大模型竟对五条腿的狗视而不见？这项研究用溯因偏好学习破解提示不敏感难题。
arXiv:2510.09887v3 Announce Type: replace Abstract: Vision and language models frequently ignore semantically critical input edits, defaulting to pret…
提出GrAInS方法，利用梯度归因在推理时精准引导LLM/VLM行为，无需微调，更灵活高效。
arXiv:2507.18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large languag…
OpenAI前研究员田永龙加盟腾讯，VLM研发有望提速
据包袋，OpenAI前研究员YonglongTian（田永龙）已于近期加入腾讯大语言模型部，后续将参与VLM（视觉语言模型）相关研发。（财联社）
京东发布工业级商品理解系统Oxygen AIIC V1，基于LLM/VLM处理数十亿SKU，提升电商运营效率与用户体验。
arXiv:2606.28070v1 Announce Type: new Abstract: JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and mill…
医学影像遇上视觉大模型，Wasserstein对齐定位让分布外检测更可靠，MICCAI 2026前沿研究。
arXiv:2605.05161v2 Announce Type: replace Abstract: Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for …
多模态大模型安全新方案：提出动态推理的政策自适应护栏，应对VLMs在消费、医疗等场景的部署风险。
arXiv:2606.22873v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterpr…
临床AI评测翻车？提示词框架竟能制造“多模态能力”假象，看清这项研究避免误判。
arXiv:2603.28387v2 Announce Type: replace Abstract: Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rathe…
病理性VLM新突破：跨尺度推理让病理图像理解更精准，细节更丰富。
arXiv:2606.17412v1 Announce Type: cross Abstract: Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from gl…
自动化选择视觉语言模型预训练方案，提升多模态任务效率
arXiv:2502.00241v2 Announce Type: replace-cross Abstract: Incorporating multiple modalities into large language models (LLMs) is a powerful way to enh…
首个金融多模态越狱检测数据集FENCE，揭示VLM脆弱性并填补资源空白。
arXiv:2602.18154v2 Announce Type: replace-cross Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and …
大模型幻觉检测新突破：密度岭选择性预测方法解决校准标签稀缺难题，提升检测可靠性
arXiv:2606.10198v1 Announce Type: cross Abstract: Hallucination detection in large language and vision-language models is increasingly framed as selec…
首个系统评估大模型在多种格式下表格理解能力的基准TABVERSE，揭示模型在处理跨格式表格时的缺陷与改进空间。
arXiv:2606.09578v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table r…
多教师知识蒸馏为自动驾驶VLM减负，兼顾GPU内存与推理延迟。
arXiv:2601.21288v2 Announce Type: replace Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have…
状态感知视觉语言模型，让机器人理解物体“能做什么”，推动具身智能新进展
arXiv:2605.03927v2 Announce Type: replace Abstract: Vision-language models (VLMs) have shown remarkable performance in various robotic tasks, as they …
用高斯过程提升大型视觉语言模型的语义不确定性量化能力，带来更可靠的评估方法。
arXiv:2512.14177v3 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust…
结合多通道脑电图波形图像，用规则基础的视觉语言模型实现可解释的睡眠分期，让AI推理透明可审计。
arXiv:2603.26738v3 Announce Type: replace Abstract: While automated sleep staging has achieved expert-level accuracy, its clinical adoption is hindere…
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…