post-training

A unified inference and post-training framework for accelerated video generation.

Awesome Reasoning LLM Tutorial/Survey/Guide

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

Explore the Multimodal “Aha Moment” on 2B Model

Train a Language Model with GRPO to create a schedule from a list of events and priorities

Revisiting Mid-training in the Era of Reinforcement Learning Scaling

A brief and partial summary of RLHF algorithms.

A collection of vision-language-action model post-training methods.

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

[NeurIPS 2025] Flow x RL. Official Implementation of "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning".

A High-Efficiency System of Large Language Model Based Search Agents

[CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis

[NeurIPS 2025 Oral] Exploring Diffusion Transformer Designs via Grafting

A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward models and learning strategies across training, inference, and post-inference stages.

Official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)

Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".

[EMNLP 2022] Continual Training of Language Models for Few-Shot Learning

A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.

Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.

Official implementation for "Diffusion Instruction Tuning"