transformers

Pytorch library for end-to-end transformer models training, inference and serving

A deep learning library based on Pytorch focussed on low resource language research and robustness

Code for Video Deepfake Detector from "MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection", paper available on IEEE Transactions on Information Forensics and Security.

Frame Semantic Parser based on T5 and FrameNet

Research experiments exploring uncommon quant techniques.

Exploring Japanese SimCSE

Vision Transformers for image classification, image segmentation, and object detection.

mindspore implementation of transformers

Library - Vanilla, ViT, DeiT, BERT, GPT

Open Source Generative AI Models for Automatic Rhythm Game Beatmap Generation (for acoustic people)

Unofficial implementation of GotenNet, new SOTA 3d equivariant transformer, in Pytorch

Implementation of deep implicit attention in PyTorch

[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.

Pytorch implementation of image captioning using transformer-based model.

Applying BERT for named entity recognition on resumes.

A geometric deep learning framework (Geometric Transformers) for predicting protein interface contacts. (ICLR 2022)

Unified Learned Sparse Retrieval Framework

Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.

Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22

Korean MRC (KorQuAD) with KoBERT