GUARD: Anomaly-Informed Q-Steering for Generative Robot Policies in Dexterous Manipulation
cs.RO
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
- SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation
- Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
- QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
- Flow Matching with Uncertainty Quantification and Guidance
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
- Exploration by Random Network Distillation
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