github Changing-look AGN (CLAGN) are quasars that switch spectral type over months to years — direct evidence of an accretion-state transition around a supermassive black hole. They’re rare (~1,000 known) and almost all of them were found by accident, in spectral repeat visits nobody scheduled specifically to catch one. If the transition leaves a signature in the photometry — the light curve alone, no spectrum required — you could search for CLAGN systematically across every quasar a survey has ever imaged, instead of waiting to get lucky....

LatentLinter is a lightweight PyTorch manifold constraint that penalizes out-of-distribution (OOD) latent states and stabilizes gradient planners.

A living resource for Vision-Language Models & multimodal learning

PyTorch implementations of research papers, aimed at deepening my understanding of the underlying concepts.

MATS, a behavioral audit for vision language models, identifies systematic failures in spatial consistency and suggests repair paths through activation patching.

Implementation of four self-supervised learning (SSL) algorithms; SimCLR, MoCo-v2, BYOL, and DINO on the CIFAR-10 dataset using a ResNet-18 backbone. All scripts are designed to run on Google Colab Free Tier (single GPU, ~12 GB RAM) with CIFAR-10.

Abstract PyTorch pipeline that uses a hypernetwork to generate task-specific LoRA adapters for Meta’s Segment Anything Model from natural language prompts, targeted segmentation on COCO instances and benchmarked mIoU via pycocotools. Links You can find the repo here.