LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework
-
Updated
Sep 7, 2026 - Python
#
dapo
Here are 13 public repositories matching this topic...
Codebase of GRPO: Implementations and Resources of GRPO and Its Variants
-
Updated
Dec 6, 2025 - Python
Open Ended Medical Reinforcement Learning
medical-vqa medical-vision-language-model grpo dapo medical-reinforcement-learning open-ended-medical-reasoning open-ended-reinforcement-learning open-ended-rl medical-rl
-
Updated
Mar 15, 2026 - Python
Exact finite-group identity behind GRPO reward standardization, unifying GRPO / Dr. GRPO / DAPO for RLVR and LLM reasoning. Paper + code.
-
Updated
Jul 2, 2026 - TeX
Process-supervised RL for a multi-step reasoning agent — DAPO + a learned Process Reward Model (PRM) training a Qwen3-8B Planner. A modern, from-scratch rebuild of the AgentFlow paper (ICLR 2026).
machine-learning reinforcement-learning ai-agents trl llm rlhf reward-model qlora ollama qwen llm-fine-tuning unsloth agentic-ai process-reward-model grpo dapo
-
Updated
Jun 2, 2026 - Python
Sync vs fully-async agentic RL on verl: multi-turn GRPO, long-tail rollout profiling, staleness ablations — quantifying when async pays off.
reinforcement-learning rollout slime post-training multi-turn megatron gspo llm-agent tool-calling verl dapo agentic-rl async-training
-
Updated
Sep 8, 2026 - Python
Unofficial PyTorch reproduction for DAPO: An Open-Source LLM Reinforcement Learning System at Scale.
reinforcement-learning pytorch reproduction policy-optimization llm-reasoning dapo unofficial-implementation
-
Updated
Jul 2, 2026 - Python
Add this topic to your repo
To associate your repository with the dapo topic, visit your repo's landing page and select "manage topics."