deep-learning

The official implementation of "EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa"

InsightSolver: Colab notebooks for exploring and solving operational issues using deep learning, machine learning, and related models.

UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer

[EMNLP'21] Visual News: Benchmark and Challenges in News Image Captioning

A Transformer made of Rotation-equivariant Attention using Vector Neurons

Deepstory turns a text/generated text into a video where the character is animated to speak your story using his/her voice.

Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022

Utility for Safetensors Files

Implementation of Logistic Regression, MLP, CNN, RNN & LSTM from scratch in python. Training of deep learning models for image classification, object detection, and sequence processing (including transformers implementation) in TensorFlow.

This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalization ability, and other properties of language models through theoretical analysis, empirical analysis, or a combination of both.

[CVPR 2024] Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities

Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI

Implementation of AlphaGenome, Deepmind's updated genomic attention model

PyTorch library for Active Fine-Tuning

This repository is used to collect papers and code in the field of AI.

Implementation of Zorro, Masked Multimodal Transformer, in Pytorch

A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks. 43 runnable notebooks, one continuous case study. MIT licensed, no signup. By Zorost Intelligence AI Lab.

Efficient Attention for Long Sequence Processing

Fine-tuning of diffusion models