Robots operating in real-world environments must in general be able to recognize previously unseen objects. As robotic systems move toward open-world autonomy, there is a growing, yet largely unmet, need for open vocabulary object detectors that are prompt-free and efficient enough for continuous deployment.
arXiv:2608. 08308v1 Announce Type: cross Abstract: Modern vision systems must operate in "open-world" settings, where models must recognize known categories and detect unseen or anomalous content.
arXiv:2607. 23924v1 Announce Type: cross Abstract: Vision foundation models have enabled strong training-free anomaly detection (AD).
arXiv:2606. 28385v1 Announce Type: cross Abstract: Recent advances in robot world models enable synthetic video generation for embodied prediction and planning.
Vision foundation models have enabled strong training-free anomaly detection (AD). However, most existing approaches rely primarily on independent local patch features, leaving the global contextual information encoded by Vision Transformers (ViTs) underexploited.
arXiv:2606. 01992v1 Announce Type: cross Abstract: Industrial anomaly detection has historically been a unimodal task.
arXiv:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?
arXiv:2608. 03231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies promise general robotic manipulation, but their robustness against physical-world attacks remains fragile.
arXiv:2608. 11739v1 Announce Type: cross Abstract: The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert.
Assessing proxemic danger from a robot's egocentric perspective is critical for safe embodied navigation in human environments and requires both visual and contextual reasoning. We evaluate three opensource vision-language models (VLMs) (\textit{InternVL}, \textit{Qwen-VL}, and \textit{SmolVLM}) on the classification of egocentric robot images into four danger levels, comparing three prompting strategies and two rounds of QLoRA fine-tuning against a stratified random baseline.
arXiv:2512. 20014v3 Announce Type: replace-cross Abstract: While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects.
arXiv:2605. 31119v2 Announce Type: replace-cross Abstract: In robotics, dangers and adversity modes are often embodiment-specific and relative to each agent.
Open-world object detection (OWOD) requires a detector to recognize known categories, discover unnamed objects from unseen categories, and incrementally learn newly annotated classes. PROB improves unknown discovery by modeling class-agnostic probabilistic objectness in the decoder-query space.