End-to-end Generative Optimization for AI Agents

VisualWebArena is a benchmark for multimodal agents.

A instruction data generation system for multimodal language models.

AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ

A Refcount-guided Fuzzer for Exposing Temporal Memory Errors in Linux Kernel

Scripts for artifaction of viper

Demonstrating the BadAss issue.

A list of data-only attacks

A tool for automatically identifying syscall-guard variables

Coveraged-based fuzzer for finding DBMS logical bugs

[ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

A curated list of insanely awesome libraries, packages and resources for systematic trading. Crypto, Stock, Futures, Options, CFDs, FX, and more | 量化交易 | 量化投资

AWM: Agent Workflow Memory

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

A programming framework for agentic AI. Discord: https://discord.gg/pAbnFJrkgZ

Embodied and organized multi-LLM-agent teams supporting communication for >3 agents. Source codes for the paper "Embodied LLM Agents Learn to Cooperate in Organized Teams".

DeepONet & FNO (with practical extensions)

[NeurIPS 2024] A task generation and model evaluation system for multimodal language models.

交易模块

[ICML 2024] 🍅HumanTOMATO: Text-aligned Whole-body Motion Generation

🐝 GPTSwarm: LLM agents as (Optimizable) Graphs

[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

Official implementation of Captain Agent

PyTorch deep learning projects made easy.

SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

m&ms: A Benchmark to Evaluate Tool-Use for multi-step multi-modal tasks

Codebase for PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs.