Recent

• Diffusion Models Dec 6, 2025

  diffusion
• Linear Vector Fields Dec 2, 2025

  flow-matching
• Generative Models Dec 2, 2025
• Diffusion Dec 2, 2025
• Stochastic Policies Nov 20, 2025
• Gaussian Policies Nov 19, 2025
• Categorical Policies Nov 19, 2025

  discreterl
• Reinforcement Learning Nov 19, 2025

  rl
• Flow Matching for Gaussian Probability Paths Aug 15, 2025

  flow-matching
• Square Root Scaling Rule Aug 9, 2025
• Token Jun 21, 2025
• Tokenization Jun 21, 2025
• Causal Attention Jun 18, 2025
• Horizon Reduction Makes RL Scalable Jun 1, 2025
• Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance Jun 1, 2025
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model Jun 1, 2025

  VLA
• Operator Flow Matching for Timeseries Forecasting Jun 1, 2025

  flow-matching
• Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful Jun 1, 2025
• Streaming Flow Policy: Simplifying Diffusion/Flow-Matching Policies by Treating Action Trajectories as Flow Trajectories Jun 1, 2025

  flow-matching
• $\pi_{0.5}$: A Vision-Language-Action Model with Open-World Generalization Jun 1, 2025