National University of Singapore

university

Verified

https://www.nus.edu.sg/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

ttu1818 authored a paper 4 days ago

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

ttu1818 submitted a paper 4 days ago

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

filicos submitted a paper 5 days ago

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

View all activity

Papers

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction

View all Papers

NationalUniversityofSingapore 's Papers 38

Submitted by

Siao Tang

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

NationalUniversityofSingapore

National University of Singapore

Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction

NationalUniversityofSingapore

National University of Singapore

Submitted by

Haiquan Lu

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

NationalUniversityofSingapore

National University of Singapore

Submitted by

zhifei

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

NationalUniversityofSingapore

National University of Singapore

Submitted by

Hao Fei

Audio-Visual Intelligence in Large Foundation Models

NationalUniversityofSingapore

National University of Singapore

Submitted by

Li Bobo

Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zigeng Chen

DMax: Aggressive Parallel Decoding for dLLMs

NationalUniversityofSingapore

National University of Singapore

Submitted by

yyyang404

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

NationalUniversityofSingapore

National University of Singapore

Submitted by

Mingzhe Du

Paper Espresso: From Paper Overload to Research Insight

NationalUniversityofSingapore

National University of Singapore

4

Submitted by

Zhanzhi Lou

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

NationalUniversityofSingapore

National University of Singapore

Submitted by

Fengyuan Yang

ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

NationalUniversityofSingapore

National University of Singapore

2

Submitted by

Zhenxiong Tan

Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers

NationalUniversityofSingapore

National University of Singapore

Submitted by

qiuhong shen

Make Geometry Matter for Spatial Reasoning

NationalUniversityofSingapore

National University of Singapore

Submitted by

LIQIIIII

Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

NationalUniversityofSingapore

National University of Singapore

Submitted by

Ruonan Yu

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

NationalUniversityofSingapore

National University of Singapore

Submitted by

Liu Tiedong

Can Vision-Language Models Solve the Shell Game?

NationalUniversityofSingapore

National University of Singapore

Submitted by

Yiran Zhao

In-Context Reinforcement Learning for Tool Use in Large Language Models

NationalUniversityofSingapore

National University of Singapore

UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark

NationalUniversityofSingapore

National University of Singapore

Submitted by

Weilong Yan

LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency

NationalUniversityofSingapore

National University of Singapore

Submitted by

Sicheng Feng

dVoting: Fast Voting for dLLMs

NationalUniversityofSingapore

National University of Singapore

Submitted by

Tianyi Wu

Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model

NationalUniversityofSingapore

National University of Singapore

Submitted by

Wenzheng Zeng

Factorized Learning for Temporally Grounded Video-Language Models

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zhenxiong Tan

SpotEdit: Selective Region Editing in Diffusion Transformers

NationalUniversityofSingapore

National University of Singapore

Submitted by

Wenzheng Zeng

SlideTailor: Personalized Presentation Slide Generation for Scientific Papers

NationalUniversityofSingapore

National University of Singapore

Submitted by

Kong

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

NationalUniversityofSingapore

National University of Singapore

Submitted by

Nuo Chen

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

NationalUniversityofSingapore

National University of Singapore

Submitted by

Xingyi Yang

Vision Bridge Transformer at Scale

NationalUniversityofSingapore

National University of Singapore

Submitted by

Xinyin Ma

In-Video Instructions: Visual Signals as Generative Control

NationalUniversityofSingapore

National University of Singapore

Submitted by

Haofeng Liu

SAM2S: Segment Anything in Surgical Videos via Semantic Long-term Tracking

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zhi Zheng

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

NationalUniversityofSingapore

National University of Singapore

Submitted by

Jinjie Ni

Diffusion Language Models are Super Data Learners

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zhiyuan Liu

EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zhang Chen

RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems

NationalUniversityofSingapore

National University of Singapore

Submitted by

Qiran Zou

FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zhenxiong Tan

MixReasoning: Switching Modes to Think

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zigeng Chen

dParallel: Learnable Parallel Decoding for dLLMs

NationalUniversityofSingapore

National University of Singapore

Submitted by

Zijian Wu

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

NationalUniversityofSingapore

National University of Singapore

Submitted by

Sicheng Feng

Efficient Reasoning Models: A Survey

NationalUniversityofSingapore

National University of Singapore