Wenhu Chen

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

UniVideo: Unified Understanding, Generation, and Editing for Videos

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

VisCoder2: Building Multi-Language Visualization Coding Agents

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

Verl-Tool: Towards Holistic Agentic Reinforcement Learning with Tool Use

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

VideoScore2: Think before You Score in Generative Video Evaluation

PhyX: Does Your Model Have the "Wits" for Physical Reasoning?

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning

Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining

MoCha: Towards Movie-Grade Talking Character Generation

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

General-Reasoner: Advancing LLM Reasoning Across All Domains

Harnessing Webpage UIs for Text-Rich Visual Understanding

VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations

TC-Bench: Benchmarking Temporal Compositionality in Conditional Video Generation