MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Paper
• 2507.21183 • Published
• 15
Finetuning Strategies
-
-
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Paper • 2507.21802 • Published • 19 -
EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Paper • 2507.21848 • Published • 9 -
Agentic Reinforced Policy Optimization
Paper • 2507.19849 • Published • 158 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 160 -
DCPO: Dynamic Clipping Policy Optimization
Paper • 2509.02333 • Published • 22 -
Towards a Unified View of Large Language Model Post-Training
Paper • 2509.04419 • Published • 76 -
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
Paper • 2509.11452 • Published • 14 -
Reinforcement Learning on Pre-Training Data
Paper • 2509.19249 • Published • 67 -
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Paper • 2510.07242 • Published • 30 -
Reinforcing Diffusion Models by Direct Group Preference Optimization
Paper • 2510.08425 • Published • 12 -
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
Paper • 2509.25771 • Published • 11 -
Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
Paper • 2511.07419 • Published • 27 -
Video Generation Models Are Good Latent Reward Models
Paper • 2511.21541 • Published • 45 -
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Paper • 2601.08763 • Published • 148 -
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Paper • 2601.02151 • Published • 109