Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

Code of "Differentiable Protein Engineering through using Diffusion Transformer over ProTokens"

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

PyTorch building blocks for the OLMo ecosystem

Labs for MIT 6.S184/6.S975, IAP 2025/2026

A curated collection of papers, datasets, and resources on Scientific Datasets and Large Language Models (LLMs)

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

[ACL 2025] SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science🌾

[ACL 24 Findings] Implementation of Resonance RoPE and the PosGen synthetic dataset.

[TOSEM'25] The official GitHub page for the survey paper "A Survey on Large Language Models for Code Generation".

A collection of papers on discrete diffusion models

[ICML 2025] The Diffusion Duality

[TMLR‘26] Discrete Diffusion in Large Language and Multimodal Models: A Survey

byteff source code

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

Accompanied repositories for our paper Graph foundation model

Generative Pre-trained Graph Eulerian Transformer [ICML2025]

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Diffusion Reinforcement Learning Library

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Implementation of OpenAI paper with Simple Noise Scale on Fastai V2