SII - Generative Artificial Intelligence Research Lab (GAIR)
GAIR is part of SII, focusing on Generative Artificial Intelligence Research, with joint effort from SJTU.
Pinned Repositories
abel
SOTA Math Opensource LLM
anole
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
ASI-Arch
AlphaGo Moment for Model Architecture Discovery.
DeepResearcher
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
factool
FacTool: Factuality Detection in Generative AI
LIMO
[COLM 2025] LIMO: Less is More for Reasoning
MathPile
[NeurlPS D&B 2024] Generative AI for Math: MathPile
O1-Journey
O1 Replication Journey
OpenResearcher
OpenResearcher, an advanced Scientific Research Assistant
ToRL
SII - Generative Artificial Intelligence Research Lab (GAIR)'s Repositories
GAIR-NLP/O1-Journey
O1 Replication Journey
GAIR-NLP/ASI-Arch
AlphaGo Moment for Model Architecture Discovery.
GAIR-NLP/LIMO
[COLM 2025] LIMO: Less is More for Reasoning
GAIR-NLP/anole
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
GAIR-NLP/DeepResearcher
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
GAIR-NLP/OpenResearcher
OpenResearcher, an advanced Scientific Research Assistant
GAIR-NLP/MathPile
[NeurlPS D&B 2024] Generative AI for Math: MathPile
GAIR-NLP/ToRL
GAIR-NLP/PC-Agent
PC Agent: While You Sleep, AI Works - A Cognitive Journey into Digital World
GAIR-NLP/ProX
[ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
GAIR-NLP/LIMR
GAIR-NLP/cognition-engineering
Generative AI Act II: Test Time Scaling Drives Cognition Engineering
GAIR-NLP/OctoThinker
Revisiting Mid-training in the Era of Reinforcement Learning Scaling
GAIR-NLP/MAYE
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
GAIR-NLP/PC-Agent-E
Efficient Agent Training for Computer Use
GAIR-NLP/OlympicArena
[NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
GAIR-NLP/thinking-with-generated-images
Doodling our way to AGI ✏️ 🖼️ 🧠
GAIR-NLP/MegaScience
MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
GAIR-NLP/AIME-Preview
GAIR-NLP/ReasonEval
[AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy
GAIR-NLP/ResearcherBench
ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry
GAIR-NLP/cs2916
GAIR-NLP/lm-open-science-evaluation
Reproducible and flexible LLM evaluations for scientific reasoning.
GAIR-NLP/DatasetResearch
DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery
GAIR-NLP/LIMOPro
GAIR-NLP/walnut-plan
The Walnut Plan
GAIR-NLP/DynToM
GAIR-NLP/ASI4AI
GAIR-NLP/WindowsAgentArena-V2
GAIR-NLP/simple_tts