3 papers
cs.LG2026
Cache-Aware Conv3D Lowering Across Embedded World-Model Decoders
Jiaming Zhang, Wu Yang, Shuai Tao +1
Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model but also on how the execution…
cs.CV2026
PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding
Siru Zhong, Qiongyan Wang, Xiaohui Lv +5
Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens, or alter internal key-value…
cs.RO2026
LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models
Lin Liu, Zhicheng Bao, Lu Zhang +7
Vision-Language-Action (VLA) or World Action (WAM) models have recently demonstrated remarkable performance in robotic manipulation. On LIBERO, SOTA method have achieved nearly 100…