arXiv AI September 18, 2026 By Maxime Alvarez, Renzo Caballero, Tatsuya Matsushima, Yusuke Iwasawa, Yutaka Matsuo

Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision

The paper proposes using action‑similarity supervision to improve cross‑embodiment transfer in latent action models (LAMs). By training the similarity between latent actions to match the similarity of ground‑truth robot action sequences—without predicting the actions themselves—the authors reduce sensitivity to background noise and embodiment differences. Experiments on RoboTwin 2.0 show that this approach more than doubles cross‑embodiment success compared to predicting ground‑truth actions, especially when similarities are computed on end‑effector motion and compared across robots.

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 AI.

robotics

arXiv Machine Learning

Jul 31

Cross-Embodiment Transfer via Behavior-Aligned Representations

arXiv:2607. 27549v1 Announce Type: cross Abstract: Recent progress in large-scale imitation learning for robot manipulation has been driven by leveraging datasets across a wide range of robot embodiments.

By Ajay Sridhar, Jensen Gao, Jonathan Yang, Jean Mercat, Suneel Belkhale, Dorsa Sadigh

robotics multimodal benchmarks

Hugging Face Trending Papers

Jul 30

Cross-Embodiment Transfer via Behavior-Aligned Representations

Recent progress in large-scale imitation learning for robot manipulation has been driven by leveraging datasets across a wide range of robot embodiments. However, achieving significant cross-embodiment transfer is often still challenging.

robotics multimodal benchmarks

arXiv AI

Jun 2

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

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

robotics multimodal

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 Machine Learning

Jul 31

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

arXiv:2505. 04999v2 Announce Type: replace-cross Abstract: Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation.

By Anthony Liang, Pavel Czempin, Matthew M. Hong, Yutai Zhou, Jingzhen Wang, Erdem Biyik, Stephen Tu

robotics

arXiv AI

Aug 28

CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators

CLAP is a cross-embodiment framework for action‑conditioned video generation that can be trained on diverse internet‑scale videos from both humans and robots. It reconciles different action spaces—end‑effector poses, language instructions, and latent actions—using a curriculum that first learns physics priors from unlabeled video and then grounds them in real‑world action spaces for zero‑shot deployment. The resulting models match or exceed state‑of‑the‑art single‑embodiment models in challenging environments and support few‑shot adaptation across a wide range of robot morphologies.

By Kechen Liu, Ola Shorinwa

agents diffusion robotics benchmarks

One email a morning, machine-written

Related stories

Cross-Embodiment Transfer via Behavior-Aligned Representations

Cross-Embodiment Transfer via Behavior-Aligned Representations

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

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

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators