This page is an archive of the Deep Learning Paper Reading Meeting. you would like to attend the meeting or have any questions, Write in the GitHub issue table or email us at 'tfkeras@kakao.com'
This page is an archive of the Deep Learning Paper Reading Meeting. If you would like to attend the meeting or have any questions, Write in the GitHub issue table or email us at 'tfkeras@kakao.com'
| Tasks | Paper | Link | Performance Index |
|---|---|---|---|
| NLP | Attention is all you need | Youtube Paper |
NLP |
| NLP | BERT | Youtube paper |
NLP, Laguage representation |
| NLP | ERNIE | Youtube paper |
NLP, Laguage representation |
| NLP | RoBERTa | Youtube paper |
NLP, Laguage representation |
| NLP | XLNET | Youtube paper |
NLP, Laguage representation |
| NLP | SentenceBert | Youtube | |
| NLP | Defending Against neural fake news | Youtube | |
| NLP | TransformerXL | Youtube blog |
|
| NLP | Understanding back translation at scale | Youtube blog |
|
| NLP | Deep Contextualized Word Representations | Youtube | |
| NLP | Univiersal LM Fine-tuning for text classification | Youtube | |
| NLP | Subword-level Word Vector Representations for Korean | Youtube | |
| NLP | A Decomposable Attention Model for Natural Language Inference | Youtube | |
| NLP | Reformer | Youtube | |
| NLP | Neural Machine Translation by Jointly Learning to Align and Translate | Youtube | |
| NLP | ELECTRA | Youtube | |
| NLP | SBERT_WK | Youtube | |
| NLP | Revealing the Dark Secrets of BERT | Youtube | |
| NLP | PEGASUS | Youtube | |
| NLP | Document-level Neural Machine Translation with Inter-Sentence Attention | Youtube | |
| NLP | Phrase-Based & Neural Unsupervised Machine | Youtube | |
| NLP | BART | Youtube | |
| NLP | BAE | Youtube | |
| NLP | A Generative Model for Joint Natural Language Understanding and Generation | Youtube | |
| NLP | Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training | Youtube | |
| NLP | Graph Attention Networks | Youtube | |
| NLP | Switch Transformers | Youtube | |
| NLP | DeText: A Deep Text Ranking Framework with BERT | Youtube | |
| NLP | Face book Chat bot , Blender bot | Youtube | |
| NLP | Extracting Training Data from Large Language Models | Youtube | |
| NLP | Longformer: The Long-Document Transformer | Youtube | |
| NLP | Visualizing and Measuring the Geometry of BERT | Youtube | |
| NLP | Encode, Tag, Realize HighPrecision Text Editing | Youtube | |
| NLP | multimodal transformer for unaligned multimodal language sequences | Youtube | |
| NLP | SCGPT : Few-shot Natural Language Generation for Task-Oriented Dialog | Youtube | |
| NLP | ColBERT: Efficient and Effective Passage Search viaContextualized Late Interaction over BERT | Youtube | |
| NLP | Restoring and Mining the Records ofthe Joseon Dynasty via Neural LanguageModeling and Machine Translation | Youtube | |
| NLP | Improving Factual Completeness and Consistency of Image to Text Radiology Report Generation | Youtube | |
| NLP | FinBERT | Youtube | |
| NLP | LayoutLM: Pre-training of Text and Layout for Document Image Understanding | Youtube | |
| NLP | Query Suggestions as Summarization inExploratory Search | Youtube | |
| NLP | H-Transformer-1D Paper : Fast One Dimensional Hierarchical Attention For Sequences | Youtube | |
| NLP | End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization | Youtube | |
| NLP | DISEASES : Text mining and data integration of disease–gene associations | Youtube | |
| NLP | RoFormer: Enhanced Transformer with Rotary Position Embedding | Youtube | |
| NLP | A Multiscale Visualization of Attention in the Transformer Model | Youtube | |
| NLP | CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees | Youtube | |
| NLP | MERL:Multimodal Event Representation Learning in Heterogeneous Embedding Spaces | Youtube | |
| NLP | Big Bird - Transformers for Longer Sequences | Youtube | |
| NLP | Decoding-Enhanced BERT with Disentangled Attention | Youtube | |
| NLP | SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis | Youtube | |
| NLP | IMPROVING BERT FINE-TUNING VIA SELF-ENSEMBLE AND SELF-DISTILL ATION | Youtube | |
| NLP | ACHIEVING HUMAN PARITY ON VISUAL QUESTION ANSWERING | Youtube | |
| NLP | Deep Encoder, Shallow Decoder: Reevaluating non- autoregressive machine translation | Youtube | |
| NLP | LaMDA : Language Models for Dialog Applications | Youtube | |
| NLP | Competition-Level Code Generation with AlphaCode | Youtube | |
| NLP | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | Youtube | |
| NLP | SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization | Youtube | |
| NLP | Graph-Bert: Only Attention is Needed for Learning Graph Representations | Youtube | |
| NLP | SimCSE:Simple Contrastive Learning of Sentence Embedding | Youtube | |
| NLP | Typical decoding for Natural Language | Youtube | |
| NLP | Perceiver IO : A GENERAL ARCHITECTURE FOR STRUCTURED INPUTS & OUTPUTS | Youtube | |
| NLP | Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference | Youtube | |
| NLP | Learning to Generalize to More:Continuous Semantic Augmentation for Neural Machine Translation | Youtube | |
| NLP | Multitask Prompted Training Enables Zero-Shot Task | Youtube | |
| NLP | Efficient Passage Retrieval with Hashing for Open-domain Question Answering(BPR) | Youtube | |
| NLP | LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS | Youtube | |
| NLP | Weakly-supervised Text Classification Based on Keyword Graph | Youtube | |
| NLP | Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation | Youtube | |
| NLP | AEDA: An Easier Data Augmentation Technique for Text Classification | Youtube | |
| NLP | GTRANS-Grouping and Fusing Transformer Layers for Neural Machine Translation | Youtube | |
| NLP | SPLADE : Sparse Lexical and Expansion Model for First Stage Ranking | Youtube | |
| NLP | Debiased Contrastive learning of Unsupervised Sentence Representation | Youtube | |
| NLP | Calibrating Sequence Likelihood Improves Conditional Language Generation | Youtube | |
| NLP | CHAIN-OF-THOUGHT PROMPTING ELICITS REASONING IN LARGE LANGUAGE MODELS | Youtube | |
| Vision | YOLO | Youtube paper |
Object detection |
| Vision | YOLO-v2 | Youtube | |
| Vision | Resnet | Youtube paper |
Image classification |
| Vision | GAN | Youtube | |
| Vision | Image Style Transfer Using CNN | Youtube | |
| Vision | SINGAN | Youtube | |
| Vision | FCN | Youtube | |
| Vision | DeepLabV3 | Youtube | |
| Vision | Unet | Youtube paper |
|
| Vision | CyCADA | Youtube | |
| Vision | D-SNE | Youtube | |
| Vision | Faster-RCNN | Youtube | |
| Vision | Weakly Supervised Object DetectionWith Segmentation Collaboration | Youtube | |
| Vision | Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias | Youtube | |
| Vision | data efficient image recognition with contrastive predictive coding | Youtube | |
| Vision | Deep Feature Consistent Variational Autoencoder | Youtube | |
| Vision | Attention Branch Network: Learning of Attention Mechanism for Visual Explanation | Youtube | |
| Vision | RELATION-SHAPE CONVOLUTIONAL NEURAL NETWORK FOR POINT CLOUD ANALYSIS | Youtube | |
| Vision | EfficientNet | Youtube | |
| Vision | Deep Clustering for Unsupervised Learning of Visual Features | Youtube | |
| Vision | Boosting Few-shot visual learning with self-supervision | Youtube | |
| Vision | Rethinking Pre-training and Self-training | Youtube | |
| Vision | BYOL : Bootstrap Your Own Latent | Youtube | |
| Vision | Deep Image Prior | Youtube | |
| Vision | Object-Centric Learning with Slot Attention | Youtube | |
| Vision | Yolo V4 | Youtube | |
| Vision | Dynamic Routing Between Capsules | Youtube | |
| Vision | Semi-Supervised Classification with Graph Convolutional Network | Youtube | |
| Vision | Generative Pretraining from Pixels | Youtube | |
| Vision | MaskFlownet | Youtube | |
| Vision | Adversarial Robustness through Local Linearization | Youtube | |
| Vision | Locating Objects Without Bounding Boxes | Youtube | |
| Vision | Training data-efficient image transformers & distillation through attention | Youtube | |
| Vision | What Makes Training Multi-modalClassification Networks Hard? | Youtube | |
| Vision | 2020 CVPR Meta-Transfer Learning for Zero-Shot Super-Resolution | Youtube | |
| Vision | 2020 ACCV Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation | Youtube | |
| Vision | Style GAN | Youtube | |
| Vision | HighPerformance Large Scale ImageRecognition Without Normalization | Youtube | |
| Vision | Focal Loss for Dense Object Detection | Youtube | |
| Vision | Editing in Style : Uncovering the Local Semantics of GANs | Youtube | |
| Vision | Efficient Net 2 | Youtube | |
| Vision | Style Clip | Youtube | |
| Vision | Swin Transformer | Youtube | |
| Vision | NBDT : Neural-backed Decision Tree | Youtube | |
| Vision | [2020 CVPR] Efficient DET | Youtube | |
| Vision | MLP - MIXER : An all-MLP Architecture for Vision | Youtube | |
| Vision | You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection | Youtube | |
| Vision | Video Prediction ! Hierarchical Long-term Video Frame Prediction without Supervision | Youtube | |
| Vision | Closed-Form Factorization of Latent Semantics in GANs | Youtube | |
| Vision | YOLOR : You Only Learn One Representation: Unified Network for Multiple Tasks | Youtube | |
| Vision | StyleSpace Analysis | Youtube | |
| Vision | Representative graph neural network | Youtube | |
| Vision | YOLOX | Youtube | |
| Vision | Joint Contrastive Learning with Infinite Possibilities | Youtube | |
| Vision | Auto Deep Lab - Hierarchical Neural Architecture Search for Semantic Image Segmentation | Youtube | |
| Vision | Explaining in style training a gan to explain a classifier in stylespace | Youtube | |
| Vision | End-to-End Semi-Supervised Object Detection with Soft Teacher | Youtube | |
| Vision | Understanding Dimensional Collapse in Contrastive Self Supervised Learning | Youtube | |
| Vision | Encoding in Style: a Style Encoder for Image-to-Image Translation | Youtube | |
| Vision | Detection in Crowded Scenes: One Proposal, Multiple Predictions | Youtube | |
| Vision | A Normalized Gaussian Wasserstein Distance for Tiny Object Detection | Youtube | |
| Vision | Siamese Neural network for one-shot image recognition | Youtube | |
| Vision | Grounded Language-Image Pre-training | Youtube | |
| Vision | Transfer Learning for Pose Estimation of Illustrated Characters | Youtube | |
| Vision | Sparse - RCNN paper explained | Youtube | |
| Vision | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | Youtube | |
| Vision | HRnet: Deep High-Resolution Representation Learning for Human Pose Estimation | Youtube | |
| Vision | MobileViT : Light-weight, general-purpose, and Mobile-friendly Vision Transformer | Youtube | |
| Vision | Effectively Leveraging Attributes for Visual Similarity | Youtube | |
| Vision | Hard Negative Mixing for Contrastive learning | Youtube | |
| Vision | HOTR : Human-Object Interaction Detection with Transformer | Youtube | |
| Vision | SSD: A UNIFIED FRAMEWORK FOR SELF-SUPERVISED OUTLIER DETECTION | Youtube | |
| Vision | StyleHEAT : One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN | Youtube | |
| Vision | Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut | Youtube | |
| Vision | Transfusion: Understanding Transfer Learning for Medical Imaging | Youtube | |
| Vision | UCTransNet | Youtube | |
| Vision | A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation | Youtube | |
| Vision | Vision Transformer with Deformable Attention | Youtube | |
| Vision | More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity | Youtube | |
| Vision | PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection | Youtube | |
| Vision | MetaFormer is Actually What You Need for Vision | Youtube | |
| Vision | An Image is Worth 16x16 Words:Transformers for Image Recognition at Scale | Youtube | |
| Vision | BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations | Youtube | |
| Vision | High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion) | Youtube | |
| Vision | Proper Reuse of Image Classification Features Improves Object Detection | Youtube | |
| Vision | Voxel Field Fusion for 3D Object Detection | Youtube | |
| Recommend System | Matrix Factorization Technique for Recommender System | Youtube paper |
Recommendation system |
| Recommend System | Collaborative Filtering for Implicit Feedback Dataset | Youtube | |
| Speech | A comparison of S2S models for speech recognition | Youtube paper |
Speech Recognition |
| Fundamental | RAdam | Youtube blog paper |
Regularization |
| Fundamental | Stacked Auto Encoder for the P300 Component Detection | Youtube | |
| Fundamental | A survey on Image Data Augmentation for DL | Youtube paper |
Data augmentation |
| Fundamental | Training Confidence-calibrated classifiers for detecting out of distribution samples | Youtube | |
| Fundamental | AdamW | Youtube blog |
|
| Fundamental | Stargan | Youtube | |
| Fundamental | Drop-out | Youtube | |
| Fundamental | BLEU - a Method for Automatic Evaluation of Machine Translation | Youtube | |
| Fundamental | t-SNE | Youtube | |
| Fundamental | Gpipe | Youtube | |
| Fundamental | explainable ai | Youtube | |
| Fundamental | TAPAS | Youtube | |
| Fundamental | Learning both Weights and Connections for Efficient Neural Networks | Youtube | |
| Fundamental | ReVACNN | Youtube | |
| Fundamental | THE LOTTERY TICKET HYPOTHESIS: FINDING SPARSE, TRAINABLE NEURAL NETWORKS | Youtube | |
| Fundamental | ALPHAGO : Mastering the game of Go with Deep Neural Networks and Tree Search | Youtube | |
| Fundamental | A_BASELINE_FOR_FEW_SHOT_IMAGE_CLASSIFICATION | Youtube | |
