An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
7 daysStars3.8k24h gain+34Score22.1
Search
Find trending repositories by name or description.
21 results for “post-training”
RankRepository7 daysStars24h gainScore
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
7 daysStars24.2k24h gain+10Score7.5
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
7 daysStars3.3k24h gain+6Score3.9
A unified inference and post-training framework for accelerated video generation.
7 daysStars4.8k24h gain+5Score3.2
AllenAI's post-training codebase
7 daysStars3.9k24h gain+3Score2.4
Daily notes on AI research, especially those on LLMs, VLMs, AI agents and related techniques such as pre-, mid-, post-training, RL, continual learning, test-time scaling, RSI, and more.
7 daysStars18224h gain+1Score0.3
High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogeneous engines and extreme memory efficiency for GRPO, PPO, etc.
7 daysStars45824h gain0Score0.2
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
7 daysStars96624h gain0Score0.0
A Lightweight LLM Post-Training Library
7 daysStars2.5k24h gain-Score0.0
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
7 daysStars41124h gain-Score0.0
Post-training with Tinker
7 daysStars4.2k24h gain-Score0.0
[ICLR 2026] RecA: Self-supervised post-training for unified multimodal models, improving image generation through visual understanding.
7 daysStars41424h gain-Score0.0
🔥🔥🔥 [TMLR] Video Generation Models: A Survey of Post-Training and Alignment | A continuously updated collection of papers, datasets, and benchmarks on post-training and alignment for video generation.
7 daysStars19724h gain-Score0.0
An asynchronous streaming data management module for efficient post-training.
7 daysStars17324h gain0Score0.0
A project implementing various agentic RL based on the Slime post-training framework
7 daysStars45324h gain-Score0.0
WorldEngine: Towards the Era of Post-Training for Autonomous Driving
7 daysStars44324h gain-Score0.0
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
7 daysStars49824h gain-Score0.0
Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.
7 daysStars19324h gain-Score0.0
An LLM post-training framework with vLLM for RL Scaling
7 daysStars49924h gain+1Score0.0
On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
7 daysStars50024h gain-Score0.0
AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.
7 daysStars46124h gain-Score0.0