Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders
Jie Ma, Zongxi Liu, Yi Zhu
Vision-language models (VLMs), such as CLIP, have achieved strong performance across multimodal tasks by aligning visual and textual representations in a shared embedding space. As…
cs.CV2026
Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perception
Sheng Xu, Enshu Wang, Hongfei Xue +6
Collaborative perception allows connected vehicles to overcome occlusions and limited viewpoints by sharing sensory information. However, existing approaches struggle to achieve hi…