DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
cs.RO, cs.AI, cs.CL, cs.CV
Submitted: 2026-05-12
Updated: 2026-09-23
Code: https://github.com/XianzheFan/DreamAvoid
Terminology
Sources
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
- VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
- Exploration-assisted Bottleneck Transition Toward Robust and Data-efficient Deformable Object Manipulation
- DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
- VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
- Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization
- On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
- EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
- VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
- PlayWorld: Learning Robot World Models from Autonomous Play
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
- Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
- DINOv2: Learning Robust Visual Features without Supervision
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
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
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving