BK Lee

MoAI. [ECCV 2024] Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks.

DeepSick-R1. Reproduction of DeepSeek-R1

Full-Segment-Anything. This is Pytorch Implementation Code for adding new features in code of Segment-Anything. Here, the features support batch-input on the full-grid prompt (automatic mask generation) with post-processing: removing duplicated or small regions and holes, under flexible input image size

Meteor. [NeurIPS 2024] Official PyTorch implementation code for realizing the technical part of Mamba-based traversal of rationale (Meteor) to improve performance of numerous vision language performances for diverse capabilities.

CoLLaVO. [ACL 2024 Findings] Official PyTorch Implementation code for realizing the technical part of CoLLaVO: Crayon Large Language and Vision mOdel to significantly improve zero-shot vision language performances

TroL. [EMNLP 2024] Official PyTorch implementation code for realizing the technical part of Traversal of Layers (TroL) presenting new propagation operation to get super vision language performances.

Phantom. [Technical Report] Official PyTorch implementation code for realizing the technical part of Phantom of Latent representing equipped with enlarged hidden dimension to build super frontier vision language models.

Adversarial-Information-Bottleneck. [NeurIPS 2021] Official PyTorch Implementation for "Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck"

Causal-Adversarial-Instruments. [CVPR 2023] Official PyTorch Implementation for "Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression"

Super-Fast-Adversarial-Training. Official PyTorch Implementation Code for Developing Super Fast Adversarial Training with Distributed Data Parallel, Channel Last Memory Format, Mixed Precision Training + Adversarial Attack, Faster Adversarial Training, and Fast Forward Computer Vision (FFCV).

Masking-Adversarial-Damage. [CVPR 2022] Official PyTorch Implementation for "Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network"

Double-Debiased-Adversary. [ICCV 2023] Official PyTorch Implementation for "Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning"

Adavanced-ECMS. Advanced Energy Control Management System (Advanced-ECMS) for Electrical Vehicle System using proposed Plus Version of Alternating Direction Method of Multipliers (ADMM+) on Robotics Operating System (ROS)

Robust-TopView. Robustly Converting Camera View from Normal View to Top View for Autonomous Vehicle System on Robotics Operating System (ROS)

Hierarchical-Bayesian-Defense. [OpenReview] Official PyTorch Implementation for "Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference"

Distill-R1. Open-source RL Framework with Online Teacher-Student Distillation

YOLO-Dyanmic-ROS. Modification to YOLO for improving Dynamic Real-Time Processing on Robotics Operating Systems for Autonomous Vehicle System

Causal-Unsupervised-Segmentation. [Pattern Recognition] Official PyTorch Implementation code for realizing the technical part of Causal Unsupervised Semantic sEgmentation (CAUSE) to improve performance of unsupervised semantic segmentation.

ByungKwanLee.

ZPPO-page. CSS

AXPO-page. CSS

ByungKwanLee-CV. TeX