[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"

An implementation of the efficient attention module.

TalkToModel gives anyone with the powers of XAI through natural language conversations 💬!

Code for the paper "Thermodynamics-informed graph neural networks" published in IEEE Transactions on Artificial Intelligence (TAI).

Deep learning research implemented on notebooks using PyTorch.

Single-file pytorch implementation of hybrid-SAC

Official implementation of the SIGGRAPH-2022 paper "DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes"

PyTorch version for the "Dual-Dtream Shallow Networks for Facial Micro-Expression Recognition"

[ACM MM22] Mimicking the Annotation Process for Recognizing the Micro Expressions

An open source implementation of the paper: "Sequential Diagnosis with Language Models" From Microsoft Built with Swarms Framework

Original Pytorch Implementation of FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation

Brain EEG signal data augmentation using synthetic signals generated by a single step diffusion probabilistic model.

Code for the paper "Structure-preserving neural networks" published in Journal of Computational Physics (JCP).

Python implementation of Efficient Graph-Based Image Segmentation.

Code for the paper "Deep learning of thermodynamics-aware reduced-order models from data" published in Computer Methods in Applied Mechanics and Engineering (CMAME).

A paper implementation and tutorial from scratch combining various great resources for implementing Transformers discussesd in Attention in All You Need Paper for the task of German to English Translation.

A minimal PyTorch implementation of Flow Matching for Generative Modeling.

Unsupervised specificity-guided optimization of Image Captioning models to encourage meaningful diversity in the generated captions. Code for the paper Generating Diverse and Meaningful Captions: Unsupervised Specificity Optimization for Image Captioning (Lindh et al., 2018).

Scale-recurrent Network for Deep Image Deblurring with neural networks

PyTorch implementation of DINO (Self-Distillation with No Labels) from scratch.