为自动驾驶场景设计带距离标注的交通感知问答数据集，评估VLM空间推理能力
arXiv:2511.13397v2 Announce Type: replace-cross Abstract: The remarkable progress of Vision-Language Models (VLMs) on a variety of tasks has raised in…
这篇论文提出了模块化后训练框架，将视觉语言模型适配到自动驾驶安全关键事件的异常检测，融合元数据、LLM描述与VQA及CoT推理，提升准确性。
arXiv:2603.18178v2 Announce Type: replace Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-cr…
最新研究揭示视觉语言模型在真实视频游戏中的表现，挑战其感知与空间导航能力
arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are …
新型方法让视觉语言模型突破3D密集几何感知瓶颈，实现高效深度估计。
arXiv:2605.15876v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited i…
VLMs靠轻量投影器映射视觉特征，但早期层对齐不足浪费深度，论文提出深度预对齐方案解决此缺陷。
arXiv:2605.15300v1 Announce Type: new Abstract: Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight…
揭示视觉语言模型语言压倒视觉导致幻觉的根源，提出几何去偏方法提升可靠性。
arXiv:2605.08245v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imag…
用多模态AI大模型突破RISC-V供应链异构数据分析，打通视觉与文本的芯片溯源新范式
arXiv:2605.15223v1 Announce Type: cross Abstract: This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-L…
无需手动筛选视觉令牌，LRCP利用低秩可压缩性自动剪枝，大幅提升LVLMs推理效率，尤其适合高分辨率图像与长视频场景。
arXiv:2605.15621v1 Announce Type: new Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost…
研究揭示视觉语言模型在追踪连续路径时的隐藏缺陷，诊断失败根源。
arXiv:2605.15672v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lac…
多智能体协调+闭环反馈，让大模型从“纸上谈兵”走向真正能扛事的机器人操作，零样本表现比开环方案靠谱一大截。
arXiv:2602.16898v5 Announce Type: replace-cross Abstract: Task planning for robotic manipulation with large language models (LLMs) is an emerging area…
首次实现统一原则训练的具身基础模型，将理解、推理、想象、动作联合优化于单一VLM中，打破独立专家系统架构，性能超越同等规模模型。具身智能迈入真正统一范式。
arXiv:2605.15153v1 Announce Type: cross Abstract: We present Pelican-Unified 1.0, the first embodied foundation model trained according to the princip…