Beyond Validation Loss: Coverage and Reliability Dynamics in Robot Policy Pretraining
cs.LG, cs.RO
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Scalable Behavior Cloning with Open Data, Training, and Evaluation
- Memorization and Regularization in Generative Diffusion Models
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Evaluating Large Language Models Trained on Code
- Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control
- Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
- Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
- On Memorization in Diffusion Models
- TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
- Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Robot Learning as an Empirical Science: Best Practices for Policy Evaluation
- TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
- What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
- MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis