3 citations · 3 across the 10 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
Jianke Zhang, Yuanfei Luo, Yucheng Hu +6
Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe system…
cs.CV2025
Diff-Feat: Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification
Tian Lan, Yiming Zheng, Jianxin Yin
Multi-label classification has broad applications and depends on powerful representations capable of capturing multiple interactions. We introduce Diff-Feat, a simple yet effective…