EXPO-FT is a system that enables stable, sample‑efficient reinforcement learning fine‑tuning of pretrained Vision‑Language‑Action (VLA) policies. It achieves perfect success on a range of manipulation tasks—such as routing string lights, striking a pool ball, and inserting a flower into a wine bottle—using only about 19.1 minutes of online robot data. The approach outperforms both RL-from-scratch and existing VLA fine‑tuning methods, and the authors provide an open‑source codebase to support wider adoption.
By Perry Dong, Kuo-Han Hung, Tian Gao, Dorsa Sadigh, Chelsea Finn
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
By Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn
arXiv:2609.38616v1 Announce Type: cross
Abstract: While Vision-Language-Action (VLA) models enable flexible action generation, their generalization across diverse environmental elements, including ma...
By Yanyan Zhang, Disheng Liu, Xinpeng Li, Chaoda Song, Mohsen Hariri, Debargha Ganguly, Wang Yang, Kai Ye, Bryce Grant, Vipin Chaudhary, Yu Yin
NavGen introduces a text-to-video data generation pipeline that creates about 400K vision‑language navigation episodes for both indoor and outdoor scenes, using high‑fidelity visual generative models. The approach includes a style‑diversification method to scale up rare, hard‑to‑collect data. Models trained on NavGen data outperform those trained on existing UAV navigation datasets and achieve a 75% success rate in real‑world flying experiments.
By Xijie Huang, Yongyang Wan, Chengbin Dong, Zimo Ding, Mo Zhu, Yijin Wang, Zhiyang Liu, Fei Gao, Yuze Wu, Xin Zhou
arXiv:2603. 04976v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.
By Xiongkun Linghu, Jiangyong Huang, Baoxiong Jia, Siyuan Huang
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
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.
By Xionghao Wu, Yijun Yang, Shiyang Zhou, Haoze Sun, Jianhui Liu, Songsong Yu, Jiyao Zhang, Wenbo Li, Bo Wang, Guoqing Ma, Lin Song, Renjie Liao, Shenghe Zheng, Wei Tang, Xiaojuan Qi, Yanwei Li, Yuan Zhang, Zhuotao Tian, Haoyang Huang, Nan Duan
arXiv:2608. 07267v1 Announce Type: new Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions.
By Yuehao Huang, Yunzi Wu, Xiaotao Zhang, Xinhai Li, Jiankun Dong, Jiajun Lv, Chi Zhang, Chenjia Bai, Yong Liu, Xuelong Li
arXiv:2607. 18236v1 Announce Type: cross Abstract: Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning.
By Gaoyue Zhou, Zichen Jeff Cui, Ada Langford, Bowen Tan, Yann LeCun, Lerrel Pinto
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
arXiv:2606. 10918v1 Announce Type: cross Abstract: The recent trend in scaling models for robot learning has resulted in impressive policies that can perform various manipulation tasks and generalize to novel scenarios.
By Artur Kuramshin, \"Ozg\"ur Aslan, Cyrus Neary, Glen Berseth
arXiv:2608. 06161v1 Announce Type: new Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints.
By Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel