The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models
cs.RO, cs.AI
Submitted: 2026-09-22
Updated: 2026-09-22
Project page: https://cxu-tri.github.io/non
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Scaling Laws for Neural Language Models
- Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
- XFlowMP: Task-Conditioned Motion Fields for Generative Robot Planning with Schrodinger Bridges
- You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
- STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
- ADPro: a Test-time Adaptive Diffusion Policy via Manifold-constrained Denoising and Task-aware Initialization for Robotic Manipulation
- Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training
- Robot Learning as an Empirical Science: Best Practices for Policy Evaluation
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