12 papers
Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos
Ke Li, Di Wang, Yongshan Zhu +5
Remote sensing visual grounding (RSVG) aims to localize a referred target in a remote sensing image or video according to a natural language expression. Existing RSVG methods usual…
Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants
Luyao Zhang, Ke Li, Yuan Ding +9
Quadruped robots are capable of traversing a wide range of complex terrains with high flexibility. As highly mobile ground-based intelligent platforms, they can be equipped with mo…
VideoAgent: Personalized Synthesis of Scientific Videos
Xiao Liang, Bangxin Li, Zixuan Chen +5
The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narr…
Improving Few-Shot Change Detection Visual Question Answering via Decision-Ambiguity-guided Reinforcement Fine-Tuning
Fuyu Dong, Ke Li, Di Wang +5
Change detection visual question answering (CDVQA) requires answering text queries by reasoning about semantic changes in bi-temporal remote sensing images. A straightforward appro…
CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency
Xiao Liang, Yuxuan An, Di Wang +4
Medical Vision-Language Models (VLMs) are prone to hallucinations, compromising clinical reliability. While reinforcement learning methods like Group Relative Policy Optimization (…
Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
Xiao Liang, Chenxi Liu, Zhi Ma +4
Medical Vision-Language Models (MedVLMs) show immense promise in clinical applicability. However, their reliability is hindered by hallucinations, where models often fail to derive…