[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]

The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"

[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

[NeurIPS 2024] Agent Planning with World Knowledge Model

Framework enabling modular interchange of language agents, environments, and optimizers

Official code repo for the paper "LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset"

The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Process" (arxiv 2407.20311) and "Physics of Language Models Part 2…

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning (NeurIPS2026-SEA)

🧪 A comprehensive chemistry library for Python.

ChemReasoner - Catalyst Discovery via Large Language Model-driven Reasoning

Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.

The code implementation of Symbolic-MoE

[NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"

The simplest, fastest repository for training/finetuning medium-sized GPTs with LoRA support.

simpleR1: A Simple Framework for Training R1-like Models

[ICLR 2024 Spotlight] "Negative Label Guided OOD Detection with Pretrained Vision-Language Models"

[NeurIPS 2024] "Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection"

[ICML 2025] Hierarchical Graph Tokenization for Molecule-Language Alignment

[NeurIPS 2024 Oral] "Bayesian-Guided Label Mapping for Visual Reprogramming"

[NeurIPS 2024] "What If the Input is Expanded in OOD Detection?"

Python translation (and extension) of the Tetrad java code.