Repository History
Explore all analyzed open source repositories
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper2Code is an innovative multi-agent LLM system designed to automate the generation of code repositories directly from scientific papers in machine learning. It employs a sophisticated three-stage pipeline, encompassing planning, analysis, and code generation, each managed by specialized agents. This approach ensures faithful and high-quality implementations, outperforming existing baselines on relevant benchmarks.
Transformer Lab App: An Open Source Platform for Frontier AI/ML Workflows
Transformer Lab App is an open-source machine learning research platform designed for frontier AI/ML workflows. It provides a comprehensive toolkit for large language models, allowing users to train, tune, and chat on their own machines, whether locally, on-prem, or in the cloud. Backed by Mozilla, this cross-platform application simplifies experimentation with a wide range of models.
big_vision: Google Research's Codebase for Large-Scale Vision Models
big_vision is Google Research's official codebase for training large-scale vision models using Jax/Flax. It has been instrumental in developing prominent architectures like Vision Transformer, SigLIP, and MLP-Mixer. This repository offers a robust starting point for researchers to conduct scalable vision experiments on GPUs and Cloud TPUs, scaling seamlessly from single cores to distributed setups.
HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation
HunyuanVideo-Avatar is a cutting-edge project by Tencent-Hunyuan for high-fidelity, audio-driven human animation. Utilizing a multimodal diffusion transformer, it generates dynamic, emotion-controllable, and multi-character dialogue videos. This innovative system addresses critical challenges in character consistency, emotion alignment, and multi-character animation, making it suitable for diverse applications like e-commerce and social media.
TextMachina: A Python Framework for MGT Dataset Generation
TextMachina is a modular and extensible Python framework designed for creating high-quality, unbiased datasets for Machine-Generated Text (MGT) tasks. It supports detection, attribution, and boundary detection, offering a user-friendly pipeline with LLM integrations, prompt templating, and bias mitigation. This tool streamlines the process of building robust models for understanding and identifying AI-generated content.
Agent-S: Open Agentic Framework for Human-like Computer Use
Agent-S is an open agentic framework designed to enable autonomous interaction with computers, allowing AI agents to use machines like humans. It provides intelligent GUI agents that learn from past experiences to perform complex tasks. This framework is a cutting-edge solution for AI automation and advanced agent-based systems.
Awesome AI Agents: A Curated List of 300+ Agentic AI Resources
Awesome AI Agents is a comprehensive, community-curated list featuring over 300 agentic AI resources, tools, and frameworks. Maintained by Slava Kurilyak, this repository serves as an essential guide for anyone exploring the rapidly evolving landscape of AI agents. It provides a centralized hub to discover new projects, understand different development approaches, and stay updated with the latest advancements in the field.
StreamDiffusion: Real-Time Interactive Generation with Diffusion Pipelines
StreamDiffusion is an innovative diffusion pipeline designed for real-time interactive generation, significantly enhancing the performance of current diffusion-based image generation techniques. It offers a pipeline-level solution to achieve high-speed image and text-to-image generation, making interactive AI experiences more accessible. This project introduces several key features to optimize computational efficiency and GPU utilization.
Toolkit-for-Prompt-Compression: A Unified Toolkit for LLM Prompt Compression
PCToolkit is a unified, plug-and-play toolkit designed for efficient prompt compression in Large Language Models (LLMs). It provides state-of-the-art compression methods, diverse datasets, and comprehensive metrics for evaluating performance. This modular toolkit simplifies the process of condensing input prompts while preserving crucial information.
Picotron: Minimalistic 4D-Parallelism Framework for LLM Training Education
Picotron is a minimalistic and hackable distributed training framework designed for educational purposes. Inspired by NanoGPT, it focuses on pre-training Llama-like models using 4D Parallelism, making complex concepts accessible. Its simple and readable codebase, with core files under 300 lines, provides an excellent tool for learning and experimentation in distributed machine learning.
Judgy: Correcting LLM Judge Bias for Reliable AI Model Evaluation
Judgy is a Python package designed to improve the reliability of evaluations performed by LLM-as-Judges. It provides tools to estimate the true success rate of a system by correcting for LLM judge bias and generating confidence intervals through bootstrapping. This helps ensure more accurate and trustworthy assessments of AI model performance.
GenerativeAICourse: A Comprehensive Hands-On Generative AI Engineering Course
This repository offers a comprehensive, hands-on Generative AI course, starting from fundamental AI concepts to building production-grade applications. It focuses on AI engineering, covering topics like LLMs, RAG, AI agents, and prompt engineering with practical tutorials. The course aims to equip learners with the skills needed to build real-world AI solutions.