13 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…
Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
Shijie Wang, Yadan Luo, Zijian Wang +2
Fine-grained image retrieval (FGIR) typically relies on supervision from seen categories to learn discriminative embeddings for retrieving unseen categories. However, such supervis…
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…
Learning to Synergize Semantic and Geometric Priors for Limited-Data Wheat Disease Segmentation
Shijie Wang, Zijian Wang, Yadan Luo +3
Wheat disease segmentation is fundamental to precision agriculture but faces severe challenges from significant intra-class temporal variations across growth stages. Such substanti…
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…