VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models
cs.RO
Submitted: 2026-11-05
Updated: 2026-11-10
Code: https://github.com/Physical-Intelligence/openpi
Project page: https://ai4ce.github.io/VICTR
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
- From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
- RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
- MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos
- Gemma 3 Technical Report
- RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
- In-Context Imitation Learning via Next-Token Prediction
- ICLR: In-Context Imitation Learning with Visual Reasoning
- Reflective VLA: In-Context Action Consequences Make VLAs Generalize
- RoboTTT: Context Scaling for Robot Policies
- SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
- TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
- Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
- LEACL: LLM-Enhanced Automatic Curriculum Learning for Reinforcement Learning in Long-Horizon Manipulation Tasks
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- Qwen3-VL Technical Report
- Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation