[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Multimodal computer agent data collection program

Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch

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

Official repository for the Boltz-1 biomolecular interaction model

Mastering Diverse Domains through World Models

Interpretable Contrastive Monte Carlo Tree Search Reasoning

Reproducible, flexible LLM evaluations

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

A simple screen parsing tool towards pure vision based GUI agent

Simple package for literate programming in Julia

Distribute and run LLMs with a single file.

Protein Ligand INteraction Dataset and Evaluation Resource

Investment Research for Everyone, Everywhere.

🤱🏻 Turn any webpage into a desktop app with Rust. 🤱🏻 利用 Rust 轻松构建轻量级多端桌面应用

aider is AI pair programming in your terminal

YouTube™ content blocker

📚 Parameterize, execute, and analyze notebooks

The AdEMAMix Optimizer: Better, Faster, Older.

Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

pseudocode and algorithms for the paper "Alpha$^2$: Discovering Logical Formulaic Alphas using Deep Reinforcement Learning"

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claud…

PINDER: The Protein INteraction Dataset and Evaluation Resource

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

End-to-end Generative Optimization for AI Agents

Low-level unprivileged sandboxing tool used by Flatpak and similar projects

Agentic components of the Llama Stack APIs