Verify, Act, Distill: Turning Test-Time Compute into Test-Time Adaptation for Vision-Language-Action Models
cs.RO
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- Thinking Fast and Slow with Deep Learning and Tree Search
- EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
- SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation
- ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
- TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
- RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- EXPO: Stable Reinforcement Learning with Expressive Policies
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
- LoRA: Low-Rank Adaptation of Large Language Models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Verifier-free Test-Time Sampling for Vision-Language-Action Models
- Refined Policy Distillation: From VLA Generalists to RL Experts
- DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
- RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies