SII - Generative Artificial Intelligence Research Lab (GAIR)

All

37 repositories

OctoThinker
Public
Revisiting Mid-training in the Era of RL Scaling
Jupyter Notebook
•
Apache License 2.0
•1•33•0•0•Updated Apr 24, 2025Apr 24, 2025
cognition-engineering
Public
Generative AI Act II: Test Time Scaling Drives Cognition Engineering
Python
•7•149•1•0•Updated Apr 22, 2025Apr 22, 2025
ProX
Public
Offical Repo for "Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale"
llama data-quality mistral pre-training continual neural-symbolic data-centric-ai llm continual-pre-training
Python
•
Apache License 2.0
•17•240•1•0•Updated Apr 18, 2025Apr 18, 2025
DeepResearcher
Public
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
Python
•
Apache License 2.0
•21•295•3•0•Updated Apr 13, 2025Apr 13, 2025
MAYE
Public
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Python
•6•119•3•0•Updated Apr 9, 2025Apr 9, 2025
LIMO
Public
LIMO: Less is More for Reasoning
Python
•47•924•4•0•Updated Apr 6, 2025Apr 6, 2025
simple_tts
Public
Python
•0•0•0•0•Updated Apr 5, 2025Apr 5, 2025
MathPile
Public
[NeurlPS D&B 2024] Generative AI for Math: MathPile
math corpus language-model pre-training large-language-models
Python
•
Apache License 2.0
•21•411•0•0•Updated Apr 4, 2025Apr 4, 2025
ToRL
Public
Python
•7•139•10•0•Updated Apr 2, 2025Apr 2, 2025
cs2916
Public
Python
•14•26•0•0•Updated Mar 27, 2025Mar 27, 2025
AIME-Preview
Public
Python
•1•60•2•0•Updated Mar 11, 2025Mar 11, 2025
OlympicArena
Public
[NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
JavaScript
•4•101•0•0•Updated Mar 6, 2025Mar 6, 2025
LIMR
Public
Python
•8•190•10•0•Updated Feb 20, 2025Feb 20, 2025
O1-Journey
Public
O1 Replication Journey
65•2k•14•0•Updated Jan 14, 2025Jan 14, 2025
PC-Agent
Public
PC Agent: While You Sleep, AI Works - A Cognitive Journey into Digital World
Python
•
MIT License
•20•235•0•0•Updated Dec 25, 2024Dec 25, 2024
ReasonEval
Public
[AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy
Python
•3•60•0•0•Updated Dec 15, 2024Dec 15, 2024
walnut-plan
Public
The Walnut Plan
0•11•0•0•Updated Oct 10, 2024Oct 10, 2024
OpenResearcher
Public
OpenResearcher, an advanced Scientific Research Assistant
HTML
•
Apache License 2.0
•36•442•1•2•Updated Oct 10, 2024Oct 10, 2024
math-evaluation-harness
Public
A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨
Python
•
MIT License
•16•2•0•0•Updated Oct 6, 2024Oct 6, 2024
ReAlign
Public
Reformatted Alignment
nlp natural-language-processing alignment large-language-models llms generative-ai
JavaScript
•7•115•0•0•Updated Sep 23, 2024Sep 23, 2024
weak-to-strong-reasoning
Public
Python
•4•59•1•0•Updated Sep 2, 2024Sep 2, 2024
factool
Public
FacTool: Factuality Detection in Generative AI
python natural-language-processing fact-checking large-language-models generative-ai chatgpt
Python
•
Apache License 2.0
•66•866•20•3•Updated Aug 19, 2024Aug 19, 2024
BeHonest
Public
BeHonest: Benchmarking Honesty in Large Language Models
nlp benchmark evaluation alignment honesty llm
JavaScript
•0•31•0•0•Updated Aug 15, 2024Aug 15, 2024
anole
Public
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
Python
•44•753•30•1•Updated Aug 5, 2024Aug 5, 2024
Safety-J
Public
Safety-J: Evaluating Safety with Critique
JavaScript
•1•16•0•0•Updated Jul 28, 2024Jul 28, 2024
MoPS
Public
[ACL 2024] Code for "MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation"
Jupyter Notebook
•1•36•0•0•Updated Jul 19, 2024Jul 19, 2024
self-improvement-reversal
Public
JavaScript
•0•13•1•0•Updated Jul 14, 2024Jul 14, 2024
MetaCritique
Public
Evaluate the Quality of Critique
Python
•
Apache License 2.0
•0•34•0•0•Updated Jun 1, 2024Jun 1, 2024
alignment-for-honesty
Public
Python
•2•73•0•0•Updated May 22, 2024May 22, 2024
benbench
Public
Benchmarking Benchmark Leakage in Large Language Models
dataset benchmarks leakage-detection large-language-models
JavaScript
•3•51•4•0•Updated May 20, 2024May 20, 2024