3 papers
cs.CV2026
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
Jinlong Li, Liyuan Jiang, Haonan Zhang +1
Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame…
cs.CV2025
FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation
Dong Zhao, Jinlong Li, Shuang Wang +4
Vision Foundation Models (VFMs) excel in generalization due to large-scale pretraining, but fine-tuning them for Domain Generalized Semantic Segmentation (DGSS) while maintaining t…
cs.CV2025
Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding
Jinlong Li, Cristiano Saltori, Fabio Poiesi +1
The lack of a large-scale 3D-text corpus has led recent works to distill open-vocabulary knowledge from vision-language models (VLMs). However, these methods typically rely on a si…