4 papers
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Liu Yu, Can Chen, Ping Kuang +3
Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination. Deviating from the prevailing attention intensity assumption, w…
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Yucheng Li, Huiqiang Jiang, Yang Xu +14
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-To…
Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
Liu Yu, Zhonghao Chen, Ping Kuang +4
Object hallucination remains a critical challenge in Large Vision-Language Models (LVLMs), where models generate content inconsistent with visual inputs. Existing language-decoder…
Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences
Liu Yu, Ludie Guo, Ping Kuang +1
Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external…