mlsanityData to 7 Oct 2026

Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation

arXiv 2605.11832 ↗First posted 12 May 2026cs.ROcited by 3

On the map: Vision-language-action models → 3D and spatial-aware VLA

Abstract (arXiv)

This paper tackles spatial perception and manipulation challenges in Vision-Language-Action (VLA) models. To address depth ambiguity from monocular input, we leverage a pre-trained multi-view diffusion model to synthesize latent novel views and propose a Geometry-Guided Gated Transformer (G3T) that aligns multi-view features under 3D geometric guidance while adaptively filtering occlusion noise. To improve action learning efficiency, we introduce Action Manifold Learning (AML), which directly predicts actions on the valid action manifold, bypassing inefficient regression of unstructured targets like noise or velocity. Experiments on LIBERO, RoboTwin 2.0, and real-robot tasks show our method achieves superior success rate and robustness over SOTA baselines. Project page: https://junjxiao.github.io/Multi-view-VLA.github.io/.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models. Builds on 82 of its 89 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

82 of 89 references.

Closest ancestors · 12

Same direction, newest first

  1. 20263D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models25 Mar
  2. 2026ST4VLA: Spatially Guided Training for Vision-Language-Action Models10 Feb
  3. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy15 Oct
  4. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning15 Oct
  5. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model14 Oct
  6. 2025GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model17 Sep
  7. 2025Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation7 Aug
  8. 2025Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding1 Jul
  9. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models9 Jun
  10. 20253D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks9 May
  11. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  12. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model27 Jan

Other references · 70

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2022Flow Matching for Generative Modelingcited by 5,426
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  11. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
38 more
  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  5. 2025Qwen3-VL Technical Reportcited by 2,534
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  8. 2021Vision Transformers for Dense Predictioncited by 1,789
  9. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  10. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  11. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  12. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  13. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  14. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  15. 2020Mastering Atari with Discrete World Modelscited by 990
  16. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  17. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  18. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  19. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  20. 2025Mean Flows for One-step Generative Modelingcited by 524
  21. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  22. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  23. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  24. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  25. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  26. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  27. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  28. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  29. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 278
  30. 2018Residual Reinforcement Learning for Robot Controlcited by 242
  31. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 166
  32. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  33. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 139
  34. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 135
  35. 2025Interactive Post-Training for Vision-Language-Action Modelscited by 129
  36. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 119
  37. 2025StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modelingcited by 107
  38. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulationcited by 2
  2. 2026EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Controlcited by 0
  3. 2026PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning
  2. 2026LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment
  3. 2026GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation
  4. 2026Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D
  5. 2026GeomVLA: Unifying Scene, Motion, and Action in 3D
  6. 2026ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
  7. 2026G3VLA: Geometric inductive bias for Vision-Language-Action Models
  8. 2026Geometric Action Model for Robot Policy Learning