, and existing designs typically only leverage a single AI accelerator for LLM inference, leading to suboptimal use of computational resources and memory bandwidth. In this paper, we first summarize key performance characteristics of heterogeneous processors, SoC memory bandwidth, etc. Drawing on these observations, we propose different heterogeneous parallel mechanisms to fully exploit both GPU and NPU computational power and memory bandwidth. We further design a fast synchronization mechanism between heterogeneous processors that leverages the unified memory architecture. By employing these techniques, we present HeteroInfer, the fastest LLM inference engine in mobile devices which supports GPU-NPU heterogeneous execution. Evaluation shows that HeteroInfer delivers a 1.34x to 6.02x end-to-end speedup over state-of-the-art GPU-only and NPU-only LLM engines, while maintaining negligible interference with other applications.

  • 8 authors
·
Oct 3, 2025 1

Qwen-Audio-Jev: A Unified Interface for Audio Decisions

Large audio language models (LALMs) have made substantial progress in audio understanding. However, in high-throughput applications requiring frequent selection, judgment, and scoring, autoregressive text generation introduces additional computational overhead and response latency. To address this limitation, we introduce Qwen-Audio-Jev by augmenting Qwen-Audio-3.1-ASR-Flash-Next with a dedicated Jev decision head. The model unifies selection, binary judgment, and scoring through three decision primitives: CHOICE, NOUL, and SCORE. Given audio, a natural-language question, and an explicit answer specification, it directly produces a task-conditioned probability distribution or a numerical score through typed decision readouts. Evaluation across 18 labeled configurations covers all three primitives: for CHOICE, Qwen-Audio-Jev achieves accuracies of 78.70% on MMAU-mini and 84.06% on MMSU; for NOUL, it achieves an equal error rate of 6.50% on the VoxCeleb1-O speaker verification benchmark; and for SCORE, the model achieves a normalized mean absolute error of 0.1062 on NISQA overall quality assessment, with Pearson and Spearman correlations of 0.8210 and 0.8074, respectively. Compared with the original Qwen-Audio-3.1-ASR-Flash-Next, Qwen-Audio-Jev achieves an approximately 20x inference speedup. It demonstrates its potential for efficient, high-throughput audio decision-making in applications such as large-scale audio screening, speaker verification, and automated quality assessment.

  • 8 authors
·
Oct 14

Don't Pause! Every prediction matters in a streaming video

Streaming video models should respond the moment an event unfolds, not after the moment has passed. Yet existing online VideoQA benchmarks remain largely retrospective. They pause the video at fixed timestamps, pose questions about current or past events, and score models only at those moments. This protocol leaves streaming predictions untested. To close this gap, we introduce SPOT-Bench, featuring multi-turn proactive queries that evaluate general streaming perception and assistive capabilities required by an always-on, real-time assistant. SPOT-Bench comes with Timeliness-F1, a consolidated metric that measures streaming predictions by their temporal precision and balanced coverage across the entire video. Our benchmark reveals: (i) offline models detect events reliably but spam predictions unprompted; (ii) post-training for silence reduces spamming but induces unresponsiveness; (iii) half of the streaming video expects no response, which we term dead-time - compute spent here does not affect response latency. These findings motivate AsynKV, a training-free streaming adaptation of offline models, that retains their event perception while improving their streaming behavior. AsynKV features a long-short term memory, utilized efficiently by scaling compute during dead-time. It serves as a strong baseline on SPOT-Bench, outperforming existing streaming models, and achieves state-of-the-art on retrospective benchmarks.

  • 5 authors
·
Apr 26

Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds

Visual interaction models that support users during ongoing physical tasks require evaluation in closed loop, where assistant responses can change subsequent user behavior and task outcomes. Existing benchmarks largely rely on offline replay and therefore cannot capture these effects. We introduce Interactive Visual Gym, a framework for closed-loop evaluation and training of visual interaction models through joint simulation of executable task environments and human users. We contribute three simulators that recreate everyday tasks and human-aligned action spaces across cooking, household manipulation, and mobile-interface domains, together with a persona-conditioned user simulation harness that collaborates with the assistant while incorporating controlled execution errors and other out-of-plan behaviors. We instantiate the framework as IVG-Bench, a benchmark with 315 interaction scenarios. Evaluating state-of-the-art VLMs as visual interaction models reveals substantial limitations: the best-performing model, Gemini 4 Argon, completes only 53.4% of tasks within the time limit, exhibits significant weaknesses in factual grounding and actionable guidance, and is often too slow to prevent errors when response latency is considered. We verify our evaluation protocol with a human study which finds 78.5% agreement between our interaction-quality metric and participant preferences. We further show that the environments provide useful learning signals: in a proof-of-concept GRPO experiment, closed-loop training improves both task success and interaction quality for Qwen3.5-4B model in our cooking environment.

  • 14 authors
·
Nov 4 3

Agentic Routing: The Harness-Native Data Flywheel

Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification. At the same time, frontier and open models are becoming structurally specialized: a model that is strong at code editing, long-context recovery, tool use, mathematical reasoning, or low-latency response may not dominate on the other axes. This makes model selection inside an agent a core systems problem rather than a per-query serving trick. Existing routing methods mostly optimize single-turn cost-quality trade-offs and therefore miss the execution state, intermediate failures, and feedback loops that make agents different from chat completion. We propose Harness-Native agentic routing, a step-level routing paradigm that selects either a single best-fit model for cost-effective execution or multiple complementary models for ensemble-style accuracy improvement, conditioned on the full harness state. The key insight is that every routing decision naturally produces a structured data record -- consisting of the query, harness state, model choice or model set, execution trace, outcome, and cost -- whose labels are supplied by the environment rather than by the router itself. These records form a harness-native data flywheel: execution traces train better routers and harness-native models, which improve cost-quality trade-offs and generate more traces under the same budget. We instantiate this idea in OpenSquilla with a four-layer routing stack, an open LightGBM cold-start ranker, and a staged router-model path that turns logged arena records into progressively stronger routing policies. The report studies singleton and multi-model routing on agentic benchmarks including DRACO and PinchBench, and argues that agentic routing is not merely cost control, but a data engine for agent-native training.

