[Nature 2026] Merlin is a 3D VLM for computed tomography that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining.

Collection of awesome medical dataset resources.

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

[TMI 2022] BowelNet: Joint Semantic-Geometric Ensemble Learning for Bowel Segmentation from Both Partially and Fully Labeled CT Images

Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)

🇰🇷파이토치에서 제공하는 튜토리얼의 한국어 번역을 위한 저장소입니다. (Translate PyTorch tutorials in Korean🇰🇷)

Official Implementation of CVPR'26 paper "Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learning"

Official implementation of the CVPR '25 highlight paper "Compositional Caching for Training-free Open-vocabulary Attribute Detection"

[ICLR 25, TPAMI 26, CVPR 26] Track-On: Online Point Tracking with Memory

PyTorch Implementation of Learning to Prompt (L2P) for Continual Learning @ CVPR22

[ICCV 2025 Oral] Official implementation of Learning Streaming Video Representation via Multitask Training.

Beautiful & consistent icon toolkit made by the community. Open-source project and a fork of Feather Icons.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Fast and memory-efficient exact attention

Official implementation for paper TEVAD: Improved video anomaly detection with captions

High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI

[CVPR-2024] Official implementations of CLIP-KD: An Empirical Study of CLIP Model Distillation

[ICCV 2025] MobileViCLIP: An Efficient Video-Text Model for Mobile Devices

This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025

VadCLIP official Pytorch implementation

Implementation of "CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection" (ICIP 2023)

Code for Spotting Temporally Precise, Fine-Grained Events in Video

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

(TPAMI 2024) A Survey on Open Vocabulary Learning