Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging
cs.RO, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/Maincode-Research/LARBRID
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- End to End Learning for Self-Driving Cars
- RT-1: Robotics Transformer for Real-World Control at Scale
- Score Regularized Policy Optimization through Diffusion Behavior
- Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
- Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
- Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
- Offline Reinforcement Learning with Implicit Q-Learning
- Flow Matching for Generative Modeling
- RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
- What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- Learning a Diffusion Model Policy from Rewards via Q-Score Matching
- Diffusion Policy Policy Optimization
- Spectral Decomposition Representation for Reinforcement Learning
- Neural-Kernelized Conditional Density Estimation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
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