Code accompanying the paper "Guiding a diffusion model with itself using sliding windows" accepted at BMVC 2025, based on open source code and weights of existing class-conditional diffusion models

Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers" (NeurIPS '25 Spotlight)

Out-of-distribution detection, robustness, and generalization resources. The repository contains a curated list of papers, tutorials, books, videos, articles and open-source libraries etc

WAVC2025: Rethinking cluster-conditioned diffusion models for label-free image synthesis

LLM101n: Let's build a Storyteller

Volumetric structures such as voxels and SDFs implemented in pytorch

Minimal multi-gpu implementation of Diffusion Models with Classifier-Free Guidance (CFG)

Official repository for "AM-RADIO: Reduce All Domains Into One"

LLM training in simple, raw C/CUDA

Labels and other data for the paper "Are we done with ImageNet?"

All the resources you need to get to Senior Engineer and beyond

List of books, blogs, newsletters and people!

A library for efficient similarity search and clustering of dense vectors.

pix2tex: Using a ViT to convert images of equations into LaTeX code.

[BMVC2023] Official code for TEMI: Exploring the Limits of Deep Image Clustering using Pretrained Models

Code for our TMLR 2024 paper: Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection https://arxiv.org/abs/2303.05828

This is the official implementation for Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models.

uBlock Origin filter list to hide YouTube Shorts

Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Advanced Topics in Artificial Intelligence, NUS CS6208, 2023

Representation Learning MSc course Summer Semester 2023

Vector (and Scalar) Quantization, in Pytorch

An open source implementation of CLIP.

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

A collection of 100 Deep Learning images and visualizations

Metrics for out-of-distribution (OOD) detection performance evaluation

iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Nature Methods: RNA foundation model (together with RhoFold)