mlsanityData to 7 Oct 2026

Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge

arXiv 2512.06951 ↗First posted 7 Dec 2025cs.RO cs.AI cs.CVcited by 13

On the map: Vision-language-action models → Failure recovery and robustness

also in 1 more
Abstract (arXiv)

We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and context-aware decision making. Building on the Pi0.5 architecture, we introduce several innovations. Our primary contribution is correlated noise for flow matching, which improves training efficiency and enables correlation-aware inpainting for smooth action sequences. We also apply learnable mixed-layer attention and System 2 stage tracking for ambiguity resolution. Training employs multi-sample flow matching to reduce variance, while inference uses action compression and challenge-specific correction rules. Our approach achieves 26% q-score across all 50 tasks on both public and private leaderboards.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Failure recovery and robustness, one of 13 directions in Vision-language-action models. Builds on 17 of its 25 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

17 of 25 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  10. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  11. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  12. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
5 more
  1. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  2. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  3. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  4. 2024BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulationcited by 140
  5. 2025A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationcited by 125

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 17
  2. 2026OAT: Ordered Action Tokenizationcited by 14
  3. 2026Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latentscited by 8
  4. 2026How VLAs (Really) Work In Open-World Environmentscited by 3
  5. 2026SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulationcited by 2
  6. 2026EmbodiedSWE: Coding Agents for Long Horizon Dexterous Roboticscited by 2
  7. 2026Make Your VLA More Robust Without More Data By Interleaving Motion Planningcited by 1
  8. 2026Potential-Guided Flow Matching for Vision-Language-Action Policy Improvementcited by 1
  9. 2026Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)cited by 0
  10. 2026A Glimpse into Long-term Physical Coexistence with Intelligent Robotscited by 0
  11. 2026Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Taskscited by 0
  12. 2026Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policiescited by 0
1 more
  1. 2026The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interfacecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies
  2. 2026Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model
  3. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  4. 2026VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
  5. 2026LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
  6. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
  7. 2025SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models
  8. 2026Quantile Head for Vision-Language-Action Models