Latent Action Models

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 31

All topics

Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies
Sep 27, 2026Jialeng Ni, Nathan Zhao, Kunpeng SongRobot Policies Latent Action Models
University of Michigan, Ann Arbor, MI, USA. · XPENG Robotics, Santa Clara, CA, USA.
Less Language, More Latents: Annotation-Efficient VLAs for Driving
Sep 23, 2026Alexey Zakharov, Kemal Oksuz, Puneet K. DokaniaDiffusion-Based Vision-Language-Actions Latent Action Models
Robert Bosch GmbH, Germany · Five AI Ltd., United Kingdom
Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision
Sep 17, 2026Maxime Alvarez, Renzo Caballero, Tatsuya Matsushima +2Latent Actions Latent Action Models
Graduate School of Engineering, The University of Tokyo
Beyond Noise Steering: Dual-Latent Space Reinforcement Learning for Generative Robot Policy
Sep 11, 2026Pengfei Zhang, Teng Sun, Xianchao XiuRobot Policies Latent Action Models
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning
Aug 7, 2026Yanping Zhao, Hang Yu, Yiwei Wang +8Diffusion-Based Vision-Language-Actions Latent Action Models
Tongji University
D-CLOT: Double Closed Loop Optimal Transport for Unsupervised Action Segmentation
Aug 6, 2026Elena Bueno-Benito, Mariella DimiccoliTemporal Action Segmentation Latent Action Models
Institut de Rob`otica i Inform`atica Industrial, CSIC-UPC, Barcelona, Spain
LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models
Aug 6, 2026Jiarui Yang, Jiale Zhange, Jiawei Li +5Latent Action Models Latent Actions
Nankai University · Tsinghua University · Swiss Federal Institute of Technology in Lausanne (EPFL) +1
DLAM: Distributional Latent Actions with Temporal Constraints
Jul 29, 2026Zuojin Tang, Feifan Luo, Haoyun Liu +10Latent Action Models Large-Scale Robot Demonstration Datasets
Zhejiang University · Nanjing University · Shanghai Jiaotong University +4
Causally Debiased Latent Action Model for Embodied Action Conditioned World Models
Jul 10, 2026Yufan Wei, Kun Zhou, Lingjun Mao +9Latent Action Models World Models
Aether AI · University of California, San Diego
CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models
Jul 6, 2026Yifu Xiong, Wenhao Yu, Jiaxuan Lin +5Diffusion-Based Vision-Language-Actions Latent Action Models
University of Science and Technology of China (USTC) · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
LaGO: Latent Action Guidance for Online Reinforcement Learning
Jun 23, 2026Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong WuLatent Action Models Latent Actions
Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, USA · Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan.
Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
Jun 19, 2026Tianyou Wang, Anson Lei, Joe Watson +1Latent Action Models Imitation Learning
University of Oxford
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
Jun 19, 2026Youngjoon Jeong, Jihwan Yu, Minsoo Jo +2Latent Actions Latent Action Models
Seoul National University
FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning
Jun 17, 2026Takanori Yoshimoto, Yang Hu, Naruya Kondo +1Latent Action Models Bottlenecks
University of Tsukuba · The University of Tokyo
Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos
Jun 17, 2026Runze Xu, Yiluo Zhang, Jian Wang +2Diffusion-Based Vision-Language-Actions Latent Action Models
Department of Electronic Engineering, Tsinghua University · Tianfu Jiangxi Laboratory
LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching
Jun 9, 2026Jiexi Lyu, Xizhou Bu, Qingqiu Huang +4Latent Action Models Latent Actions
LARA: Latent Action Representation Alignment for Vision-Language-Action Models
Jun 5, 2026Mengya Liu, Baoxiong Jia, Jiangyong Huang +2Latent Action Models Large-Scale Robot Demonstration Datasets
State Key Laboratory of General Artificial Intelligence, BIGAI · Peking University · Delta Intelligence
Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization
May 19, 2026Franco Terranova, Guillermo Bernardez, Albert Cabellos-Aparicio +2Combinatorial Optimization Graph Representations
UL, LORIA, Inria · Université de Lorraine, CNRS, Inria, LORIA · UC Santa Barbara +4
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
May 18, 2026Zhiyuan Feng, Qixiu Li, Huizhi Liang +12Diffusion-Based Vision-Language-Actions Latent Action Models
1Tsinghua University · 5Microsoft Research Asia · 2HKUST +4
Latent Action Control for Reasoning-Guided Unified Image Generation
May 16, 2026Fuxiang Zhai, Sixiang Chen, Yingjin Li +4Multimodal Generation Image Generation
The Hong Kong University of Science and Technology (Guangzhou)
DiLA: Disentangled Latent Action World Models
May 15, 2026Tianqiu Zhang, Muyang Lyu, Yufan Zhang +2Latent Action Models Latent World Models
Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, IDG/McGovern Institute for Brain Research, Peking University. · Center of Quantitative Biology, Peking University. · School of Psychological and Cognitive Sciences, Key Laboratory of Machine Perception (Ministry of Education), Peking University.
RotVLA: Rotational Latent Action for Vision-Language-Action Model
May 13, 2026Qiwei Li, Xicheng Gong, Xinghang Li +5Latent Actions Latent Action Models
Wangxuan Institute of Computer Technology, Peking University · Xiaomi Robotics · CASIA
Why Latent Actions Fail, and How to Prevent It
May 13, 2026Jung Min Lee, Taehyun Cho, Li Zhao +1Latent Actions Latent Action Models
Seoul National University · Microsoft Research
Zero-shot Imitation Learning by Latent Topology Mapping
May 8, 2026Maxwell J. Jacobson, Yexiang XueTemporally Coherent Imitation Learning Imitation Learning
Purdue University, Department of Computer Science, West Lafayette, IN
Learning Visual Feature-Based World Models via Residual Latent Action
May 8, 2026Xinyu Zhang, Zhengtong Xu, Yutian Tao +3Latent World Models Latent Action Models
1Rutgers University · 2Purdue University · University of Wisconsin-Madison
Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
May 7, 2026Roussel Desmond Nzoyem, Mauro ComiVideo World Models Latent World Models
Department of Computer Science University of Manchester Manchester, M13 9PL · Department of Computer Science University of Bristol Bristol, BS8 1QU
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
May 6, 2026Yihan Lin, Haoyang Li, Yang Li +4Diffusion-Based Vision-Language-Actions Latent Action Models
School of Information, Renmin University of China, Beijing, China · Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China · Engineering Research Center of Database and Business Intelligence, Beijing, China
LA-Pose: Latent Action Pretraining Meets Pose Estimation
Apr 30, 2026Zhengqing Wang, Saurabh Nair, Prajwal Chidananda +4Wifi-Csi 3D Human Pose Estimation Latent Action Models
1Wayve · 2Simon Fraser University
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
Apr 23, 2026Songen Gu, Yuhang Zheng, Weize Li +6Robotic Manipulation Novel View Synthesis
1Fudan University · 2TARS Robotics · 4NUS +1
Latent Policy Steering through One-Step Flow Policies
Mar 5, 2026Hokyun Im, Andrey Kolobov, Jianlong Fu +1Model-Based Reinforcement Learning Flow Policies
Department of Artificial Intelligence, Yonsei University · Microsoft Research
On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
Feb 2, 2026Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau +1Strong Imitation Learning Imitation Learning
Département d’informatique et de recherche opérationnelle, Université de Montréal · Mila – Quebec AI Institute · Samsung AI Lab, Montreal +1

Sep 27, 2026, cs.ROJ/K move · Enter open · S save

Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies

Jialeng Ni, Nathan Zhao, Kunpeng Song

University of Michigan, Ann Arbor, MI, USA. · XPENG Robotics, Santa Clara, CA, USA.

Robot Policies Latent Action Models Subspace Prior Knowledge Integration

Open paper AskPDF arXiv

Generative robot policies provide expressive behavior priors, but updating a large diffusion or flow-matching model through online interaction is costly. Latent-space reinforcement learning avoids updating the pretrained generator by controlling its initial sampling noise, yet high-dimensional noise can have strongly anisotropic effects on decoded actions. We introduce Principal Steering Subspaces (PSS), a forward-query interface that constructs a fixed low-dimensional control basis from finite-difference decoder responses. Soft Actor-Critic controls the leading response directions, while the orthogonal complement is independently resampled from the Gaussian prior at each query. On three RoboMimic tasks with diffusion and flow-matching policies, response spectra reveal substantial concentration. Across five matched task-generator pairs, the training curves indicate that PSS generally converges faster and exhibits more stable late-training behavior than full-latent control, while achieving stronger final performance overall. Controlled Diffusion-Square ablations further show that leading-response directions outperform random and least-responsive subspaces of equal dimension. We further integrate PSS with a frozen, closed-source 3B-parameter vision-language-action (VLA) policy in a humanoid learning system with synchronous transition collection, reset-time optimization, and latency-aware asynchronous deployment. In an exploratory screwdriver-placement evaluation, success is observed in 2/10 trials for the frozen VLA policy and 6/10 after SAC+PSS adaptation. These results support decoder-response geometry as a practical basis for online adaptation of frozen generative robot policies.

Momentum

Related topics

Latest papers 31