LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment

• URL: http://arxiv.org/abs/2604.11689v1
• Date: Mon, 13 Apr 2026 16:30:35 GMT
• Title: LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
• Abstract summary: General visual foundation models consistently outperform specialized embodied latent action models.<n>Latent-based visual space is better aligned to physical action space than pixel-based space.
• Score: 19.95295518800639
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source. A critical challenge in utilizing large-scale human video datasets lies in transforming visual signals into ontology-independent representations, known as latent actions. However, the capacity of latent action representation to derive robust control from visual observations has yet to be rigorously evaluated. We introduce the Latent Action Representation Yielding (LARY) Benchmark, a unified framework for evaluating latent action representations on both high-level semantic actions (what to do) and low-level robotic control (how to do). The comprehensively curated dataset encompasses over one million videos (1,000 hours) spanning 151 action categories, alongside 620K image pairs and 595K motion trajectories across diverse embodiments and environments. Our experiments reveal two crucial insights: (i) General visual foundation models, trained without any action supervision, consistently outperform specialized embodied latent action models. (ii) Latent-based visual space is fundamentally better aligned to physical action space than pixel-based space. These results suggest that general visual representations inherently encode action-relevant knowledge for physical control, and that semantic-level abstraction serves as a fundamentally more effective pathway from vision to action than pixel-level reconstruction.

Related papers

• Towards Generalizable Visually Grounded Exploration of Household Devices [74.66117923766632]
  Key bottleneck of realizing general autonomous embodied agents lies in Generalizable Visually Grounded Exploration.<n>We introduce VGEBench, a benchmark designed to evaluate the generalizable visually grounded exploration capabilities of Vision-Language Models.<n>Unlike static datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling agents to achieve goals by active visual perception and feedback-driven correction.
  arXiv  Detail & Related papers  (2026-09-01T07:42:45Z)
• Making Foresight Actionable: Repurposing Representation Alignment in World Action Models [57.23863557252883]
  World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution.<n> generating plausible visual futures does not always guarantee the extraction of accurate actions.<n>We propose AGRA, an Action-Grounded Representation Alignment objective.
  arXiv  Detail & Related papers  (2026-06-10T15:31:25Z)
• DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
  We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
  arXiv  Detail & Related papers  (2026-06-06T03:50:45Z)
• GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations [19.347332945780273]
  Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action.<n>We introduce gesture as a parallel instruction modality and propose a Gesture-aware Vision-Language-Action model (GesVLA)<n> Experimental results show that incorporating gesture consistently improves target grounding accuracy and human-robot interaction efficiency.
  arXiv  Detail & Related papers  (2026-05-21T17:57:44Z)
• 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 Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models [14.109112325287208]
  We study the study of latent action supervision from two perspectives: (i) regularizing the trajectory via image-based latent actions, and (ii) unifying the target space with action-based latent actions.<n>Our results reveal a formulation-task correspondence, whereas action-based latent actions excel at complex motor coordination.
  arXiv  Detail & Related papers  (2026-05-06T09:27:07Z)
• InstrAct: Towards Action-Centric Understanding in Instructional Videos [12.356484522873577]
  InstrAction is a pretraining framework for instructional videos' action-centric representations.<n>We first introduce a data-driven strategy, which filters noisy captions and generates action-centric hard negatives.<n>At the visual feature level, an Action Perceiver extracts motion-relevant tokens from redundant video encodings.
  arXiv  Detail & Related papers  (2026-04-09T20:51:13Z)
• LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning [51.969318585152116]
  LatentPilot exploits future observations during training as a valuable data source to learn action-conditioned visual dynamics.<n>We propose a flywheel-style training mechanism that iteratively collects on-policy trajectories and retrains the model to better match the agent's behavior distribution.<n> Experiments on R2R-CE, RxR-CE, and R2R-PE benchmarks achieve new SOTA results, and real-robot tests across diverse environments demonstrate LatentPilot's superior understanding of environment-action dynamics in scene.
  arXiv  Detail & Related papers  (2026-03-31T02:21:59Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• 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)
• VisualActBench: Can VLMs See and Act like a Human? [47.16421650715271]
  Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments.<n>However, their ability to proactively reason and act based solely on visual inputs, without explicit textual prompts, remains underexplored.<n>We introduce a new task, Visual Action Reasoning, and propose VisualActBench, a large-scale benchmark comprising 1,074 videos and 3,733 human-annotated actions.
  arXiv  Detail & Related papers  (2025-12-10T18:36:18Z)
• Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception [8.542874528320004]
  Existing vision models and fixed RGB-D camera systems fail to reconcile wide-area coverage with fine-grained detail acquisition.<n>We propose EyeVLA, a robotic eyeball for active visual perception that can take proactive actions based on instructions.
  arXiv  Detail & Related papers  (2025-11-19T09:42:08Z)
• SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding [48.64661382961745]
  We introduce Spatio-temporal Video Action Grounding (SVAG), a novel task that requires models to simultaneously detect, track, and temporally localize all referent objects in videos.<n>To support this task, we construct SVAG-Bench, a large-scale benchmark comprising 688 videos, 19,590 annotated records, and 903 unique verbs.<n> Empirical results show that existing models perform poorly on SVAG, particularly in dense or complex scenes.
  arXiv  Detail & Related papers  (2025-10-14T22:10:49Z)
• Precise Action-to-Video Generation Through Visual Action Prompts [62.951609704196485]
  Action-driven video generation faces a precision-generality trade-off.<n>Agent-centric action signals provide precision at the cost of cross-domain transferability.<n>We "render" actions into precise visual prompts as domain-agnostic representations.
  arXiv  Detail & Related papers  (2025-08-18T17:12:28Z)
• From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection [60.11169426478452]
  This paper aims to introduce fixation information to assist the detection of salient objects under weak supervision.<n>We propose a Position and Semantic Embedding (PSE) module to provide location and semantic guidance during the feature learning process.<n>An Intra-Inter Mixed Contrastive (MCII) model improves thetemporal modeling capabilities under weak supervision.
  arXiv  Detail & Related papers  (2025-06-30T05:01:40Z)
• Object Concepts Emerge from Motion [24.73461163778215]
  We propose a biologically inspired framework for learning object-centric visual representations in an unsupervised manner.<n>Our key insight is that motion boundary serves as a strong signal for object-level grouping.<n>Our framework is fully label-free and does not rely on camera calibration, making it scalable to large-scale unstructured video data.
  arXiv  Detail & Related papers  (2025-05-27T18:09:02Z)
• Self-supervised Video Object Segmentation by Motion Grouping [79.13206959575228]
  We develop a computer vision system able to segment objects by exploiting motion cues. We introduce a simple variant of the Transformer to segment optical flow frames into primary objects and the background. We evaluate the proposed architecture on public benchmarks (DAVIS2016, SegTrackv2, and FBMS59)
  arXiv  Detail & Related papers  (2021-04-15T17:59:32Z)

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.