Highlights
- Pro
Lists (3)
Stars
Official Inspect Implementation for "ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases"
A Diagnostic Guardrail Framework for AI Agent Safety and Security
A curated list of Multi-Modal Reinforcement Learning resources (continually updated)
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark.
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
A version of verl to support diverse tool use
My learning notes for ML SYS.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
open source codebase for BioRiskEval
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
[ICLR'26] Stronger-MAS: A RL Framework for multi LLM agent system
slime is an LLM post-training framework for RL Scaling.
verl: Volcano Engine Reinforcement Learning for LLMs
An extensible RL framework for training LLM agents with advanced search capabilities, built on VERL and supporting state-of-the-art search strategies.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!
Foundation Models for Genomics & Transcriptomics
Curated coding interview preparation materials for busy software engineers
Pretraining infrastructure for multi-hybrid AI model architectures