Wengang Zhou

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Primary-Fine Decoupling for Action Generation in Robotic Imitation

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

T2G-Reasoner: Deep Reasoning for Text-to-Gloss Translation

Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling

Envision the Future in Open-World Dynamic Tasks by a Hierarchical World Model with Residual Enhanced Foresight

ScaleWeaver: Weaving Efficient Controllable T2I Generation with Multi-Scale Reference Attention

Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation

Uni-Sign: Toward Unified Sign Language Understanding at Scale

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling

Robust Multimodal Large Language Models Against Modality Conflict

EG4D: Explicit Generation of 4D Object without Score Distillation

Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering

Super Robot View Transformer

MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning