Dongyoon Han

aether. Python

GatedDeltaNet-2. Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

REFINED-BIAS. REFINED-BIAS: a REliable Framework for INtegrated Evaluation and Disentangled Benchmark of Interpretable Alignment of Shape/texture in neural networks Official Code

visual_scratchpad. Python

pptx-design-styles. pptx-design-styles

FastKVzip. Accurate and fast KV cache compression with a gating mechanism

tobo. [NeurIPS 2025] Official PyTorch implementation of "Token Bottleneck: One Token to Remember Dynamics"

trl. Train transformer language models with reinforcement learning.

diffusion-fscil.

seit. [ECCV2024][ICCV2023] Official PyTorch implementation of SeiT++ and SeiT

SyMerge. SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation

hype. [ECCV 2024] Official PyTorch implementation of "HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts"

dtm. Python

rewas. Official PyTorch implementation of ReWaS (AAAI'25) "Read, Watch and Scream! Sound Generation from Text and Video"

negmerge. [ICML 2025] Official PyTorch implementation of "NegMerge: Sign-Consensual Weight Merging for Machine Unlearning"

dawin. [ICLR 2025] Official PyTorch implementation of "DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation"

lut. [ECCV 2024] Official PyTorch implementation of LUT "Learning with Unmasked Tokens Drives Stronger Vision Learners"

StyleKeeper. Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance"

yet-another-mujoco-tutorial-v3. Jupyter Notebook

demystifying-ntk. Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training? (CVPR 2022)

rdnet. [ECCV2024] Official implementation of paper, "DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs".

model-stock. Model Stock: All we need is just a few fine-tuned models

rope-vit. [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

dual-teacher. Official code for the NeurIPS 2023 paper "Switching Temporary Teachers for Semi-Supervised Semantic Segmentation"

dap-cl. Official code of "Generating Instance-level Prompts for Rehearsal-free Continual Learning (ICCV 2023)"

imagenet-12k. ImageNet-12k subset of ImageNet-21k (fall11)

ChatGPT-AutoExpert. 🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).

open_clip. An open source implementation of CLIP.

augsub. [CVPR 2025] Official PyTorch implementation of MaskSub "Masking meets Supervision: A Strong Learning Alliance"

serge. A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

NeglectedFreeLunch. Jupyter Notebook

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

imagenet-annotation-tool. TypeScript

NeglectedFreeLunch.

temporal-selfsupervision. Python

PfLayer. Learning Features with Parameter-Free Layers, ICLR 2022

rexnet. Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models

i-Blurry. Official Pytorch implementation of Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR 2022)

cgl_fairness. Python

FSMR. Official Tensorflow implementation of "Feature Statistics Mixing Regularization for Generative Adversarial Networks" (CVPR 2022)

puridiver. Official PyTorch Implementation of PuriDivER CVPR 2022.

eccv-caption. Extended COCO Validation (ECCV) Caption dataset (ECCV 2022)

pcme. Official Pytorch implementation of "Probabilistic Cross-Modal Embedding" (CVPR 2021)

hypermix. Code for text augmentation method leveraging large-scale language models

StyleMapGAN. Official pytorch implementation of StyleMapGAN (CVPR 2021)

c3-gan. Official Pytorch implementation of C3-GAN (Spotlight at ICLR 2022)

AdamP. AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights

ViLT. Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ViLT. Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

calm. Python

pit. Python

vidt. Python

lookwhostalking. Look Who’s Talking: Active Speaker Detection in the Wild

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

relabel_imagenet. Python

ssdlite-pytorch-mobilenext. A PyTorch implementation of SSDLite on COCO

ImageClassification-CoreML. The example of running Image Classification using Core ML

ext_portrait_segmentation. Python

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

wsolevaluation. Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020)

embedding-expansion. Official MXNet implementation of "Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning" (CVPR 2020)

symmetrical-synthesis. Official Tensorflow implementation of "Symmetrical Synthesis for Deep Metric Learning" (AAAI 2020)

overhaul-distillation. Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019)

dmfont. Official PyTorch implementation of DM-Font (ECCV 2020)

ResNeSt. ResNeSt: Split-Attention Networks

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

frostnet. FrostNet: Towards Quantization-Aware Network Architecture Search

stargan-v2-tensorflow. StarGAN v2 - Official Tensorflow Implementation (CVPR 2020)

stargan-v2. StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

rebias. Official Pytorch implementation of ReBias (Learning De-biased Representations with Biased Representations), ICML 2020

Active-Shift-TF. Tensorflow implementation for Active Shift Layer(ASL)

Active-Shift. Caffe implementation for Active Shift Layer(ASL)

ssd_detectors. SSD-based object and text detection with Keras, SSD, DSOD, TextBoxes, SegLink, TextBoxes++, CRNN

tensorflow-style-transfer. A simple, concise tensorflow implementation of style transfer (neural style)

tensorflow-mnist-VAE. Tensorflow implementation of variational auto-encoder for MNIST

tensorflow-generative-model-collections. Collection of generative models in Tensorflow

awesome-deep-text-detection-recognition. A curated list of resources for text detection/recognition (optical character recognition ) with deep learning methods.

CRAFT-pytorch. Official implementation of Character Region Awareness for Text Detection (CRAFT)

CutMix-PyTorch. Official Pytorch implementation of CutMix regularizer

Tensorflow-Cookbook. Simple Tensorflow Cookbook for easy-to-use

deform_conv_pytorch. PyTorch Implementation of Deformable Convolution

pytorch_shake_shake. A PyTorch implementation of shake-shake

soccerontable. Upconverting YouTube soccer videos in 3D for viewing in AR/VR devices.Soccer On Your Tabletop

ELDNet. Source code for our journal submission : ELD-Net: An efficient deep learning architecture for accurate saliency detection

wtte-rnn. WTTE-RNN a framework for churn and time to event prediction

cudnn.torch. Torch-7 FFI bindings for NVIDIA CuDNN

Stochastic_Depth. Deep Networks with Stochastic Depth

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

py-faster-rcnn. Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

PyramidNet-caffe. Caffe implementation of the paper "Deep Pyramidal Residual Networks" (https://arxiv.org/abs/1610.02915).

densenet-pytorch. A PyTorch Implementation for Densely Connected Convolutional Networks (DenseNets)

fb.resnet.torch. Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

R-FCN. R-FCN: Object Detection via Region-based Fully Convolutional Networks

Deformable-ConvNets. Deformable Convolutional Networks

ICMR2017. Code for paper "Musical Instrument Recognition in User-generated Videos using a Multimodal Convolutional Neural Network Architecture" by Olga Slizovskaia, Emilia Gomez, Gloria Haro. ICMR 2017

vision. Datasets, Transforms and Models specific to Computer Vision

PyramidNet. Torch implementation of the paper "Deep Pyramidal Residual Networks" (https://arxiv.org/abs/1610.02915).