Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determining generation length and maintaining KV-cache compatibility, achieving high eff…

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

Reference PyTorch implementation and models for DINOv3

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

The official Python SDK for Model Context Protocol servers and clients

한국어 데이터 세트 링크

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Official repository for "VideoPrism: A Foundational Visual Encoder for Video Understanding" (ICML 2024)

A high-throughput and memory-efficient inference and serving engine for LLMs

Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.

PyTorch code and models for VJEPA2 self-supervised learning from video.

[CVPR 2023] "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation" official implementation.

MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;

Real-time Action detection demo for the work Actor Conditioned Attention Maps. This repo includes a complete pipeline for person detection/tracking and analyzing their actions in real-time.

Demo of a customer service use case implemented with the OpenAI Agents SDK

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey [Miyai+, TMLR2025]

[ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

A python module to repair invalid JSON from LLMs

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Awesome list for LLM quantization

[CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

Anthropic's Interactive Prompt Engineering Tutorial

Kernels & AI inference engine for phones

Vision-Language Model Emergency Recognition Evaluation

Real-time webcam demo with SmolVLM and llama.cpp server

OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.