Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild

• URL: http://arxiv.org/abs/2602.21736v1
• Date: Wed, 25 Feb 2026 09:46:42 GMT
• Title: Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild
• Abstract summary: We present JALA, a pretraining framework that learns Jointly-Aligned Latent Actions.<n>We scale this approach with UniHand-Mix, a 7.5M video corpus (>2,000 hours) blending laboratory and in-the-wild footage.<n>Experiments demonstrate that JALA generates more realistic hand motions in both controlled and unconstrained scenarios.
• Score: 37.43820830488286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite progress, Vision-Language-Action models (VLAs) are limited by a scarcity of large-scale, diverse robot data. While human manipulation videos offer a rich alternative, existing methods are forced to choose between small, precisely-labeled datasets and vast in-the-wild footage with unreliable hand tracking labels. We present JALA, a pretraining framework that learns Jointly-Aligned Latent Actions. JALA bypasses full visual dynamic reconstruction, instead learns a predictive action embedding aligned with both inverse dynamics and real actions. This yields a transition-aware, behavior-centric latent space for learning from heterogeneous human data. We scale this approach with UniHand-Mix, a 7.5M video corpus (>2,000 hours) blending laboratory and in-the-wild footage. Experiments demonstrate that JALA generates more realistic hand motions in both controlled and unconstrained scenarios, significantly improving downstream robot manipulation performance in both simulation and real-world tasks. These results indicate that jointly-aligned latent actions offer a scalable pathway for VLA pretraining from human data.

Related papers

• From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [71.22409934108924]
  Human videos are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation.<n>This survey provides a unified view of how human videos are transformed into effective knowledge for Vision-Language-Action (VLA) models.<n>We highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency.
  arXiv  Detail & Related papers  (2026-05-18T06:19:16Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization [65.37179698521766]
  Vision-Language-Action (VLA) models show strong promise for generalist robot control.<n>It remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics.<n>We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots.
  arXiv  Detail & Related papers  (2026-02-10T12:25:43Z)
• ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation [27.54751123419347]
  We propose ConLA, an unsupervised pretraining framework for learning robotic policies from human videos.<n>By pretraining solely on human videos, our method for the first time surpasses the performance obtained with real robot trajectory pretraining.
  arXiv  Detail & Related papers  (2026-01-31T06:40:57Z)
• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos [73.51386721543135]
  We propose Contrastive Latent Action Pretraining (CLAP), a framework that aligns the visual latent space from videos with a proprioceptive latent space from robot trajectories.<n>CLAP maps video transitions onto a quantized, physically executable codebook.<n>We introduce a dual-formulation VLA framework offering both CLAP-NTP, an autoregressive model excelling at instruction following and object generalization, and CLAP-RF, a Rectified Flow-based policy designed for high-frequency, precise manipulation.
  arXiv  Detail & Related papers  (2026-01-07T16:26:33Z)
• Robotic VLA Benefits from Joint Learning with Motion Image Diffusion [114.60268819583017]
  Vision-Language-Action (VLA) models have achieved remarkable progress in robotic manipulation by mapping multimodal observations and instructions directly to actions.<n>We propose joint learning with motion image diffusion, a novel strategy that enhances VLA models with motion reasoning capabilities.<n> Experiments in both simulation and real-world environments demonstrate that joint learning with motion image diffusion improves the success rate of pi-series VLAs to 97.5%.
  arXiv  Detail & Related papers  (2025-12-19T19:07:53Z)
• METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model [36.82365894983052]
  A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills.<n>We propose METIS, a vision-language-action model for dexterous manipulation pretrained on egocentric datasets.<n>Our method demonstrates exceptional dexterous manipulation capabilities, achieving highest average success rate in six real-world tasks.
  arXiv  Detail & Related papers  (2025-11-21T16:32:36Z)
• Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos [42.86535655563404]
  We develop a fully-automated holistic human activity analysis approach for arbitrary human hand videos.<n>We process a large volume of egocentric videos and create a hand-VLA training dataset containing 1M episodes and 26M frames.<n>We design a dexterous hand VLA model architecture and pretrain the model on this dataset.
  arXiv  Detail & Related papers  (2025-10-24T15:39:31Z)
• Latent Action Pretraining Through World Modeling [1.988007188564225]
  We propose LAWM, a model-agnostic framework to pretrain imitation learning models in a self-supervised way.<n>Our framework is designed to be effective for transferring across tasks, environments, and embodiments.
  arXiv  Detail & Related papers  (2025-09-22T21:19:10Z)
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining [65.8971623698511]
  We build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR)<n>PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining.<n>Experiments on the ManiSkill benchmark show that PAR achieves a 100% success rate on the PushCube task.
  arXiv  Detail & Related papers  (2025-08-13T13:54:51Z)
• Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos [66.62109400603394]
  We introduce Being-H0, a dexterous Vision-Language-Action model trained on large-scale human videos.<n>Our approach centers on physical instruction tuning, a novel training paradigm that combines large-scale VLA pretraining from human videos, physical space alignment for 3D reasoning, and post-training adaptation for robotic tasks.<n>We empirically show the excellence of Being-H0 in hand motion generation and instruction following, and it also scales well with model and data sizes.
  arXiv  Detail & Related papers  (2025-07-21T13:19:09Z)
• AMPLIFY: Actionless Motion Priors for Robot Learning from Videos [29.799207502031496]
  We introduce AMPLIFY, a novel framework that leverages large-scale video data.<n>We train a forward dynamics model on abundant action-free videos and an inverse dynamics model on a limited set of action-labeled examples.<n>In downstream policy learning, our dynamics predictions enable a 1.2-2.2x improvement in low-data regimes, a 1.4x average improvement by learning from action-free human videos, and the first generalization to LIBERO tasks from zero in-distribution action data.
  arXiv  Detail & Related papers  (2025-06-17T05:31:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.