Di ZHANG

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

Unified In-Context Video Editing

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter

Towards Subject-Consistent and Text-Aligned Personalized Image Generation via Precise Attribute Learning

FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation

Interpreting Any Condition to Caption for Controllable Video Generation

Physical Dynamics as Next Geometric Graph Prediction

Efficient Training-Free High-Resolution Synthesis with Energy Rectification in Diffusion Models

PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis

OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

Flow-GRPO: Training Flow Matching Models via Online RL

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Stable Segment Anything Model

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

Improving Video Generation with Human Feedback

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Motion Inversion for Video Customization

Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance

Geometric Spatiotemporal Transformer to Simulate Long-Term Physical Dynamics

Kinda-45M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content

Explicit-Constrained Single Agent for Enhanced Task-Solving in LLMs

DMQR-RAG: Diverse Multi-Query Rewriting in Retrieval-Augmented Generation

Recipes for Unbiased Reward Modeling Learning: An Empirically Study

Generate explorative goals with large language model guidance

EVLM: An Efficient Vision-Language Model for Visual Understanding