Repo đang lênCập nhật hằng ngày từ GitHub

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.

DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

Constrained optimization toolkit for PyTorch

Sketch Your Own GAN: Customizing a GAN model with hand-drawn sketches.

Open-source AI-powered data science platform.

Cookiecutter template for FastAPI projects using: Machine Learning, uv, Github Actions and Pytests

LLMFlows - Simple, Explicit and Transparent LLM Apps

PaddleNLP UIE模型的PyTorch版实现

A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.

Implementations of various VAE-based semi-supervised and generative models in PyTorch

Practical Full-Stack Machine Learning

A curated list of resources focused on Machine Learning in Geospatial Data Science.

[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

A Python frontend and library for ComfyUI

Live2D Virtual Human for Chatting based on Unity

DenseNet implementation in Keras

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

This is the open-source version of ICRA 2019 submission "Real-time Scalable Dense Surfel Mapping"

An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group

Code for Hands-on Unsupervised Learning Using Python (O'Reilly Media)

Machine learning algorithms for many-body quantum systems

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

Top 100 trending deep learning repositories sorted by the number of stars gained on a specific day.

TonY is a framework to natively run deep learning frameworks on Apache Hadoop.

Event-sourced graph runtime for durable and stateful agents

DiffuEraser is a diffusion model for video inpainting, which performs great content completeness and temporal consistency while maintaining acceptable efficiency.

PyTorch implementation of CNNs for CIFAR benchmark

PyTorch for Numpy users. https://pytorch-for-numpy-users.wkentaro.com

A neural network for end-to-end speech denoising

Minimal Seq2Seq model with Attention for Neural Machine Translation in PyTorch

DeepTables: Deep-learning Toolkit for Tabular data

Facebook chatbot that I trained to talk like me using Seq2Seq

The PyTorch implementation of STGCN.

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)

Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries

A Full Stack ML (Machine Learning) Roadmap involves learning the necessary skills and technologies to become proficient in all aspects of machine learning, including data collection and preprocessing, model development, deployment, and maintenance.

Community desktop companion for DeepSeek Harness — one-click Electron app for macOS and Windows

Real-time Hand Gesture Recognition with PyTorch on EgoGesture, NvGesture, Jester, Kinetics and UCF101

Finetune ModelScope's Text To Video model using Diffusers 🧨

The javascript presentation library for the automation era.

🥰 Building AI-based conversational avatars lightning fast ⚡️💬

Generating Videos with Scene Dynamics. NIPS 2016.

An end-to-end library for automatic character rigging, skinning, and blend shapes generation, as well as a visualization tool [SIGGRAPH 2021]

Submarine is Cloud Native Machine Learning Platform.

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

An AI Skill Runtime for knowledge-intensive work which makes everything under your control.