Senqiao Yang

Multimodal Dataset Distillation via Phased Teacher Models

Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs

Consistency Beyond Contrast: Enhancing Object Detection Robustness through Scene-Augmented Feature Alignment

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs