arXiv Computer Vision October 28, 2026 By Jiabing Yang, Yixiang Chen, Yuan Xu, Peiyan Li, Zichen Wen, Bowen Fang, Chenhang Cui, Tao Yu, Qisen Ma, Kai Wang, Ziheng He, Wen Ye, Xiangnan Wu, Yingda Li, Yan Huang, Liang Wang

AWARE: Action-Entropy-Weighted and Attention-Guided Retrieval of Observation Evidence for Vision-Language-Action Models

Read the original on arXiv Computer Vision →

AWARE is a plug‑in module for Vision‑Language‑Action models that retrieves observation evidence without extra training. It tracks uncertainty via Action Entropy, uses associative memory to fetch relevant features, and weights them with instruction‑guided attention, scaling the injection by entropy and depth. Experiments on LIBERO, SIMPLER, CALVIN, and real‑world robot tasks show consistent performance gains, especially on long‑horizon tasks, with negligible computational cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jul 3

VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment

arXiv:2607. 01586v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because existing models often differ in architecture, data, action space, and evaluation protocol.

By Guoyang Xia, Fengfa Li, Hongjin Ji, Lei Ren, Fangxiang Feng, Kun Zhan, Yan Xie

robotics multimodal benchmarks safety

arXiv AI

Oct 27

Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models

arXiv:2610.34251v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown remarkable success in robotic manipulation, yet their ability to execute long-horizon tasks remains limi...

By Xinyu Liu, Daiying Tian, Chenwei Tang, Ruyang Han, Chengyang Zhang, Qingyu Zeng, Wei Ju, Liangli Zhen, Jiancheng Lv

robotics multimodal benchmarks

arXiv Machine Learning

Jul 8

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

arXiv:2607. 06370v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.

By Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, Daichi Fujiki

diffusion robotics efficiency multimodal

arXiv Machine Learning

Aug 4

ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

arXiv:2607. 06370v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.

By Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, Daichi Fujiki

robotics efficiency multimodal

arXiv AI

Jun 29

S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

arXiv:2606. 27872v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, but their performance degrades significantly in long-horizon tasks due to cumulative error propagation.

By Zhipeng Xie, Zongyi Han, Xiangyi Wei, Shiliang Sun, Yang Li, Jing Zhao

robotics multimodal benchmarks

arXiv AI

Jun 19

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

arXiv:2606. 20246v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.

By Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha, Khoa Vo, Philip Lund M{\o}ller, Quang T. Nguyen, Long Dinh, Tuan Dam, Vu Duong, Tung M. Luu, Trung Le, Tran Nguyen Le, Minh Vu, An Thai Le, Ngan Le, Daniel Sonntag, James Zou, Jan Peters, Duy M. H. Nguyen, Ngo Anh Vien

robotics fine-tuning multimodal benchmarks safety

One email a morning, machine-written

Related stories

VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment

Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think