Creating deformable assets for robot manipulation requires jointly specifying their geometry, appearance, and physical properties. This is especially challenging for deformable objects, since text and images provide limited evidence about how they deform and respond to contact, yet these responses directly affect their...
This work introduces FlashBack, a training-free framework for selective, multi-level memory in streaming vision-language models, and shows improvements on several long-horizon and memory-dependent tasks while largely preserving real-time perception.
Yi Chen, Ming-Ming Yu, Rui-Qi Wang et al.· 0 citations
ReflectWorld-MM is proposed, an entity-oriented multimodal memory system for open-ended video streams that achieves the best accuracy on all six long-video and lifelong-memory benchmarks, outperforming strong memory agents and a frontier model.
Xiaokang Ma, Yifan Sun, Zhihong Jin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.