Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
cs.LG
Submitted: 2026-01-29
Updated: 2026-11-16
Code: https://github.com/XinPeng76/Flow_
Terminology
Sources
- NICE: Non-linear Independent Components Estimation
- Sampling from Energy-based Policies using Diffusion
- Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning
- FlowRL: Matching Reward Distributions for LLM Reasoning
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