new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Nov 5

Submitted by

Paranioar

From Pixels to Actions - Towards Native Vision-Language-Action Policies

mmlab-ntu

1

Submitted by

Kangverse

GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling

AlayaLab

Submitted by

XiangnanW

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

·
23 authors

Submitted by

taesiri

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

·
72 authors

Submitted by

JokerJan

What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?

CASIA

Chinese Academic of Science Institute of Automation

Submitted by

xiwenyoumu

PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data

DAGroup-PKU

2

Submitted by

Dunge0nMaster

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

Tencent-Hunyuan

Tencent Hunyuan

Submitted by

imkenLuo

StreamDuo: A Live Commentator and a Research Agent for Unseen Games

AlayaLab

Submitted by

jgkwak

Solv3R: 3D Looped Transformer as a Multi-view Solver

·
5 authors

Submitted by

junbrro

Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs

kaist-ai

Submitted by

Luo-Yihong

VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

·
3 authors

Submitted by

vkvermaa

MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation

IITK

Indian Institute of Technology, Kanpur

Submitted by

Zhengdong-Hu

VideoMemBench: How Well Do MLLMs Remember in Video Conversations?

·
7 authors

Submitted by

ismailelyamany

AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds

·
6 authors

1

Submitted by

junzhang98

SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding

Qwen

Submitted by

AIPeanutman

VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing

tencent

Submitted by

Juseon

TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens

DISLab

Data Intelligence System Lab

1

Submitted by

mscheong

LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

Seoul National University

Submitted by

Qiiiiiiiii

PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World

·
10 authors

1

Submitted by

peiranW

SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?

antgroup

1

Submitted by

AustinXiao

VeriSpoof: Beyond Real or Fake with One Audio LLM

unimelb-hf

The University of Melbourne

Submitted by

hannayukhymenko

How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates

swiss-ai

Swiss AI Initiative

Submitted by

hqeric

Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

MicrosoftResearch

Microsoft Research

Submitted by

ZachW

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

ByteDance

Submitted by

ChenDY

NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers

SketchX

Submitted by

razmars

Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting

SequentialLearning

The Sequential Learning Group

Submitted by

cszhilu1998

UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling

·
8 authors

2

Submitted by

shahafvl

GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats

The Hebrew University of Jerusalem

1