17 papers
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
Bowen Yuan, Zijian Wang, Yadan Luo +2
Large vision-language models (LVLMs) exhibit strong reasoning ability but suffer from visual forgetting during long-horizon decoding, where attention progressively drifts away from…
Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data
Shijie Wang, Yadan Luo, Zijian Wang +3
This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration N…
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
Shijie Wang, Zijian Wang, Yadan Luo +3
Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic ye…
AnchorVLA: Anchored Diffusion for Efficient End-to-End Mobile Manipulation
Jia Syuen Lim, Zhizhen Zhang, Peter Bohm +3
A central challenge in mobile manipulation is preserving multiple plausible action models while remaining reactive during execution. A bottle in a cluttered scene can often be appr…
OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
Zhuoxiao Chen, Hongyang Yu, Ying Xu +3
Radiology report generation (RRG) aims to automatically produce clinically faithful reports from chest X-ray images. Prevailing work typically follows a scale-driven paradigm, by m…
MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent
Yuxia Fu, Zhizhen Zhang, Yuqi Zhang +3
Recent Vision-Language-Action (VLA) models reformulate vision-language models by tuning them with millions of robotic demonstrations. While they perform well when fine-tuned for a…