Contrastive-LSH Embedding and Tokenization Technique for Multivariate Time Series Classification

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

Pytorch implementation of the models RT-1-X and RT-2-X from the paper: "Open X-Embodiment: Robotic Learning Datasets and RT-X Models"

Tensorflow implementation of a 3D-CNN U-net with Grid Attention and DSV for pancreas segmentation trained on CT-82.

A TensorFlow implementation of the Transformer model for machine translation tasks. This package includes data loading, model definition, and training scripts for translating Portuguese to English using the TED Talks dataset. The repository provides a complete pipeline from preprocessing the data to training and testing the model.

[CVPR 2024] "CFAT: Unleashing Triangular Windows for Image Super-resolution"

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

Implementation of the model "AudioFlamingo" from the paper: "Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities"

Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta

Hyperspectral Unmixing via Dual Attention Convolutional Neural Networks | 基于双注意力卷积神经网络的高光谱图像解混

Abstractive Text summarization using deep learning.

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)

Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, x86, x64, ARM), multimodal model for text and images and so on.

ABAW6 (CVPR-W) We achieved second place in the valence arousal challenge of ABAW6

This repository contains notes, slides, labs, assignments and projects for the Deep Learning Specialization by DeepLearning.AI and Coursera.

[FG 2024] "Audio-Visual Person Verification based on Recursive Fusion of Joint Cross-Attention"

Specifically built for the research proposal: Estimating sector attention index with deep learning methods : example of Chinese stock market, Jan. 4, 2024.

code for paper on person Re-ID

Successfully established a Seq2Seq with attention model which can perform English to Spanish language translation up to an accuracy of almost 97%.