| Fundamental | Sharp Minima Can Generalize For Deep Nets | Youtube | |
| Fundamental | Pediatric Sleep Stage Classification Using Multi-Domain Hybrid Neural Networks | Youtube | |
| Fundamental | Pruning from Scratch | Youtube | |
| Fundamental | Do We Need Zero Training Loss After Achieving Zero Training Error? | Youtube | |
| Fundamental | Deep Recurrent Q-Learning for Partially Observable MDPs | Youtube | |
| Fundamental | Large Margin Deep Networks for Classification | Youtube | |
| Fundamental | generating wikipedia by summarizing long sequences | Youtube | |
| Fundamental | Plug and Play Language Models: A Simple Approach to Controlled Text Generation | Youtube | |
| Fundamental | What Uncertainties Do We Need in Bayesian DeepLearning for Computer Vision? | Youtube | |
| Fundamental | KRED | Youtube | |
| Fundamental | Early Stopping as nonparametric Variational | Youtube | |
| Fundamental | Sharpness Aware Minimization for efficeintly improving generalization | Youtube | |
| Fundamental | Neural Graph Collaborative Filtering | Youtube | |
| Fundamental | Restricting the Flow: Information Bottlenecks for Attribution | Youtube | |
| Fundamental | Real world Anomaly Detection in Surveillance Videos | Youtube | |
| Fundamental | Deep learning model to 2Bit Quantization?! BRECQ Paper review (2021 ICLR) | Youtube | |
| Fundamental | Deep sets (2017 NIPS) | Youtube | |
| Fundamental | StyleGAN2 | Youtube | |
| Fundamental | SOTA - Beyond Synthetic Noise:Deep Learning on Controlled Noisy Labels | Youtube | |
| Fundamental | Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems | Youtube | |
| Fundamental | Longformer: The Long-Document Transformer | Youtube | |
| Fundamental | soft actor critic | Youtube | |
| Fundamental | Loss Function Discovery for Object Detection Via Convergence- Simulation Driven Search | Youtube | |
| Fundamental | [2021 ICLR] The Deep Bootstrap Framework:Good Online Learners are good Offline Generalizers | Youtube | |
| Fundamental | Meta HIN | Youtube | |
| Fundamental | When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations | Youtube | |
| Fundamental | Self similarity Student for Partial Label Histopathology Image Segmentation | Youtube | |
| Fundamental | ANALYSING MATHEMATICAL REASONING ABILITIES OF NEURAL MODELS | Youtube | |
| Fundamental | Self-training Improves Pre-training for Natural Language Understanding | Youtube | |
| Fundamental | Preference Amplification in Recommender Systems | Youtube | |
| Fundamental | Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation | Youtube | |
| Fundamental | Evaluating Classifiers by Mean of Test Data with Noisy Labels | Youtube | |
| Fundamental | Progressive Identification of True Labels for Partial-Label Learning | Youtube | |
| Fundamental | Fine-grained Interest Matching For Neural News Recommendation | Youtube | |
| Fundamental | Adversarial Reinforced Learning for Unsupervised Domain Adaptation | Youtube | |
| Fundamental | Neural Tangent Kernel - Convergence and Generalization in neural Network | Youtube | |
| Fundamental | Intriguing Properties of Contrastive Losses | Youtube | |
| Fundamental | Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets | Youtube | |
| Fundamental | Transformer Interpretability Beyond Attention Visualization | Youtube | |
| Fundamental | How does unlabeled data improve generalization in self-training? | Youtube | |
| Fundamental | Rainbow: Combining Improvements in Deep Reinforcement Learning | Youtube | |
| Fundamental | Once-for-All: Train One Network and Specialize it for Efficient Deployment | Youtube | |
| Fundamental | Effective Diversity in Population Based Reinforce Learning | Youtube | |
| Fundamental | Fine-Tuning can Distort Pretrained Features and Under perform Out-of-Distribution | Youtube | |
| Fundamental | GCN-LRP explanationexploring latent attention of graph convolutional networks | Youtube | |
| Fundamental | Towards Safe Online Reinforced Learning in Computer Systems | Youtube | |
| Fundamental | Conflict-Averse Gradient Descent for Multi-task Learning | Youtube | |
| Fundamental | Explainability Methods for Graph Convolutional Neural Networks | Youtube | |
| Fundamental | Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning | Youtube | |
| Fundamental | Efficiently Identifying Task Grouping for Multi-Task Learning | Youtube | |
| Fundamental | DeepFM: A Factorization-Machine based Neural Network for CTR Prediction | Youtube | |
| Fundamental | Task Adaptive Parameter Sharing for Multi-Task Learning | Youtube |