slime is an LLM post-training framework for RL Scaling.

PyTorch code and models for VJEPA2 self-supervised learning from video.

Official implementation of TreeSynth: Synthesizing Diverse Data via Tree-Guided Subspace Partitioning (NeurIPS 2025 Spotlight).

Official code of RDT 2

CellVerse: Do Large Language Models Really Understand Cell Biology?

LeKiwi - Low-Cost Mobile Manipulator

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Minimal reproduction of DeepSeek R1-Zero

AllenAI's post-training codebase

GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.

MSA Transformer reproduction code

AlphaFold 3 inference pipeline.

[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

A Neural Framework for MT Evaluation

Transformers for Cantonese

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

A command-line tool for tweaking WeChat - 首款微信 macOS 客户端撤回拦截与多开 🔨

Implementation of Nougat Neural Optical Understanding for Academic Documents