A computer algebra system written in pure Python

ML Benchmarks in Algebraic Combinatorics

A Lightweight library for concept/sentence/paragraph extraction with negation detection.

A flexible and efficient training framework for large-scale alignment tasks

An Open-Source Package for Knowledge Embedding (KE)

Clinical Histopathology Imaging Evaluation Foundation Model

A modular graph-based Retrieval-Augmented Generation (RAG) system

GenoBoost: Polygenic method using non-additive models

SMAC: The StarCraft Multi-Agent Challenge

MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)

SWE-bench: Can Language Models Resolve Real-world Github Issues?

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

🐚 OpenDevin: Code Less, Make More

Natural Number Game

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Models [TMLR]

Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation [NAACL 2024]

🙌 OpenHands: AI-Driven Development

Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Code and data for TrialGPT.

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

DeepConsensus uses gap-aware sequence transformers to correct errors in Pacific Biosciences (PacBio) Circular Consensus Sequencing (CCS) data.

[NeurIPS 2023] Official codes of "MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data"

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".