1
2
Caption Bottleneck Models
提出Caption Bottleneck模型，通过瓶颈模块压缩视觉特征并生成描述，在ECCV 2026上展现多模态理解新范式。
arXiv:2607.00578v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide interpretability by routing predictions through a layer of hu…
3
Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data
自我中心视角下的VLA模型微调，融合人类与机器人数据，拓展具身智能新思路。
arXiv:2606.08107v1 Announce Type: cross Abstract: Robotics faces a fundamental challenge of data scarcity. Unlike language or vision research, there i…
4
Domain Adaptation with a Single Vision-Language Embedding
利用单一视觉语言嵌入实现高效域适应，方法简洁且效果显著。
arXiv:2410.21361v2 Announce Type: replace-cross Abstract: Domain adaptation has been extensively investigated in computer vision but still requires ac…
5
Contrastive Representation Regularization for Vision-Language-Action Models
提出对比表示正则化方法，有效提升VLA模型在机器人操作中对动作信号的敏感性，弥补现有表示缺陷。
arXiv:2510.01711v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by …
6
Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation
利用视觉信号增强视觉-语言模型令牌级不确定性估计，提升生成稳健性，前沿研究值得关注。
arXiv:2605.27136v1 Announce Type: new Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) f…
7
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
自动驾驶VLA模型在传感器扰动下推理脆弱性被揭穿，最新论文揭示其可靠性隐患
arXiv:2605.21446v1 Announce Type: cross Abstract: Interpretable autonomous driving planners depend not only on generating explanations, but also on th…
8
Leveraging Vision-Language Models to Detect Attention in Educational Videos
用视觉-语言模型实时检测学生走神，让远程教育更懂你的专注力
arXiv:2605.20211v1 Announce Type: new Abstract: Educational videos are a cornerstone of remote and blended learning. However, learners' fluctuating at…