deep-learning

The notebook explains the various steps to obtain the results of publication: "Is Space-Time Attention All You Need for Video Understanding?"

Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.

[NeurIPS-2024] The offical Implementation of "Instruction-Guided Visual Masking"

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

Implementation dino v2 for remote sensing with huggingface transformers

Turn text into video using Stable Diffusion and Google FILM

[WACV 2025] Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge

Papers of ASR, Tools of ASR

A pipeline for Prompt-tuning

Official resource of the paper "Knowledge Enhanced Masked Language Model for Stance Detection", NAACL 2021

A simple and intuitive library for diffusion models using Flax and Jax. Includes detailed notebooks on DDPM, DDIM, and EDM with simplified mathematical explanations. Made as part of my journey for learning and experimenting with generative AI.

Implementation of the "Learn No to Say Yes Better" paper.

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

[IEEE TGRS 2025] Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices

NSFW Prompt Detection for Stable Diffusion

This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"

Multimodal foundation model predicting transcriptome-wide virtual spatial transcriptomics from histology.

Train YOLO + VLM with one command. Auto-generate vision-language training data from YOLO labels - no extra labeling needed.

Predict the Body Mass Index with one image of a human face, with state-of-the-art results.

The code to finetune SAM with bounding box prompt for segmentation of the lungs on CT