Fan Yang

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

Thyme: Think Beyond Images

Beyond Text-Only: Towards Multimodal Table Retrieval in Open-World

Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model

OmniCVR: A Benchmark for Omni-Composed Video Retrieval with Vision, Audio, and Text

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning

InstructEngine: Instruction-driven Text-to-Image Alignment

Unifying Reinforcement Learning and Distillation via Distribution Matching for Video Generation

SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation

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

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

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

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

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

EVLM: An Efficient Vision-Language Model for Visual Understanding