deep-learning

A comprehensive hands-on guide to building production-grade distributed applications with Ray - from distributed training and multimodal data processing to inference and reinforcement learning.

Website for the Natural Language Processing with Transformers book

Fine-tuning an LLM using a Generic Workflow and Best Practices with PyTorch

Think.ai hackathon winner project : Moroccan interior design generator

Learning PyTorch through the D2L book. A series of notebooks for the same

多模态情绪识别方法研究（Multimodal Emotion Recognition）

WeldFusionNet: Multimodal deep learning for automated weld defect classification using sensor, audio, and video data (F1: 0.9567)

Advanced NLP Workshop: word-sense disambiguation with RoBERTa and text summarization with BART (Machine Learning Milan)

Repository for the paper 'Enhancing Clinical Decision Support with Physiological Waveforms — A Multimodal Benchmark in Emergency Care'.

Implementation of Bitune: Bidirectional Instruction-Tuning

VAAS is an inference-first, research-driven library for image integrity analysis. It integrates Vision Transformer Attention Mechanisms with patch-level self-consistency analysis to enable fine-grained localization and detection of visual inconsistencies across diverse image analysis tasks.

Generate README.md with GPT-3 few-shot learning

分享高质量的AI项目

Transformer-based online speech recognition system with TensorFlow 2

Code for paper "Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation (ECCV 2024)"

Official Repository for the paper 'MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification' @ EMNLP 2024

Easy to use Multi-Provider ASR/Speech To Text and NLP engine

Building an Image-to-Video (I2V) Model from Scratch

AESTETIK: Convolutional autoencoder for learning spot representations from spatial transcriptomics and morphology data

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simulation, Godzilla KVarN/TriAttention with SM86/SM89 qualification, CUDA weight sharing, and multi-GPU planning.