5 papers
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
Jizhihui Liu, Ruizi Han, Miao Zhang +4
Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory…
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding
Chang Liu, Henghui Ding, Nikhila Ravi +40
This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, whi…
Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Models
Zhiming Liu, Yujie Wei, Lei Feng +5
Current VLMs have demonstrated capabilities across a wide range of multimodal tasks. Typically, in a pretrained VLM, all layers are engaged by default to make predictions on downst…
ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation
Weisheng Dai, Kai Lan, Jianyi Zhou +5
Vision-Language-Action (VLA) models achieve preliminary generalization through pretraining on large scale robot teleoperation datasets. However, acquiring datasets that comprehensi…
HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
Jizhihui Liu, Feiyi Du, Guangdao Zhu +5
Vision-Language Models (VLMs) encode images and videos into abundant tokens, which contain substantial redundancy and computation cost. While visual token pruning mitigates the iss…