Stars
PyTorch code and models for VJEPA2 self-supervised learning from video.
[CVPR2026 Findings] VHS: Verifier on Hidden States, an efficient inference-time scaling verification framework for DiT-based image generation.
[CVPR 2026] Official repository for "Reviving ConvNeXt for Efficient Convolutional Diffusion Models"
[WACV2026] PaRaChute: Pathology-Radiology Cross-Modal Fusion for Missing-Modality-Robust Survival Prediction
[WACV 2026] Official implementation of the paper: “CountingDINO: A Training-free Pipeline for Exemplar-based Class-Agnostic Counting”
Official inference repo for FLUX.2 models
LLM Council works together to answer your hardest questions
[AAAI2026] Mitigating Negative Flips via Margin Preserving Training
A simple MCP server that let you gather marine forecast data from OpenMeteo.
[ECCV'24] Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities
[ICCV 2025] What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models
[ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"
[CVPR 2026] Official Repository of the Paper "One Patch to Caption Them All A Unified Zero-Shot Captioning Framework"
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
Realtime voice-enabled AI assistant that can engage in natural conversations
A from-scratch GPT built with NumPy and Python’s standard library. No autograd, no frameworks: every layer is re-implemented with its own forward and backward pass. Gradients are computed manually,…
Make huge neural nets fit in memory
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)
Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
A simple local Retrieval-Augmented Generation (RAG) chatbot that can answer to questions by acquiring information from personal PDF documents.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A self-hosted web application to track boardgames matches within your group of friends
A PyTorch native platform for training generative AI models
Easy wrapper for inserting LoRA layers in CLIP.