  • 15 authors
·
Jul 12

RelayS2S: A Dual-Path Speculative Generation for Real-Time Dialogue

Real-time spoken dialogue systems face a fundamental tension between latency and response quality. End-to-end speech-to-speech (S2S) models respond immediately and naturally handle turn-taking, backchanneling, and interruption, but produce semantically weaker outputs. Cascaded pipelines (ASR -> LLM) deliver stronger responses at the cost of latency that grows with model size. We present RelayS2S, a hybrid architecture that runs two paths in parallel upon turn detection. The fast path -- a duplex S2S model -- speculatively drafts a short response prefix that is streamed immediately to TTS for low-latency audio onset, while continuing to monitor live audio events. The slow path -- a cascaded ASR -> LLM pipeline -- generates a higher-quality continuation conditioned on the committed prefix, producing a seamless utterance. A lightweight learned verifier gates the handoff, committing the prefix when appropriate or falling back gracefully to the slow path alone. Experiments show that RelayS2S achieves P90 onset latency comparable to the S2S model while retaining 99% cascaded response quality in average score, with benefits growing as the slow-path model scales. Because the prefix handoff requires no architectural modification to either component, RelayS2S serves as a lightweight, drop-in addition to existing cascaded pipelines. Our code and data are publicly available at: https://github.com/mailong25/relays2s

  • 1 authors
·
Mar 24

GEB-1.3B: Open Lightweight Large Language Model

Recently developed large language models (LLMs) such as ChatGPT, Claude, and Llama have demonstrated impressive abilities, and even surpass human-level performance in several tasks. Despite their success, the resource-intensive demands of these models, requiring significant computational power for both training and inference, limit their deployment to high-performance servers. Additionally, the extensive calculation requirements of the models often lead to increased latency in response times. With the increasing need for LLMs to operate efficiently on CPUs, research about lightweight models that are optimized for CPU inference has emerged. In this work, we introduce GEB-1.3B, a lightweight LLM trained on 550 billion tokens in both Chinese and English languages. We employ novel training techniques, including ROPE, Group-Query-Attention, and FlashAttention-2, to accelerate training while maintaining model performance. Additionally, we fine-tune the model using 10 million samples of instruction data to enhance alignment. GEB-1.3B exhibits outstanding performance on general benchmarks such as MMLU, C-Eval, and CMMLU, outperforming comparative models such as MindLLM-1.3B and TinyLLaMA-1.1B. Notably, the FP32 version of GEB-1.3B achieves commendable inference times on CPUs, with ongoing efforts to further enhance speed through advanced quantization techniques. The release of GEB-1.3B as an open-source model marks a significant contribution to the development of lightweight LLMs, promising to foster further research and innovation in the field.

  • 4 authors
·
Jun 14, 2024 3

Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response

Large language models (LLMs) promise to accelerate incident response in production systems, yet single-agent approaches generate vague, unusable recommendations. We present MyAntFarm.ai, a reproducible containerized framework demonstrating that multi-agent orchestration fundamentally transforms LLM-based incident response quality. Through 348 controlled trials comparing single-agent copilot versus multi-agent systems on identical incident scenarios, we find that multi-agent orchestration achieves 100% actionable recommendation rate versus 1.7% for single-agent approaches, an 80 times improvement in action specificity and 140 times improvement in solution correctness. Critically, multi-agent systems exhibit zero quality variance across all trials, enabling production SLA commitments impossible with inconsistent single-agent outputs. Both architectures achieve similar comprehension latency (approx.40s), establishing that the architectural value lies in deterministic quality, not speed. We introduce Decision Quality (DQ), a novel metric capturing validity, specificity, and correctness properties essential for operational deployment that existing LLM metrics do not address. These findings reframe multi-agent orchestration from a performance optimization to a production-readiness requirement for LLM-based incident response. All code, Docker configurations, and trial data are publicly available for reproduction.

  • 1 authors
·
Nov 19, 2025

Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation

Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duplex: new observations cannot naturally enter an active generation stream. Proactive alternatives use micro-turn polling or external response gates, which fragment continuous interaction, decouple response timing from language generation, and complicate KV-cache-friendly serving. We introduce Aero Realtime, a 4B streaming multimodal model with a duplex architecture for realtime generation. Aero Realtime aligns video, audio, and textual output on a shared temporal grid, where each approximately 80-ms audio slot predicts either a lexical token or a silence token. This allows input and output to advance together, enabling one autoregressive objective to learn both when to respond and what to generate. During inference, Aero Realtime appends only the newest multimodal slot, carries forward the previous output state, and reuses the KV cache for efficient incremental execution. We further provide a complete training and serving recipe, including realtime QA construction, slot-aligned supervision, hardware-aware distributed training, and resumable inference. On four NVIDIA A6000 workstation GPUs, Aero Realtime maintains 84-ms median and 173-ms P95 processing lag over 20 minutes of a continuously streamed video, remaining within 200~ms of the source timeline. These results demonstrate the feasibility of fully aligned input-output modeling for duplex, proactive, and hardware-aligned multimodal interaction.

  • 5 authors
·
Aug 8

Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs

Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over the traditional autoregressive paradigm. However, this parallelism is constrained by the requirement of a fixed-size response length prior to generation. This architectural limitation imposes a severe trade-off: oversized response length results in computational waste on semantically meaningless padding tokens, while undersized response length causes output truncation requiring costly re-computations that introduce unpredictable latency spikes. To tackle this issue, we propose Predict-then-Diffuse, a simple and model-agnostic framework that enables compute-budgeted inference per input query by first estimating the response length and then using it to run inference with D-LLM. At its core lies an Adaptive Response Length Predictor (AdaRLP), which estimates the optimal response length given an input query. As a measure against under-estimating the response length and re-running inference with a higher value, we introduce a data-driven safety mechanism based on a small increase of the predicted length. As a whole, our framework avoids wasting computation on padding tokens, at the same time preserving output quality. Experimental validation on multiple datasets demonstrates that Predict-then-Diffuse significantly reduces computational costs (FLOP) compared to the default D-LLM inference mechanism, while being robust to skewed data distributions.

  • 3 authors
·
May 13

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although these modes differ in reasoning budget, their delivered responses should satisfy the same user-facing standard. Correctness alone may not characterize this response quality; we therefore evaluate task accuracy and response-pattern failures as complementary outcomes. We study this gap through response-pattern alignment: whether thinking and non-thinking interfaces preserve acceptable final-response behavior. We introduce PatternEval, a failure-enriched diagnostic benchmark comprising 2,415 multimodal prompts spanning visual perception and grounding, structured image understanding, and multimodal knowledge reasoning. PatternEval tests four recurrent failures: chain-of-thought leakage, response repetition, logical contradiction, and performative reasoning. Response-pattern failures are widespread across models from different providers, with non-thinking inference exhibiting substantially higher failure rates and thereby creating systematic misalignment between thinking and non-thinking interfaces. Motivated by this diagnosis, we develop PatternRM, a response-level reward model, and PatternRL, which introduces pattern-specific penalties during reinforcement learning. Experiments on Qwen3-VL-4B and Qwen3-VL-8B show that incorporating pattern-specific penalties into reinforcement learning can mitigate cross-mode misalignment while incurring a marginal task performance trade-off. Together, PatternEval and PatternRL provide an evaluation-and-training framework for aligning user-visible response patterns across hybrid-thinking interfaces.

tencent Tencent
·
Aug 16 7

Probing then Editing Response Personality of Large Language Models

Large Language Models (LLMs) have demonstrated promising capabilities to generate responses that exhibit consistent personality traits. Despite the major attempts to analyze personality expression through output-based evaluations, little is known about how such traits are internally encoded within LLM parameters. In this paper, we introduce a layer-wise probing framework to systematically investigate the layer-wise capability of LLMs in encoding personality for responding. We conduct probing experiments on 11 open-source LLMs over the PersonalityEdit benchmark and find that LLMs predominantly encode personality for responding in their middle and upper layers, with instruction-tuned models demonstrating a slightly clearer separation of personality traits. Furthermore, by interpreting the trained probing hyperplane as a layer-wise boundary for each personality category, we propose a layer-wise perturbation method to edit the personality expressed by LLMs during inference. Our results show that even when the prompt explicitly specifies a particular personality, our method can still successfully alter the response personality of LLMs. Interestingly, the difficulty of converting between certain personality traits varies substantially, which aligns with the representational distances in our probing experiments. Finally, we conduct a comprehensive MMLU benchmark evaluation and time overhead analysis, demonstrating that our proposed personality editing method incurs only minimal degradation in general capabilities while maintaining low training costs and acceptable inference latency. Our code is publicly available at https://github.com/universe-sky/probing-then-editing-personality.

  • 10 authors
·
Apr 14, 2025

Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute increase. Prompt compression, which reduces the size of input prompts while aiming to preserve performance on downstream tasks, has established itself as a cost-effective and low-latency method for accelerating inference in large language models. However, its usefulness depends on whether the additional preprocessing time during generation is offset by faster decoding. We present the first systematic, large-scale study of this trade-off, with thousands of runs and 30,000 queries across several open-source LLMs and three GPU classes. Our evaluation separates compression overhead from decoding latency while tracking output quality and memory usage. LLMLingua achieves up to 18% end-to-end speed-ups, when prompt length, compression ratio, and hardware capacity are well matched, with response quality remaining statistically unchanged across summarization, code generation, and question answering tasks. Outside this operating window, however, the compression step dominates and cancels out the gains. We also show that effective compression can reduce memory usage enough to offload workloads from data center GPUs to commodity cards, with only a 0.3s increase in latency. Our open-source profiler predicts the latency break-even point for each model-hardware setup, providing practical guidance on when prompt compression delivers real-world benefits.

  • 4 authors
·
Apr 2

Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning

Large language models have been extended to the speech domain, leading to the development of speech large language models (SLLMs). While existing SLLMs demonstrate strong performance in speech instruction-following for core languages (e.g., English), they often struggle with non-core languages due to the scarcity of paired speech-text data and limited multilingual semantic reasoning capabilities. To address this, we propose the semi-implicit Cross-lingual Speech Chain-of-Thought (XS-CoT) framework, which integrates speech-to-text translation into the reasoning process of SLLMs. The XS-CoT generates four types of tokens: instruction and response tokens in both core and non-core languages, enabling cross-lingual transfer of reasoning capabilities. To mitigate inference latency in generating target non-core response tokens, we incorporate a semi-implicit CoT scheme into XS-CoT, which progressively compresses the first three types of intermediate reasoning tokens while retaining global reasoning logic during training. By leveraging the robust reasoning capabilities of the core language, XS-CoT improves responses for non-core languages by up to 45\% in GPT-4 score when compared to direct supervised fine-tuning on two representative SLLMs, Qwen2-Audio and SALMONN. Moreover, the semi-implicit XS-CoT reduces token delay by more than 50\% with a slight drop in GPT-4 scores. Importantly, XS-CoT requires only a small amount of high-quality training data for non-core languages by leveraging the reasoning capabilities of core languages. To support training, we also develop a data pipeline and open-source speech instruction-following datasets in Japanese, German, and French.

  • 6 authors
·
Apr 29, 2025

Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling

Interactive agents repeatedly choose among a finite set of actions, labels, or ordinal outcomes. Generating a free-form response for each choice adds latency and complicates the interface between a model and its environment. We present Intern-Decision, a family of 0.8B, 2B, and 4B multimodal decision models that return structured choices and candidate probabilities from text and optional images. Our autoregressive masked language modeling objective places one decision placeholder per field in a complete assistant JSON skeleton. Ground-truth symbols appear only in supervision, while all fields are evaluated in a single causal forward pass using the backbone's native language-model head. The 4B model achieves a 90.02% unweighted average accuracy across seven evaluation suites, compared with 88.74% for Jev v1.13.0. For a fixed 289-token request with three fields on one RTX 4090, mean latency is 44.16 ms for the 4B model and approximately 33--34 ms for the smaller models. On a separate 96-case known-distribution pilot, temperature scaling reduces expected multiclass Brier from 0.628 to 0.550 and expected calibration error from 0.213 to 0.089. A confidence-based handoff study on 111 public Jevbench-Hard items improves accuracy from 82/111 (73.87%) to 97/111 (87.39%) by routing 42 items to Atria-Dawn-Preview. We also describe qualitative game, visual interface, and browser demonstrations. These results support compact decision models as a practical component of larger agent systems.

Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems

Existing long-term personalized dialogue systems struggle to reconcile unbounded interaction streams with finite context constraints, often succumbing to memory noise accumulation, reasoning degradation, and persona inconsistency. To address these challenges, this paper proposes Inside Out, a framework that utilizes a globally maintained PersonaTree as the carrier of long-term user profiling. By constraining the trunk with an initial schema and updating the branches and leaves, PersonaTree enables controllable growth, achieving memory compression while preserving consistency. Moreover, we train a lightweight MemListener via reinforcement learning with process-based rewards to produce structured, executable, and interpretable {ADD, UPDATE, DELETE, NO_OP} operations, thereby supporting the dynamic evolution of the personalized tree. During response generation, PersonaTree is directly leveraged to enhance outputs in latency-sensitive scenarios; when users require more details, the agentic mode is triggered to introduce details on-demand under the constraints of the PersonaTree. Experiments show that PersonaTree outperforms full-text concatenation and various personalized memory systems in suppressing contextual noise and maintaining persona consistency. Notably, the small MemListener model achieves memory-operation decision performance comparable to, or even surpassing, powerful reasoning models such as DeepSeek-R1-0528 and Gemini-3-Pro.

  • 8 authors
·
Jan 8

SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models

Large language models (LLMs) have recently garnered significant accomplishments in various exploratory tasks, even surpassing the performance of traditional reinforcement learning-based methods that have historically dominated the agent-based field. The purpose of this paper is to investigate the efficacy of LLMs in executing real-time strategy war tasks within the StarCraft II gaming environment. In this paper, we introduce SwarmBrain, an embodied agent leveraging LLM for real-time strategy implementation in the StarCraft II game environment. The SwarmBrain comprises two key components: 1) a Overmind Intelligence Matrix, powered by state-of-the-art LLMs, is designed to orchestrate macro-level strategies from a high-level perspective. This matrix emulates the overarching consciousness of the Zerg intelligence brain, synthesizing strategic foresight with the aim of allocating resources, directing expansion, and coordinating multi-pronged assaults. 2) a Swarm ReflexNet, which is agile counterpart to the calculated deliberation of the Overmind Intelligence Matrix. Due to the inherent latency in LLM reasoning, the Swarm ReflexNet employs a condition-response state machine framework, enabling expedited tactical responses for fundamental Zerg unit maneuvers. In the experimental setup, SwarmBrain is in control of the Zerg race in confrontation with an Computer-controlled Terran adversary. Experimental results show the capacity of SwarmBrain to conduct economic augmentation, territorial expansion, and tactical formulation, and it shows the SwarmBrain is capable of achieving victory against Computer players set at different difficulty levels.

  • 4 authors
·
Jan 31, 2024

Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models

The Transformer architecture has become the de facto standard for Large Language Models (LLMs), demonstrating remarkable capabilities in language understanding and generation. However, its application in conversational AI is fundamentally constrained by its stateless nature and the quadratic computational complexity (O(L^2)) with respect to sequence length L. Current models emulate memory by reprocessing an ever-expanding conversation history with each turn, leading to prohibitive costs and latency in long dialogues. This paper introduces the Reactive Transformer (RxT), a novel architecture designed to overcome these limitations by shifting from a data-driven to an event-driven paradigm. RxT processes each conversational turn as a discrete event in real-time, maintaining context in an integrated, fixed-size Short-Term Memory (STM) system. The architecture features a distinct operational cycle where a generator-decoder produces a response based on the current query and the previous memory state, after which a memory-encoder and a dedicated Memory Attention network asynchronously update the STM with a representation of the complete interaction. This design fundamentally alters the scaling dynamics, reducing the total user-facing cost of a conversation from quadratic (O(N^2 cdot T)) to linear (O(N cdot T)) with respect to the number of interactions N. By decoupling response generation from memory updates, RxT achieves low latency, enabling truly real-time, stateful, and economically viable long-form conversations. We validated our architecture with a series of proof-of-concept experiments on synthetic data, demonstrating superior performance and constant-time inference latency compared to a baseline stateless model of comparable size.

ReactiveAI Reactive AI
·
Oct 3, 2025 2

Clairvoyant: Predictive SJF Scheduling to Mitigate Head-of-Line Blocking in Serial LLM Backends

Serial LLM inference backends -- such as Ollama -- process requests one at a time under FCFS admission, causing Head-of-Line Blocking (HOLB) under mixed workloads at high utilisation: short factual queries can be delayed by minutes behind long generation jobs. While cloud-scale deployments mitigate HOLB via continuous batching (vLLM, Orca), these solutions require tens of GB of VRAM for concurrent KV-caches -- infeasible for memory-constrained edge and local deployments that rely on serial request dispatch. We present \clairvoyant, a drop-in sidecar proxy for any serial OpenAI-compatible backend (e.g., Ollama, llama.cpp). \clairvoyant predicts response length from 19 lightweight lexical features via an ONNX-exported XGBoost classifier, achieving 0.029\,ms per-request latency (four orders of magnitude below typical generation time). Because admission scheduling depends on relative ordering rather than exact prediction, the system optimises ranking fidelity, achieving 62--96\% in-distribution and 52--66\% cross-distribution accuracy across natural conversation datasets. We find that curated instruction datasets are degenerate training sources for length prediction: GPT-imposed brevity constraints reduce Long-class representation to under 0.02\% of examples, making natural conversation logs the only viable training source. End-to-end GPU benchmarks on an RTX~4090 show 70--76\% P50 latency reduction for short requests under maximum queue pressure (100 concurrent requests) and 17\% under steady-state Poisson arrivals (ρ=0.74). \clairvoyant is open-source and requires no modifications to the inference backend.

  • 1 authors
·
Jun 4

AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models

Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves reasoning and audio understanding, but generating intermediate reasoning tokens delays responses. Describing fine-grained acoustic cues further lengthens CoT and increases latency. Latent reasoning can reduce this overhead, yet existing methods often trail CoT and remain limited by single-path supervision and reasoning budgets that do not adapt to problem difficulty. We introduce AURAL, which models a distribution over multiple plausible reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and reasoning latency. To provide initial supervision for latent reasoning, we construct AuralReason-683K: 683K bilingual speech utterances (about 1,000 hours) with concise CoT for emotion recognition, empathetic dialogue, and general reasoning. AURAL-RL then explores beyond these traces, rewarding concise reasoning that yields high-quality answers and adapting reasoning effort to each problem. Across two backbones, AURAL-RL achieves performance comparable to CoT-RL, with larger gains over the respective supervised checkpoints on most metrics. Analysis further shows that harder questions elicit more latent reasoning steps. On Qwen2.5-Omni, it reduces time to the first answer token by 11.8x, from 1.22 to 0.10 s, versus 0.05 s for direct answering.

  • 15 authors
·
Sep 30

IC-Cache: Efficient Large Language Model Serving via In-context Caching

Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-world studies reveal that over 70% of user requests to LLMs have semantically similar counterparts, suggesting the potential for knowledge transfer among requests. However, naively caching and reusing past responses leads to a big quality drop. In this paper, we introduce IC-Cache, a caching system that enables live LLM capability augmentation to improve serving efficiency: by leveraging historical request-response pairs from larger models as in-context examples, IC-Cache empowers small LLMs to imitate and even exceed the compositional abilities (e.g., reasoning) of their larger counterparts, enabling selective offloading of requests to reduce cost and latency. Achieving this live augmentation at scale introduces intricate trade-offs between response quality, latency, and system throughput. For a new request, IC-Cache efficiently selects similar, high-utility examples to prepend them to the new request's input. At scale, it adaptively routes requests across LLMs of varying capabilities, accounting for response quality and serving loads. IC-Cache employs a cost-aware cache replay mechanism that refines example quality offline to maximize online cache utility and efficiency. Evaluations on millions of realistic requests demonstrate that IC-Cache improves LLM serving throughput by 1.4-5.9x and reduces latency by 28-71% without hurting response quality.

  • 10 authors
·
Jan 22, 2025

ExtremControl: Low-Latency Humanoid Teleoperation with Scaled Velocity Feedforward

Building a low-latency humanoid teleoperation system is essential for collecting diverse reactive and dynamic demonstrations. However, end-to-end latencies in existing approaches consistently hover around 200ms, roughly equal to human reaction time, that severely limits responsiveness and prevents tasks requiring rapid feedback. We identify position-only PD control as the root cause of this latency floor and propose ExtremControl, a low-latency whole-body control framework that: (1) incorporates scaled velocity feedforward in low-level control, reducing tracking delay by approximately 70ms with a provably optimal feedforward ratio; (2) operates directly on SE(3) poses of selected rigid links, primarily humanoid extremities, to avoid joint-space retargeting in the control loop. To minimize retargeting time, we derive a closed-form Cartesian-space mapping that uses a single anthropomorphic calibration step to translate human motion into humanoid link targets, accommodating operators with varying body proportions. Furthermore, we provide a theoretical framework for selecting control hyperparameters, and validate the effectiveness of velocity feedforward control in the reinforcement learning for locomotion setting through experiments in both simulation and the real world. Building on ExtremControl, we implement a teleoperation system supporting both optical motion capture and VR-based tracking, achieving end-to-end latency as low as 50ms --- well beneath the threshold at which system delay adds a full human reaction cycle to the control loop. This enables a qualitatively new class of reactive behaviors, including ping-pong ball balancing, juggling, and real-time return, that are beyond the capability of existing teleoperation systems.

  • 6 authors
·
Oct 20

Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark

Rapid advancements in large language models (LLMs) have increased interest in deploying them on mobile devices for on-device AI applications. Mobile users interact differently with LLMs compared to desktop users, creating unique expectations and data biases. Current benchmark datasets primarily target at server and desktop environments, and there is a notable lack of extensive datasets specifically designed for mobile contexts. Additionally, mobile devices face strict limitations in storage and computing resources, constraining model size and capabilities, thus requiring optimized efficiency and prioritized knowledge. To address these challenges, we introduce Mobile-MMLU, a large-scale benchmark dataset tailored for mobile intelligence. It consists of 16,186 questions across 80 mobile-related fields, designed to evaluate LLM performance in realistic mobile scenarios. A challenging subset, Mobile-MMLU-Pro, provides advanced evaluation similar in size to MMLU-Pro but significantly more difficult than our standard full set. Both benchmarks use multiple-choice, order-invariant questions focused on practical mobile interactions, such as recipe suggestions, travel planning, and essential daily tasks. The dataset emphasizes critical mobile-specific metrics like inference latency, energy consumption, memory usage, and response quality, offering comprehensive insights into model performance under mobile constraints. Moreover, it prioritizes privacy and adaptability, assessing models' ability to perform on-device processing, maintain user privacy, and adapt to personalized usage patterns. Mobile-MMLU family offers a standardized framework for developing and comparing mobile-optimized LLMs, enabling advancements in productivity and decision-making within mobile computing environments. Our code and data are available at: https://github.com/VILA-Lab/Mobile-MMLU.

  • 9 authors
·
Mar 26, 2025

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

Advanced Large Language Models (LLMs) have achieved impressive performance across a wide range of complex and long-context natural language tasks. However, performing long-context LLM inference locally on a commodity GPU (a PC) with privacy concerns remains challenging due to the increasing memory demands of the key-value (KV) cache. Existing systems typically identify important tokens and selectively offload their KV data to GPU and CPU memory. The KV data needs to be offloaded to disk due to the limited memory on a commodity GPU, but the process is bottlenecked by token importance evaluation overhead and the disk's low bandwidth. In this paper, we present LeoAM, the first efficient importance-aware long-context LLM inference system for a single commodity GPU with adaptive hierarchical GPU-CPU-Disk KV management. Our system employs an adaptive KV management strategy that partitions KV data into variable-sized chunks based on the skewed distribution of attention weights across different layers to reduce computational and additional transmission overheads. Moreover, we propose a lightweight KV abstract method, which minimizes transmission latency by storing and extracting the KV abstract of each chunk on disk instead of the full KV data. LeoAM also leverages the dynamic compression and pipeline techniques to further accelerate inference. Experimental results demonstrate that LongInfer achieves an average inference latency speedup of 3.46x, while maintaining comparable LLM response quality. In scenarios with larger batch sizes, it achieves up to a 5.47x speedup.

  • 4 authors
·
Jun 25, 2025

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing inference runtimes are designed mainly for request-response serving and therefore do not satisfy the runtime contract of embodied deployment: multi-rate execution inside closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible embodied interfaces beyond fixed token I/O. We present Embodied.cpp, a portable C++ inference runtime for embodied models. Based on an architectural analysis of representative VLA models and WAMs, Embodied.cpp captures a shared execution path and organizes it into five layers: input adapters, sequence builders, backbone execution, head plugins, and deployment adapters. The runtime provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support, enabling deployment across heterogeneous devices, robots, and simulators through one backend abstraction. We evaluate Embodied.cpp on two VLA models, HY-VLA and pi0.5, and on a preliminary WAM benchmark using a LingBot-VA Transformer block. The VLA deployments achieve successful closed-loop execution with 100.0% and 91.0% task success rates, respectively. The WAM benchmark reduces block memory from 312.2 MiB to 88.1 MiB. These results show that Embodied.cpp improves deployment efficiency while preserving high accuracy across diverse embodied model architectures.

SteerDuplex: Steerable Duplex Speech Dialogue Models

Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplored: steerability, the ability to reliably shift conversational behavior along attributes such as tone, persona, speaking rate, and voice style in response to user instructions. We introduce a taxonomy of text- and audio-based steerability that identifies substantial gaps in current full-duplex models. To address this gap, we introduce SteerDuplex, a Moshi-based full-duplex speech model fine-tuned on natural conversations and synthetic dialogues targeting instruction following, vocal delivery, reasoning, and duplex interaction. We further apply two-stage reinforcement learning (RL) with hybrid rewards, combining verifiable interaction checks and judge-based semantic feedback to improve timing and response continuity. To evaluate full-duplex spoken steerability, we introduce SteerBench, a benchmark with 390 spoken prompts and 1,067 human-authored binary audio and text rubrics spanning tone, persona, style/accent, and speed/length. On SteerBench, supervised training improves audio-steering average pass rate by 44.5 percentage points over the strongest evaluated open baseline. On Audio MultiChallenge, task average pass rate improves by 7 points over its strongest evaluated open baseline. RL further raises source-clean interruption response from 72.5% to 82.5% and reduces synthetic pause barge-in from 26.5% to 9%. Steering and aggregate task scores remain comparable or higher, while reward probes reveal reward hacking through incomplete responses. Our model and benchmark support systematic research on spoken steerability, with reward analysis showing why timing gains must be evaluated alongside response completeness.

ScaleAI Scale AI
·
Sep 10 2

Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation

Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in dynamic financial environments. To address these challenges, Retrieval-Augmented Generation (RAG) models have emerged as a powerful solution, combining retrieval-based methods with generative capabilities to enhance response quality. In this study, we present a Retrieval-Augmented Generation (RAG) system designed to generate responses related to stock market information. The system integrates retrieval-based and generative approaches to enhance the accuracy and relevance of financial text generation. To evaluate its effectiveness, we employ the ROUGE metric, specifically ROUGE-1, ROUGE-2, and ROUGE-L, to measure lexical and structural similarity between generated and reference texts. Experimental results on a dataset of 100 stock market-related queries demonstrate high ROUGE scores, indicating strong alignment with reference documents. Additionally, we assess latency to evaluate the system responsiveness, achieving an average response time of 1.16 seconds. These findings confirm that our RAG model is capable of providing accurate and timely stock market insights, making it a promising approach for financial information retrieval.

  • 6 authors
·
Nov 1 2

MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understanding

Medical image understanding with vision-language models (VLMs) typically relies on autoregressively generating reasoning and answer tokens. These unnecessary tokens make the inference cost scale with the response length and force the answer to be parsed from free-form text, incurring avoidable latency and decision errors. To this end, we introduce MedJev, a system one vision-language decision model that maps medical images, questions, and candidate answers directly to decisions in a single multimodal forward pass, without any autoregressive generation process. For fast inference, MedJev removes the upper language layers and the generative output pathway, while keeping the full vision pathway and all visual tokens. On this shortened backbone, a decision head scores each candidate by pretrained query--key matching and refines the scores with a lightweight multilayer perceptron (MLP) residual, coupling the pretrained matching structure with task-specific nonlinear discrimination. Built on Qwen3.5-4B, MedJev-4B improves both accuracy and speed over the original model on each of four medical image classification and visual question answering benchmarks, with an absolute accuracy gain of 7.93\% and a 6.04times end-to-end speedup. Further comparison with 20 cutting-edge models shows that MedJev-4B achieves state-of-the-art performance and inference speed among 4B--9B general and medical VLMs, indicating that direct multimodal decision making is an effective route to fast and effective medical image understanding.

Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI

AI Video Chat emerges as a new paradigm for Real-time Communication (RTC), where one peer is not a human, but a Multimodal Large Language Model (MLLM). This makes interaction between humans and AI more intuitive, as if chatting face-to-face with a real person. However, this poses significant challenges to latency, because the MLLM inference takes up most of the response time, leaving very little time for video streaming. Due to network uncertainty and instability, transmission latency becomes a critical bottleneck preventing AI from being like a real person. To address this, we propose Artic, an AI-oriented Real-time Communication framework, exploring the network requirement shift from "humans watching video" to "AI understanding video". To reduce bitrate dramatically while maintaining MLLM accuracy, we propose Context-Aware Video Streaming that recognizes the importance of each video region for chat and allocates bitrate almost exclusively to chat-important regions. To avoid packet retransmission, we propose Loss-Resilient Adaptive Frame Rate that leverages previous frames to substitute for lost/delayed frames while avoiding bitrate waste. To evaluate the impact of video streaming quality on MLLM accuracy, we build the first benchmark, named Degraded Video Understanding Benchmark (DeViBench). Finally, we discuss some open questions and ongoing solutions for AI Video Chat.

  • 4 authors
·
Jul 14, 2025 2

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking process before responding. In contrast, humans typically engage in complex mental reasoning internally, enabling them to communicate ideas clearly and concisely. Thus, integrating an unspoken thought process into SLMs is highly desirable. While naively generating a complete chain-of-thought (CoT) reasoning before starting to talk can enable thinking for SLMs, this induces additional latency for the speech response, as the CoT reasoning can be arbitrarily long. To solve this issue, we propose Stitch, a novel generation method that alternates between the generation of unspoken reasoning chunks and spoken response chunks. Since the audio duration of a chunk of spoken response is much longer than the time to generate the tokens in a chunk of spoken response, we use the remaining free time to generate the unspoken reasoning tokens. When a chunk of audio is played to the user, the model continues to generate the next unspoken reasoning chunk, achieving simultaneous thinking and talking. Remarkably, Stitch matches the latency of baselines that cannot generate unspoken CoT by design while outperforming those baselines by 15% on math reasoning datasets; Stitch also performs equally well on non-reasoning datasets as those baseline models. Some animations and demonstrations are on the project page: https://d223302.github.io/STITCH.

  • 10 authors
·
Jul 21, 2025 1

Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference

Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on these models, by design, harnesses a temporal dependency, where the current token's probability distribution is conditioned on preceding tokens. This inherent characteristic severely impedes computational efficiency during inference as a typical inference request can require more than thousands of tokens, where generating each token requires a load of entire model weights, making the inference more memory-bound. The large overhead becomes profound in real deployment where requests arrive randomly, necessitating various generation lengths. Existing solutions, such as dynamic batching and concurrent instances, introduce significant response delays and bandwidth contention, falling short of achieving optimal latency and throughput. To address these shortcomings, we propose Flover -- a temporal fusion framework for efficiently inferring multiple requests in parallel. We deconstruct the general generation pipeline into pre-processing and token generation, and equip the framework with a dedicated work scheduler for fusing the generation process temporally across all requests. By orchestrating the token-level parallelism, Flover exhibits optimal hardware efficiency and significantly spares the system resources. By further employing a fast buffer reordering algorithm that allows memory eviction of finished tasks, it brings over 11x inference speedup on GPT and 16x on LLAMA compared to the cutting-edge solutions provided by NVIDIA FasterTransformer. Crucially, by leveraging the advanced tensor parallel technique, Flover proves efficacious across diverse computational landscapes, from single-GPU setups to distributed scenarios, thereby offering robust performance optimization that adapts to variable use cases.

