arXiv AI
MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 22
SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists
arXiv:2609.22854v1 Announce Type: cross Abstract: Vision-language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually i...
arXiv Computer Vision
3d ago
D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
arXiv:2609.34792v2 Announce Type: replace Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-actio...
arXiv AI
2d ago
Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies
arXiv:2610.00982v1 Announce Type: cross Abstract: Vision-language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the acti...
arXiv AI
Jul 29
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.
arXiv AI
Jun 8
Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation
arXiv:2603. 24576v2 Announce Type: replace-cross Abstract: Robots often observe information that determines a future action long before that action is executed.
arXiv AI
Sep 1
AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies
arXiv:2608.29537v1 Announce Type: cross Abstract: Frozen vision-language-action (VLA) policies offer broad manipulation skills but execute open-loop action chunks without tracking task progress, so t...