SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

Everything about the SmolLM & SmolLM2 family of models

An Open Large Reasoning Model for Real-World Solutions

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models

Automatically update arXiv papers about SOT & VLT, Multi-modal Learning, LLM and Video Understanding using Github Actions.

Uniform Manifold Approximation and Projection

AdalFlow: The library to build & auto-optimize LLM applications.

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

Building modular LMs with parameter-efficient fine-tuning.

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

LLM KV cache compression made easy

Automatic Evals for Instruction-Tuned Models

Training Sparse Autoencoders on Language Models

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

A profiling and performance analysis tool for TensorFlow

RAG that intelligently adapts to your use case, data, and queries

Library for managing LLM interactions

Dynamiq is an orchestration framework for agentic AI and LLM applications

User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)

Go-blueprint allows users to spin up a quick Go project using a popular framework

WebApps in pure Python. No JavaScript, HTML and CSS needed

Simple script that reads an image and dumps the text it reads using a vision model and KobolodCPP

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340