  • 7 authors
·
May 22, 2023

FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data

The growing demand for data-driven decision-making has created an urgent need for data agents that can integrate structured and unstructured data for analysis. While data agents show promise for enabling users to perform complex analytics tasks, this field still suffers from three critical limitations: first, comprehensive data agent benchmarks remain absent due to the difficulty of designing test cases that evaluate agents' abilities across multi-source analytical tasks; second, constructing reliable test cases that combine structured and unstructured data remains costly and prohibitively complex; third, existing benchmarks exhibit limited adaptability and generalizability, resulting in narrow evaluation scope. To address these challenges, we present FDABench, the first data agent benchmark specifically designed for evaluating agents in multi-source data analytical scenarios. Our contributions include: (i) we construct a standardized benchmark with 2,007 diverse tasks across different data sources, domains, difficulty levels, and task types to comprehensively evaluate data agent performance; (ii) we design an agent-expert collaboration framework ensuring reliable and efficient benchmark construction over heterogeneous data; (iii) we equip FDABench with robust generalization capabilities across diverse target systems and frameworks. We use FDABench to evaluate various data agent systems, revealing that each system exhibits distinct advantages and limitations regarding response quality, accuracy, latency, and token cost.

  • 7 authors
·
Sep 2, 2025

Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings

Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities through multiple dialogues and multi-modal data sources. These unique characteristics of LLMs, together with their large model size, make their deployment more challenging. Specifically, (i) deploying LLMs on local devices faces computational, memory, and energy resource issues, while (ii) deploying them in the cloud cannot guarantee real-time service and incurs communication/usage costs. In this paper, we design TMO, a local-cloud LLM inference system with Three-M Offloading: Multi-modal, Multi-task, and Multi-dialogue. TMO incorporates (i) a lightweight local LLM that can process simple tasks at high speed and (ii) a large-scale cloud LLM that can handle multi-modal data sources. We develop a resource-constrained reinforcement learning (RCRL) strategy for TMO that optimizes the inference location (i.e., local vs. cloud) and multi-modal data sources to use for each task/dialogue, aiming to maximize the long-term reward (response quality, latency, and usage cost) while adhering to resource constraints. We also contribute M4A1, a new dataset we curated that contains reward and cost metrics across multiple modality, task, dialogue, and LLM configurations, enabling evaluation of offloading decisions. We demonstrate the effectiveness of TMO compared to several exploration-decision and LLM-as-Agent baselines, showing significant improvements in latency, cost, and response quality.

  • 4 authors
·
Dec 29, 2025

Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans

Existing co-speech gesture generation methods are predominantly studied in offline settings, where gestures are synthesized from complete speech segments. However, interactive digital humans in real-world scenarios are required to generate speech-synchronous gestures online, using only currently available response audio under strict latency constraints. As a result, prior methods are unsuitable for real-time interaction, as they either rely on future speech information or incur substantial inference delay. In this paper, we formulate online co-speech gesture generation for interactive digital humans and propose a real-time interactive framework that couples a streaming speech response module with an online gesture generation module. Specifically, the gesture generator is designed as a causal multimodal autoregressive model that predicts body motion from streaming response speech and motion history, enabling low-latency and speech-aligned gesture synthesis without access to future speech. To support this setting, we further propose an offline data synthesis pipeline tailored to virtual companion scenarios, which leverages topic- and emotion-aware subject corpora to construct diverse human-agent dialogues and then generates co-speech gestures conditioned on the agent responses. Moreover, to bridge the gap between offline data construction and online deployment, we establish a self-evolving training loop by incorporating user feedback collected during online interaction into the data generation process, enabling continual adaptation to user preferences. Extensive experiments demonstrate that our framework achieves superior better latency-quality trade-off, stronger speech-motion synchronization, and higher user preference than competitive existing baselines. Project Page: https://super-star-2026.github.io/

  • 7 authors
·
Jul 21 1

Leveraging Interpretability in the Transformer to Automate the Proactive Scaling of Cloud Resources

Modern web services adopt cloud-native principles to leverage the advantages of microservices. To consistently guarantee high Quality of Service (QoS) according to Service Level Agreements (SLAs), ensure satisfactory user experiences, and minimize operational costs, each microservice must be provisioned with the right amount of resources. However, accurately provisioning microservices with adequate resources is complex and depends on many factors, including workload intensity and the complex interconnections between microservices. To address this challenge, we develop a model that captures the relationship between an end-to-end latency, requests at the front-end level, and resource utilization. We then use the developed model to predict the end-to-end latency. Our solution leverages the Temporal Fusion Transformer (TFT), an attention-based architecture equipped with interpretability features. When the prediction results indicate SLA non-compliance, we use the feature importance provided by the TFT as covariates in Kernel Ridge Regression (KRR), with the response variable being the desired latency, to learn the parameters associated with the feature importance. These learned parameters reflect the adjustments required to the features to ensure SLA compliance. We demonstrate the merit of our approach with a microservice-based application and provide a roadmap to deployment.

  • 3 authors
·
Sep 3, 2024

Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models

Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: listen chunks leave compute idle while awaiting audio, and speak and tool-call chunks require serial generation, which delays responses and tool calls. Using the idle compute for the next chunk requires decoding it before its audio arrives, under an assumed input. Taking silence as the assumed input and comparing the output with the output under real audio on four models, we observe two properties. First, the next audio chunk does not change the output in 95.3% of chunks. Second, 88% of changes begin at the first output token. Building on these properties, we propose Speculative Listening, a training-free, lossless framework for input-time self-speculative decoding. During idle time, the model drafts the next chunk under silence and, for changes at the first token, a second branch from the runner-up first token. It keeps all drafts in a cross-chunk hypothesis pool and verifies them when the audio arrives. On our eight-task benchmark TickTock-Bench, Speculative Listening speeds up speak chunks by 2.6-2.8x and tool-call chunks by up to 23.4x. On average, it reduces the decoding delay before a response starts by 73%, to 74-241 ms, close to the 200 ms gap between human turns, and the maximum lag behind real time by 94.4%.

