8 papers
Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
Zhiwei Yang, Yuanchen Wu, Nan Zhang +3
Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structu…
Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models
Enguang Wang, Qiang Wang, Yuanchen Wu +5
While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear…
Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
Yuanchen Wu, Ke Yan, Shouhong Ding +2
Large Vision-Language Models (LVLMs) have manifested strong visual question answering capability. However, they still struggle with aligning the rationale and the generated answer,…
See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
Ziyun Dai, Xiaoqiang Li, Shaohua Zhang +2
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in visual understanding and multimodal reasoning. However, LVLMs frequently exhibit hallucination phe…
AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models
Ziyin Zhou, Yunpeng Luo, Yuanchen Wu +7
The rapid development of AI-generated content (AIGC) technology has led to the misuse of highly realistic AI-generated images (AIGI) in spreading misinformation, posing a threat to…
Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
Yuanchen Wu, Lu Zhang, Hang Yao +5
Large Vision-Language Models (LVLMs) have achieved impressive results across various cross-modal tasks. However, hallucinations, i.e., the models generating counterfactual response…
ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts
Yuanchen Wu, Junlong Du, Ke Yan +2
Vision-language (VL) learning requires extensive visual perception capabilities, such as fine-grained object recognition and spatial perception. Recent works typically rely on trai…
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation
Yuanchen Wu, Xichen Ye, Kequan Yang +2
Recently, One-stage Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained increasing interest due to simplification over its cumbersome multi-stage coun…