mlsanityData to 7 Oct 2026

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

arXiv 2508.10333 ↗First posted 14 Aug 2025cs.RO cs.CVcited by 80

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model's generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization. Our project page is https://zionchow.github.io/ReconVLA/.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 40 of its 50 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

40 of 50 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation6 May
  2. 2025VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation19 Feb
  3. 2025GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation13 Feb
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  5. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robots22 Dec
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 34

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  7. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  8. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  9. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
  10. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  11. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  12. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
22 more
  1. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  2. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 414
  3. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  4. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  5. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  6. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  7. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  8. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  9. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  10. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Datacited by 171
  11. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  12. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  13. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  14. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learningcited by 87
  15. 2024Prediction with Action: Visual Policy Learning via Joint Denoising Processcited by 64
  16. 2024Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulationcited by 51
  17. 2024VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulationcited by 45
  18. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decodingcited by 38
  19. 2024GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robotcited by 28
  20. 2025MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Modelscited by 27
  21. 2024VIP: Vision Instructed Pre-training for Robotic Manipulationcited by 11
  22. 2024QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 69.

80 papers.

Sort:

By area:

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  2. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  3. 2025FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Modelscited by 50
  4. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Processcited by 37
  5. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  6. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 33
  7. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 27
  8. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 22
  9. 2026AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Modelscited by 21
  10. 2026DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Modelscited by 20
  11. 2025QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Modelscited by 19
  12. 2026Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulationcited by 19
38 more
  1. 2026Towards Generalizable Robotic Manipulation in Dynamic Environmentscited by 17
  2. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 16
  3. 2026Mask World Model: Predicting What Matters for Robust Robot Policy Learningcited by 15
  4. 2026FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Modelcited by 14
  5. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  6. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  7. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  8. 2026HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulationcited by 10
  9. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baselinecited by 9
  10. 2026Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performancecited by 9
  11. 2025Multi-speaker Attention Alignment for Multimodal Social Interactioncited by 8
  12. 2025UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformercited by 8
  13. 2026ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulationcited by 8
  14. 2026AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understandingcited by 8
  15. 2026HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation Systemcited by 7
  16. 2026PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidancecited by 6
  17. 2026GEM: Generative Supervision Helps Embodied Intelligencecited by 6
  18. 2026UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Modelscited by 5
  19. 2026DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matchingcited by 5
  20. 2026FocusVLA: Focused Visual Utilization for Vision-Language-Action Modelscited by 5
  21. 2026AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignmentcited by 5
  22. 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Modelcited by 5
  23. 2026Is Forward Prediction Enough? Physical State Grounding for JEPA World Modelscited by 5
  24. 2025NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfacescited by 4
  25. 2025TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perceptioncited by 4
  26. 2026TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulationcited by 4
  27. 2026UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Modelscited by 4
  28. 2026Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignmentcited by 4
  29. 2026SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Modelscited by 3
  30. 2026Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meterscited by 3
  31. 2026Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Modelscited by 3
  32. 2026Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulationcited by 3
  33. 2026OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulationcited by 3
  34. 2026MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresightcited by 3
  35. 2026VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Modelscited by 2
  36. 2026VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Modelscited by 2
  37. 2026Unleashing More Actions via Action Compositional Training for VLA Modelscited by 2
  38. 2026DreamTrajectory: Trajectory-Guided Action Generation with World Model Alignment for Mobile Manipulationcited by 2

50 most cited of 80 All 80 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought
  2. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  3. 2026GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
  4. 2025VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
  5. 2025HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks
  6. 2026LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
  7. 2025PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention
  8. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges