mlsanityData to 14 Oct 2026

FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

arXiv 2606.20867 ↗First posted 18 Jun 2026cs.CV cs.AIcited by 2

On the map: Vision-language-action models → Reinforcement learning and post-training

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models enable general-purpose robotic control via large-scale multimodal pretraining, yet their effectiveness under few-shot imitation learning remains limited. We conduct a systematic stress test of state-of-the-art VLA models and show that performance degrades sharply as demonstrations are reduced, revealing a key weakness of existing adaptation strategies. To address this, we introduce FOCA, a future-oriented conditioning framework for data-efficient VLA adaptation. FOCA combines explicit prediction of task-grounded future interaction embeddings with implicit alignment to future goal observations, enabling long-horizon reasoning in latent space without pixel-level prediction. This formulation naturally supports action-free co-training with synthetic videos from video world models and can be interpreted as learning a future-conditioned value-like representation. Extensive experiments demonstrate FOCA achieves 95.7% success with 20 demonstrations on LIBERO, improves 7-12% on RoboCasa, and delivers up to 26% absolute gains on real robots, establishing a new state of the art in few-shot VLA adaptation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models. Builds on 50 of its 63 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

50 of 63 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models19 Jun
  2. 2024Octo: An Open-Source Generalist Robot Policy20 May

Other references · 48

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  11. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  12. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
36 more
  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  2. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  3. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  4. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  5. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  6. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  7. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 459
  8. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  9. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  10. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  11. 2024Latent Action Pretraining from Videoscited by 321
  12. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 304
  13. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 289
  14. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 253
  15. 2017One-Shot Imitation Learningcited by 233
  16. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  17. 2025World Simulation with Video Foundation Models for Physical AIcited by 200
  18. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 179
  19. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 156
  20. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  21. 2025FLARE: Robot Learning with Implicit World Modelingcited by 113
  22. 2020C-Learning: Learning to Achieve Goals via Recursive Classificationcited by 103
  23. 2025Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfercited by 87
  24. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 80
  25. 2024ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperationcited by 63
  26. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 61
  27. 2024RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learningcited by 46
  28. 2023Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Datacited by 23
  29. 2025Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspectivecited by 20
  30. 2023Contrastive Language, Action, and State Pre-training for Robot Learningcited by 16
  31. 2024Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulationcited by 15
  32. 2025Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrationscited by 15
  33. 2025CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulationcited by 11
  34. 2025Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Groundingcited by 10
  35. 2025SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulationcited by 9
  36. 2026ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026FINE: Future-Informed Navigation Encoding for Data-Efficient Vision-Language Navigationcited by 0
  2. 2026Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
  2. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
  3. 2026VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
  4. 2026Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
  5. 2026CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models
  6. 2026Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
  7. 2026RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
  8. 2026VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models