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models

Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the RL infrastructure, slows training, and makes training curriculum (e.g., response length extension) and hyperparameter selection challenging. In this work, we propose cascaded domain-wise reinforcement learning (Cascade RL) to develop general-purpose reasoning models, Nemotron-Cascade, capable of operating in both instruct and deep thinking modes. Departing from conventional approaches that blend heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL, reducing engineering complexity and delivering state-of-the-art performance across a wide range of benchmarks. Notably, RLHF for alignment, when used as a pre-step, boosts the model's reasoning ability far beyond mere preference optimization, and subsequent domain-wise RLVR stages rarely degrade the benchmark performance attained in earlier domains and may even improve it (see an illustration in Figure 1). Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6/Pro and achieves silver-medal performance in the 2025 International Olympiad in Informatics (IOI). We transparently share our training and data recipes.

nvidia NVIDIA
·
Dec 15, 2025 1

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies are either target-misaligned, incapable of few-step generation, or too costly to scale. We propose Causal Forcing++, a principled and scalable pipeline that uses causal consistency distillation (causal CD) for few-step AR initialization. The core idea is that causal CD learns the same AR-conditional flow map as causal ODE distillation, but obtains supervision from a single online teacher ODE step between adjacent timesteps, avoiding the need to precompute and store full PF-ODE trajectories. This makes the initialization both more efficient and easier to optimize. The resulting pipeline, \ours, surpasses the SOTA 4-step chunk-wise Causal Forcing under the \textbf{frame-wise 2-step setting} by 0.1 in VBench Total, 0.3 in VBench Quality, and 0.335 in VisionReward, while reducing first-frame latency by 50\% and Stage 2 training cost by sim4times. We further extend the pipeline to action-conditioned world model generation in the spirit of Genie3. Project Page: https://github.com/thu-ml/Causal-Forcing and https://github.com/shengshu-ai/minWM .

DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents

Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation, termed as 1) Latency Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm induces severe end-to-end latency. Intuitively, dLLMs can leverage their distinctive strengths to optimize the operational efficiency of agents under the ReAct agent paradigm. Practically, existing dLLM backbones face the 2) Agent Ability Challenge. That is, existing dLLMs exhibit remarkably weak reasoning and tool-calling capabilities, preventing these advantages from being effectively realized in practice. In this paper, we propose DLLM-Searcher, an optimization framework for dLLM-based Search Agents. To solve the Agent Ability Challenge, we design a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning (Agentic SFT) and Agentic Variance-Reduced Preference Optimization Agentic VRPO, which enhances the backbone dLLM's information seeking and reasoning capabilities. To mitigate the Latency Challenge, we leverage the flexible generation mechanism of dLLMs and propose a novel agent paradigm termed Parallel-Reasoning and Acting P-ReAct. P-ReAct guides the model to prioritize decoding tool_call instructions, thereby allowing the model to keep thinking while waiting for the tool's return. Experimental results demonstrate that DLLM-Searcher achieves performance comparable to mainstream LLM-based search agents and P-ReAct delivers approximately 15% inference acceleration. Our code is available at https://anonymous.4open.science/r/DLLM-Searcher-553C

Artic: AI-oriented Real-time Communication for MLLM Video Assistant

AI Video Assistant emerges as a new paradigm for Real-time Communication (RTC), where one peer is a Multimodal Large Language Model (MLLM) deployed in the cloud. This makes interaction between humans and AI more intuitive, akin to chatting with a real person. However, a fundamental mismatch exists between current RTC frameworks and AI Video Assistants, stemming from the drastic shift in Quality of Experience (QoE) and more challenging networks. Measurements on our production prototype also confirm that current RTC fails, causing latency spikes and accuracy drops. To address these challenges, we propose Artic, an AI-oriented RTC framework for MLLM Video Assistants, exploring the shift from "humans watching video" to "AI understanding video." Specifically, Artic proposes: (1) Response Capability-aware Adaptive Bitrate, which utilizes MLLM accuracy saturation to proactively cap bitrate, reserving bandwidth headroom to absorb future fluctuations for latency reduction; (2) Zero-overhead Context-aware Streaming, which allocates limited bitrate to regions most important for the response, maintaining accuracy even under ultra-low bitrates; and (3) Degraded Video Understanding Benchmark, the first benchmark evaluating how RTC-induced video degradation affects MLLM accuracy. Prototype experiments using real-world uplink traces show that compared with existing methods, Artic significantly improves accuracy by 15.12% and reduces latency by 135.31 ms. We will release the benchmark and codes at https://github.com/pku-netvideo/DeViBench.

  • 5 authors
·
Feb 13

Harnessing Streaming Video in the Wild

Vision-Language Models (VLMs) are increasingly required to process unbounded video streams in applications such as video-call assistants, live commentary, and embodied robots. An ideal streaming system should support proactive interaction, long-horizon memory, and real-time processing, while resting on a VLM backbone capable of handling diverse in-the-wild streaming tasks. However, existing VLMs excel at offline video understanding but fall short in streaming capabilities and lack dedicated infrastructure for streaming deployment. We address this gap on three fronts. (i) For backbone capability, we construct Streaming-Train-248K, a streaming dataset paired with a novel training objective for adapting VLMs to streaming interaction and understanding. (ii) For real-world deployment, we introduce Streaming Harness, a plug-and-play system that endows any VLM with three core abilities: proactive interaction (per-second response decisions), long-term memory (12-hour context retention), and real-time processing (sub-second latency). (iii) To drive continued community progress on streaming capabilities, we design Streaming-Eval, a benchmark that reflects models' capabilities across diverse in-the-wild scenarios. Extensive experiments demonstrate consistent gains from our approach across all core capabilities required for streaming video understanding. We will open-source our data, code, and benchmark to advance the community's shift from offline video understanding to deployable streaming intelligence.

  • 11 authors
·
Jun 6

Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency

While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist policies, such as VLAs, poses a fundamental obstacle to effective RL improvement. In particular, their severe inference latency---which can lead to pauses or jerky movements---can alter the effective environment dynamics and, if not correctly accounted for, break the Markov assumption that RL relies on, causing standard RL algorithms to fail completely. In this work, we introduce a latency-aware framework, Asynchronous RL with Intermediate Information (ARLI), that enables RL-based improvement of generalist policies under inference delays. Our framework builds on asynchronous inference approaches, which interleave action generation with execution to hide latency, and addresses its incompatibility with RL by providing a low-latency RL policy design that maximizes reactivity within the inference window through two contributions: state augmentations that restore near-Markovian structure by incorporating committed actions and a mid-inference observation. We evaluate our approach across simulated and real-world manipulation tasks, and find that it enables effective finetuning under inference delays where standard RL fails entirely, even matching or exceeding the performance of standard RL in idealized no-latency settings.

  • 20 authors
·
Aug 25