Code for Paper: Learning Adaptive Parallel Reasoning with Language Models
Official PyTorch implementation for "Large Language Diffusion Models"
RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
Hybrid Latent Reasoning via Reinforcement Learning
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
A Survey on Multimodal Retrieval-Augmented Generation
[SIGIR 2025] The official repo for "Scaling Sparse and Dense Retrieval in Decoder-Only LLMs"
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
The official implementation of Self-Play Preference Optimization (SPPO)
Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".
[ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
Textbook on reinforcement learning from human feedback
Minimal reproduction of DeepSeek R1-Zero
Codes for Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
Medical o1, Towards medical complex reasoning with LLMs
Search-o1: Agentic Search-Enhanced Large Reasoning Models
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Async Agent RL)
AirLLM 70B inference with single 4GB GPU
This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.