SABER: A Scalable Action-Based Embodied Dataset for Real-World VLA Adaptation

• URL: http://arxiv.org/abs/2605.09613v1
• Date: Sun, 10 May 2026 15:51:01 GMT
• Title: SABER: A Scalable Action-Based Embodied Dataset for Real-World VLA Adaptation
• Abstract summary: SABER is a high-fidelity retail robotics action dataset built from over 100 hours of natural in-store capture.<n>It contains 44.8K training samples across three action representation streams.<n>It yields a mean success rate of 29.3% across ten retail manipulation tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Robotic deployment in real-world environments depends on rich, domain-specific action data as much as on strong model architecture. General-purpose robot foundation models show modest performance in complex unseen tasks such as manipulation in a retail domain when applied out of the box. The root cause is a data gap: retail environments are structurally absent from general robot pretraining distributions, and the path to filling that gap through teleoperation is prohibitively expensive, logistically constrained, and difficult to scale. We introduce SABER, a high-fidelity retail robotics action dataset built from over 100 hours of natural in-store capture across multiple real grocery environments. Egocentric footage from head-mounted cameras records fine-grained hand activity at the point of interaction, while exocentric 360-degree scene footage from DreamVu's ALIA camera simultaneously observes all actors and activities across the entire space. This combination yields a uniquely complete picture of human retail behavior: dexterous hand activity, whole-body motion, and scene dynamics, all captured without staging, scripting, or teleoperation overhead. The SABER corpus contains 44.8K training samples across three action representation streams: 25K latent action sequences via LAPA-style encoding, 18.6K dexterous hand-pose trajectories retargeted to robot joint space, and 1.2K whole-body synchronized motion sequences retargeted to a humanoid embodiment. When applied to GR00T N1.6 via a shared-backbone multi-task post-training recipe, SABER yields a mean success rate of 29.3% across ten retail manipulation tasks -- more than 2.19x over fine-tuning baselines (13.4%). SABER demonstrates that the path to capable retail robots runs through better data, which can be collected today, at scale, without a robot in the loop. The dataset and code are available at https://dreamvu.ai/saber

Related papers

• ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training [93.39352617578857]
  We introduce ZimaBlue, a framework for learning generalizable World Action Models from large-scale video.<n>ZimaBlue follows a three-stage training curriculum, first performing causal embodied video pre-training on large-scale human and robot egocentric videos.<n>ZimaBlue further delivers strong performance across multiple benchmarks, with particularly pronounced gains on unseen tasks.
  arXiv  Detail & Related papers  (2026-08-31T18:09:52Z)
• Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data [60.94418315274988]
  Ego2Robot supports both curated and in-the-wild videos, producing 18,561 hours of robot training data spanning 15 robot morphologies.<n>Joint pretraining on Ego2Robot-synthesized and robot data consistently improves out-of-distribution generalization across multiple types.
  arXiv  Detail & Related papers  (2026-08-03T17:52:26Z)
• RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation [48.828787848144806]
  We introduce digital teleoperation, a paradigm that decouples data collection from physical constraints by replacing real robot with a generative world model.<n>We instantiate this paradigm in RynnWorld-Teleop, a system that integrates depth-aware skeletal conditioning, progressive human-to-robot training on a video Diffusion Transformer, and streaming autoregressive distillation.<n>This pipeline compresses the generative process into a single-pass inference, enabling 40+ FPS, real-time interactive generation on a single H100 GPU.
  arXiv  Detail & Related papers  (2026-07-07T17:58:11Z)
• GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors [113.71148915419246]
  We present GRAIL, a digital generation pipeline that composes 3D assets, simulator-ready scenes, and priors from video foundation models (VFMs) to synthesize interactions without rebuilding physical environments or teleoperating the robot.<n>GRAIL starts from fully specified 3D configurations in which object geometry, camera parameters, metric scale, environment depth, and a robot-proportioned character are known before video generation and reused during reconstruction.<n>We retarget the recovered motions to a humanoid robot and train complementary task-general morphology trackers.<n>GRAIL produces over 20,000 sequences spanning pick-up, object manipulation, sitting
  arXiv  Detail & Related papers  (2026-06-03T17:57:45Z)
• UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos [65.2981273885678]
  Dexterous manipulation remains challenging due to the cost of collecting real-robot teleoperation data.<n>We present UniDex, a robot foundation suite that couples a large-scale robot-centric dataset with a unified vision-language-action (VLA) policy.<n>UniDex-Dataset, UniDex-VLA, and UniDex-Cap provide a scalable foundation suite for universal dexterous manipulation.
  arXiv  Detail & Related papers  (2026-03-23T17:49:12Z)
• Morphology-Consistent Humanoid Interaction through Robot-Centric Video Synthesis [25.249184346335557]
  Dream2Act is a robot-centric framework enabling zero-shot interaction through generative video.<n> operating strictly within the robot-native space, Dream2Act avoids errors and eliminates task-specific policy training.
  arXiv  Detail & Related papers  (2026-03-20T07:27:09Z)
• EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents [85.77432303199176]
  We propose EmbodMocap, a portable and affordable data collection pipeline using two moving iPhones.<n>Our key idea is to jointly calibrate dual RGB-D sequences to reconstruct both humans and scenes.<n>Based on the collected data, we empower three embodied AI tasks: monocular human-scene-reconstruction, where we fine-tune feedforward models that output metric-scale, world-space aligned humans and scenes; physics-based character animation, where we prove our data could be used to scale human-object interaction skills and scene-aware motion tracking; and robot motion control, where we train a humanoid robot via
  arXiv  Detail & Related papers  (2026-02-26T16:53:41Z)
• Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild [37.43820830488286]
  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.
  arXiv  Detail & Related papers  (2026-02-25T09:46:42Z)
• RoboPaint: From Human Demonstration to Any Robot and Any View [9.083647729839688]
  We propose a Real-Sim-Real data collection and data editing pipeline to transform human demonstrations into robot-executable, environment-specific training data.<n>We show that retargeted dex-hand trajectories achieve an 84% success rate across 10 diverse object manipulation tasks.<n>We offer a scalable, cost-effective alternative to teleoperation with minimal performance loss for complex dexterous manipulation.
  arXiv  Detail & Related papers  (2026-02-05T05:45:12Z)
• 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)
• Recognizing Actions from Robotic View for Natural Human-Robot Interaction [52.00935005918032]
  Natural Human-Robot Interaction (N-HRI) requires robots to recognize human actions at varying distances and states, regardless of whether the robot itself is in motion or stationary.<n>Existing benchmarks for N-HRI fail to address the unique complexities in N-HRI due to limited data, modalities, task categories, and diversity of subjects and environments.<n>We introduce (Action from Robotic View) a large-scale dataset for perception-centric robotic views prevalent in mobile service robots.
  arXiv  Detail & Related papers  (2025-07-30T09:48:34Z)
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation [65.46610405509338]
  We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal. We show that this approach of combining scalably learned track prediction with a residual policy enables diverse generalizable robot manipulation.
  arXiv  Detail & Related papers  (2024-05-02T17:56:55Z)
• Revisit Human-Scene Interaction via Space Occupancy [55.67657438543008]
  Human-scene Interaction (HSI) generation is a challenging task and crucial for various downstream tasks. In this work, we argue that interaction with a scene is essentially interacting with the space occupancy of the scene from an abstract physical perspective. By treating pure motion sequences as records of humans interacting with invisible scene occupancy, we can aggregate motion-only data into a large-scale paired human-occupancy interaction database.
  arXiv  Detail & Related papers  (2023-12-05T12:03:00Z)

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.