… For distributional consistency, we apply a token-level surrogate KL penalty against the worst-case augmentation; to prevent policy collapse under regularization, an auxiliary policy gradient loss anchored to clean-image advantages preserves a reliable reward signal; and to avoid systematically inco… …
… We introduce the best entropy curve and the trick to achieve it for any policy-gradient method. …
… The following papers were recommended by the Semantic Scholar API $R \text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation 2026 S-GRPO: Unified Post-Training for Large Vision-Language Models 2026 OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models 2026 … …
… The following papers were recommended by the Semantic Scholar API From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning 2026 Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning 2026 LaST-R1: Reinforcing Ac… …
… The following papers were recommended by the Semantic Scholar API Flow Matching Policy with Entropy Regularization 2026 ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching 2026 Truncated Rectified Flow Policy for Reinforcement Learning with One-Step … …
… We introduce Policy Optimization with Internal State Value Estimation , which obtains a baseline at negligible cost by using the policy model's internal signals already computed during the policy forward pass. …
… The following papers were recommended by the Semantic Scholar API Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents 2026 Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing 2026 Revisiting On-Policy Distillation: Empirical Failure Modes and Sim… …
… The following papers were recommended by the Semantic Scholar API Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent 2026 HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation 2026 PAI… …
… To improve training efficiency and stability, we propose Turn-level Truncated On-Policy Distillation TT-OPD , a self-distillation framework where a gradient-free EMA teacher leverages outcome-privileged information to provide dense, outcome-aware KL regularization at every conversation turn. …
… The following papers were recommended by the Semantic Scholar API AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning 2026 Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy Modulation 2026 CLIPO: Contrastive Learning in Po… …
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.