English(EN)Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
新研究推进机器人和推理的视觉-语言-动作模型 · 跟踪9个来源
作者PulseAugur 编辑部·[15 个来源]·
多篇研究论文探讨了视觉-语言-动作（VLA）模型的进展，重点在于提高其鲁棒性、可解释性和效率。一篇论文介绍了JADE，一种联合去噪方法，使视觉语言模型和动作专家能够更紧密地协作，从而提高机器人任务的性能。另一篇论文JPTA提出了一个通过将文本原型视为语义参考来稳健地进行VLM归纳适应的框架，这些参考会根据批次可靠性进行调整。SD-LoRA专注于少样本适应，在训练过程中将结构信息提炼到轻量级模型中。此外，还在进行有关大型视觉语言模型安全审计、开发集成操作和认知能力的具身视觉语言模型（如Concertina）以及创建用于预测和分类VLA模型故障的方法（如VLA-Tug）的研究。最后，引入了一个名为MPRBench的基准来评估多模态个性化推理能力。
AI
arXiv:2605.17204v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from langua…
arXiv:2611.06993v1 Announce Type: cross Abstract: Transductive adaptation improves vision-language models at test time by refining predictions on an unlabeled batch, but current methods face a key trade-off. Aggressive approaches exploit batch structure but can drift when batches…
arXiv:2611.07063v1 Announce Type: cross Abstract: Few-shot adaptation of vision-language models must balance two competing goals: learning fine-grained visual distinctions from very limited supervision and preserving the efficiency that makes frozen CLIP-like models attractive fo…
arXiv cs.AI
TIER_1English(EN)·Hong kyu Lee, Kai Shu, Li Xiong·
arXiv:2611.07216v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning. Recent alignment methods report strong scores …
arXiv:2611.07513v1 Announce Type: cross Abstract: Most vision-language-action (VLA) policies decouple manipulation from cognition by bolting an external action mechanism onto a vision-language model (VLM)--either quantizing actions into discrete tokens whose errors bear no stable…
arXiv cs.AI
TIER_1English(EN)·Michal P. Podolinsky, Yunhao Yang, Daniel Little, Hong Lu, Rohan Siva, Olin Goudey, Neel P. Bhatt, Matthias Scheutz, Ufuk Topcu·
arXiv:2611.08425v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) enable general-purpose embodied intelligence, but their performance is brittle under distribution shift, where unanticipated failures can damage equipment or endanger people. Deploying VLAs in …
arXiv:2611.06259v1 Announce Type: new Abstract: People often make decisions by holistically reasoning over heterogeneous forms of personal information. In this paper, we study the relatively underexplored capability of multimodal personalized reasoning in multimodal large languag…
arXiv:2611.05565v1 Announce Type: cross Abstract: Contrastive vision-language models score left/right relations near chance, but the symptom has two causes that call for opposite repairs: the relation may survive in the pooled embedding yet be unreachable by native image-text sim…
People often make decisions by holistically reasoning over heterogeneous forms of personal information. In this paper, we study the relatively underexplored capability of multimodal personalized reasoning in multimodal large language models (MLLMs). To this end, we introduce \tex…
Vision-language verifiers judge whether an image faithfully matches a textual description, yet existing training pipelines typically rely on static supervision from stronger external judges or curated hard-negative data. Such supervision requires external generation or annotation…
SIMIT is a test-time framework that lets vision-language models generate their own practice data to improve answers on unlabeled queries without external annotations.
arXiv:2611.06918v1 Announce Type: new Abstract: Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals mos…
