Stars
A vector index built on TurboQuant, written in Rust with Python bindings
Curated list of datasets and tools for post-training.
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny co…
[ICLR2026] There is No VAE: End-To-End Pixel-Space Generative Modeling Via Self-Supervised Pre-Training
[ECCV 2026] Towards Scalable Pre-training of Visual Tokenizers for Generation
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
Official implementation of HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration (SIGGRAPH 2025)
MedSAM3: Delving into Segment Anything with Medical Concepts
Segment Anything in Medical Images
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
[CVPR 2025] BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
[ CVPR 2025 ] We introduce LT3SD, a novel latent 3D scene diffusion approach enabling high-fidelity generation of infinite 3D environments in a patch-by-patch and coarse-to-fine fashion.
This repository contains the implementation of our novel approach associated with the paper "Don't Splat Your Gaussians" to modeling and rendering scattering and emissive media using volumetric pri…
This repo contains the official implementation for the paper "Neural Reconstruction through Scattering Media with Forward and Backward Losses".
All Algorithms implemented in Python
[NeurIPS 2025] Official repository for "Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling"
A summary of related works about flow matching, stochastic interpolants
collection of diffusion model papers categorized by their subareas
PyTorch implementation of RCG https://arxiv.org/abs/2312.03701
Code and data for "Three-dimensional imaging through scattering media based on confocal diffuse tomography"
Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"
The official pytorch implementation of "NLOS-NeuS: Non-line-of-sight Neural Implicit Surface," ICCV2023.
Neural transient field for non-line-of-sight imaging
[CVPR 2024] This repository includes the official implementation our paper "MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections"