4 papers
DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding
Jianfei Zhao, Feng Zhang, Xin Sun +3
Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, th…
Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
Jianfei Zhao, Feng Zhang, Xin Sun +2
Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We ob…
ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
Jianghao Chen, Wei Sun, Qixiang Yin +2
Long-form generation has become a critical and challenging application for Large Language Models (LLMs). Existing studies are limited by their reliance on scarce, high-quality long…
Cross-Layer Vision Smoothing: Enhancing Visual Understanding via Sustained Focus on Key Objects in Large Vision-Language Models
Jianfei Zhao, Feng Zhang, Xin Sun +2
Large Vision-Language Models (LVLMs) can accurately locate key objects in images, yet their attention to these objects tends to be very brief. Motivated by the hypothesis that sust…