[NeurIPS'26] Differentiable Bit-Widths: Co-Optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression

[EMNLP2026] Official source code for Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing

[EMNLP2026] Official source code for 'Layer-wise Curriculum Learning for Efficient LLM Compression'.

[EMNLP2026] Official source code for Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing

[WACV'25] Enriching Local Patterns with Multi-Token Attention for Broad-Sight Neural Networks

[CVPR'25] Do Your Best and Get Enough Rest for Continual Learning

[CMPB'24] Attentional Decoder Networks for Chest X-ray Image Recognition on High-resolution Features

OSX 의 NFD 사용으로 인한 한글 자소분리 버그를 해결합니다.

CVPR2024: Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

LAVIS - A One-stop Library for Language-Vision Intelligence

A simple library for implementing common design patterns.

A collection of design patterns/idioms in Python

CoreNet: A library for training deep neural networks

SVG icons for popular brands

A list of awesome resources for tmux

[NeurIPS 2023] A faithful benchmark for vision-language compositionality

2021 Ajou University Spring SW capstone design - FindU NLP (Winning the gold prize 2021 College Student Paper Contest of DCS)

An open source implementation of CLIP.

Collection of AWESOME vision-language models for vision tasks

Code for the paper https://arxiv.org/abs/2003.00827

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

PyTorch implementation of Hinton's FF Algorithm with hard negatives sampling

PyTorch implementation of some attentions for Deep Learning Researchers.

Acceptance rates for the major AI conferences

Example of one shot learning and few shot learning with omniglot dataset.

PyTorch extensions for fast R&D prototyping and Kaggle farming

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and rela…

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

BMVC2021 - Grouping Bilinear Pooling