arXiv AI August 25, 2026 By Farida Mohsen, Thowayba Elkaffash, Mohammad Reza Chalak Qazani, Mohamed Mabrok, Nader Meskin, Ali Safa

Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Experts

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv AI

Aug 13

G0.5: One Autoregressive Stream for Robot Reasoning and Action

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.

By Yicheng Liu, Zibin Dong, Baijun Ye, Tianyuan Yuan, Tao Jiang, Anqi Yang, Shicheng Cao, Haonan Liu, Yue Sun, Zihan Guo, Xiao Liu, Dong Ke, Changxun Pan, Chenru Wu, Tailai Cheng, Xiaoshu Ren, Xinlei Zhang, Jianning Cui, Zijie Zhao, Haoyu Zhang, Kaiming Xu, Haodong Yang, Bowen Zhang, Jiahui Niu, Shaoting Zhu, Shiduo Zhang, Hang Zhao

llms nlp robotics fine-tuning multimodal benchmarks

arXiv AI

Aug 6

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

arXiv:2511. 15669v3 Announce Type: replace-cross Abstract: Does Chain-of-Thought (CoT) reasoning genuinely improve Vision Language Action (VLA) models, or does it merely add overhead?

By Cheng Yin, Yankai Lin, Wang Xu, Sikyuen Tam, Xiangrui Zeng, Zhiyuan Liu, Zhouping Yin

reinforcement-learning robotics fine-tuning multimodal safety

arXiv AI

Jun 9

CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models

arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.

By Zhi Liu

llms reinforcement-learning fine-tuning multimodal benchmarks safety

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.

By Minhyeok Lee, Chiyoung Kim, Chanhoe Gu, Seongrok Kim, Sanghyuk Roy Choi, Donghwan Hwang, Donghun Ryu, Seokhyun Kim

robotics efficiency multimodal benchmarks

arXiv AI

Aug 18

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory

arXiv:2608. 16889v1 Announce Type: cross Abstract: Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task.

By Bingxin Xu, Yuzhang Shang, Emilio Ferrara

llms agents robotics multimodal benchmarks

arXiv AI

Jun 26

WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation

arXiv:2606. 26443v1 Announce Type: cross Abstract: A robot working alongside people must reason about what they have done, in what order, and with what intent.

By Baiqi Li, Ce Zhang, Yu Fang, Yue Yang, Shangzhe Li, Mingyu Ding, Gedas Bertasius

llms agents robotics multimodal benchmarks

One email a morning, machine-written

Related stories

G0.5: One Autoregressive Stream for Robot Reasoning and Action

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models

CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory

WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation