natural language processing

Flaxformer: transformer architectures in JAX/Flax

• https://github.com/google/flaxformer

Pathways Language Model (PaLM): Scaling to 540 Billion Parameters for Breakthrough Performance

• https://ai.googleblog.com/.../pathways-language-model...

Part-of-speech Tagging

• (2000) A Statistical Part-of-Speech Tagger
  • TLDR: Seminal paper demonstrating a powerful HMM-based POS tagger. Many tips and tricks for building such classical systems included.
• (2003) Feature-rich part-of-speech tagging with a cyclic dependency network
  • TLDR: Proposes a number of powerful linguistic features for building a (then) SOTA POS-tagging system
• (2015) Bidirectional LSTM-CRF Models for Sequence Tagging
  • TLDR: Proposes an element sequence-tagging model combining neural networks with conditional random fields, achieving SOTA in POS-tagging, NER, and chunking.

https://github.com/ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code

Parsing

• (2003) Accurate unlexicalized parsing :bulb:
  • TLDR: Beautiful paper demonstrating that unlexicalized probabilistic context free grammars can exceed the performance of lexicalized PCFGs.
• (2014) A Fast and Accurate Dependency Parser using Neural Networks
  • TLDR: Very important work ushering in a new wave of neural network-based parsing architectures, achieving SOTA performance as well as blazing parsing speeds.

Named Entity Recognition

• (2005) Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling
  • TLDR: Using cool Monte Carlo methods combined with a conditional random field model, this work achieves a huge error reduction in certain information extraction benchmarks.
• (2015) Bidirectional LSTM-CRF Models for Sequence Tagging
  • TLDR: Proposes an element sequence-tagging model combining neural networks with conditional random fields, achieving SOTA in POS-tagging, NER, and chunking.

Coreference Resolution

• (2010) A multi-pass sieve for coreference resolution :bulb:
  • TLDR: Proposes a sieve-based approach to coreference resolution that for many years (until deep learning approaches) was SOTA.
• (2015) Entity-Centric Coreference Resolution with Model Stacking
  • TLDR: This work offers a nifty approach to building coreference chains iteratively using entity-level features.
• (2016) Improving Coreference Resolution by Learning Entity-Level Distributed Representations
  • TLDR: One of the earliest effective approaches to using neural networks for coreference resolution, significantly outperforming the SOTA.

Sentiment Analysis

• (2012) Baselines and Bigrams: Simple, Good Sentiment and Topic Classification
  • TLDR: Very elegant paper, illustrating that simple Naive Bayes models with bigram features can outperform more sophisticated methods like support vector machines on tasks such as sentiment analysis.
• (2013) Recursive deep models for semantic compositionality over a sentiment treebank :vhs:
  • TLDR: Introduces the Stanford Sentiment Treebank, a wonderful resource for fine-grained sentiment annotation on sentences. Also introduces the Recursive Neural Tensor Network, a neat linguistically-motivated deep learning architecture.

Natural Logic/Inference

• (2007) Natural Logic for Textual Inference
  • TLDR: Proposes a rigorous logic-based approach to the problem of textual inference called natural logic. Very cool mathematically-motivated transforms are used to deduce the relationship between phrases.
• (2008) An Extended Model of Natural Logic
  • TLDR: Extends previous work on natural logic for inference, adding phenomena such as semantic exclusion and implicativity to enhance the premise-hypothesis transform process.
• (2014) Recursive Neural Networks Can Learn Logical Semantics
  • TLDR: Demonstrates that deep learning architectures such as neural tensor networks can effectively be applied to natural language inference.
• (2015) A large annotated corpus for learning natural language inference :vhs:
  • TLDR: Introduces the Stanford Natural Language Inference corpus, a wonderful NLI resource larger by two orders of magnitude over previous datasets.

Machine Translation

• (1993) The Mathematics of Statistical Machine Translation :bulb:
  • TLDR: Introduces the IBM machine translation models, several seminal models in statistical MT.
• (2002) BLEU: A Method for Automatic Evaluation of Machine Translation :vhs:
  • TLDR: Proposes BLEU, the defacto evaluation technique used for machine translation (even today!)
• (2003) Statistical Phrase-Based Translation
  • TLDR: Introduces a phrase-based translation model for MT, doing nice analysis that demonstrates why phrase-based models outperform word-based ones.
• (2014) Sequence to Sequence Learning with Neural Networks :bulb:
  • TLDR: Introduces the sequence-to-sequence neural network architecture. While only applied to MT in this paper, it has since become one of the cornerstone architectures of modern natural language processing.
• (2015) Neural Machine Translation by Jointly Learning to Align and Translate :bulb:
  • TLDR: Extends previous sequence-to-sequence architectures for MT by using the attention mechanism, a powerful tool for allowing a target word to softly search for important signal from the source sentence.
• (2015) Effective approaches to attention-based neural machine translation
  • TLDR: Introduces two new attention mechanisms for MT, using them to achieve SOTA over existing neural MT systems.
• (2016) Neural Machine Translation of Rare Words with Subword Units
  • TLDR: Introduces byte pair encoding, an effective technique for allowing neural MT systems to handle (more) open-vocabulary translation.
• (2016) Pointing the Unknown Words
  • TLDR: Proposes a copy-mechanism for allowing MT systems to more effectively copy words from a source context sequence.
• (2016) Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
  • TLDR: A wonderful case-study demonstrating what a production-capacity machine translation system (in this case that of Google) looks like.

Semantic Parsing

• (2013) Semantic Parsing on Freebase from Question-Answer Pairs :bulb: :vhs:
  • TLDR: Proposes an elegant technique for semantic parsing that learns directly from question-answer pairs, without the need for annotated logical forms, allowing the system to scale up to Freebase.
• (2014) Semantic Parsing via Paraphrasing
  • TLDR: Develops a unique paraphrase model for learning appropriate candidate logical forms from question-answer pairs, improving SOTA on existing Q/A datasets.
• (2015) Building a Semantic Parser Overnight :vhs:
  • TLDR: Neat paper showing that a semantic parser can be built from scratch starting with no training examples!
• (2015) Bringing Machine Learning and Computational Semantics Together
  • TLDR: A nice overview of a computational semantics framework that uses machine learning to effectively learn logical forms for semantic parsing.

Question Answering/Reading Comprehension

• (2016) A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
  • TLDR: A great wake-up call paper, demonstrating that SOTA performance can be achieved on certain reading comprehension datasets using simple systems with carefully chosen features. Don't forget non-deep learning methods!
• (2017) SQuAD: 100,000+ Questions for Machine Comprehension of Text :vhs:
  • TLDR: Introduces the SQUAD dataset, a question-answering corpus that has become one of the defacto benchmarks used today.

Natural Language Generation/Summarization

• (2004) ROUGE: A Package for Automatic Evaluation of Summaries :vhs:
  • TLDR: Introduces ROUGE, an evaluation metric for summarization that is used to this day on a variety of sequence transduction tasks.
• (2015) Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
  • TLDR: Proposes a neural natural language generator that jointly optimises sentence planning and surface realization, outperforming other systems on human eval.
• (2016) Pointing the Unknown Words
  • TLDR: Proposes a copy-mechanism for allowing MT systems to more effectively copy words from a source context sequence.
• (2017) Get To The Point: Summarization with Pointer-Generator Networks
  • TLDR: This work offers an elegant soft copy mechanism, that drastically outperforms the SOTA on abstractive summarization.

Dialogue Systems

• (2011) Data-drive Response Generation in Social Media
  • TLDR: Proposes using phrase-based statistical machine translation methods to the problem of response generation.
• (2015) Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
  • TLDR: Proposes a neural natural language generator that jointly optimises sentence planning and surface realization, outperforming other systems on human eval.
• (2016) How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation :bulb:
  • TLDR: Important work demonstrating that existing automatic metrics used for dialogue woefully do not correlate well with human judgment.
• (2016) A Network-based End-to-End Trainable Task-oriented Dialogue System
  • TLDR: Proposes a neat architecture for decomposing a dialogue system into a number of individually-trained neural network components.
• (2016) A Diversity-Promoting Objective Function for Neural Conversation Models
  • TLDR: Introduces a maximum mutual information objective function for training dialogue systems.
• (2016) The Dialogue State Tracking Challenge Series: A Review
  • TLDR: A nice overview of the dialogue state tracking challenges for dialogue systems.
• (2017) A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue
  • TLDR: Shows that simple sequence-to-sequence architectures with a copy mechanism can perform competitively on existing task-oriented dialogue datasets.
• (2017) Key-Value Retrieval Networks for Task-Oriented Dialogue :vhs:
  • TLDR: Introduces a new multidomain dataset for task-oriented dataset as well as an architecture for softly incorporating information from structured knowledge bases into dialogue systems.
• (2017) Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings :vhs:
  • TLDR: Introduces a new collaborative dialogue dataset, as well as an architecture for representing structured knowledge via knowledge graph embeddings.
• (2017) Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
  • TLDR: Introduces a hybrid dialogue architecture that can be jointly trained via supervised learning as well as reinforcement learning and combines neural network techniques with fine-grained rule-based approaches.

Interactive Learning

• (1971) Procedures as a Representation for Data in a Computer Program for Understanding Natural Language
  • TLDR: One of the seminal papers in computer science, introducing SHRDLU an early system for computers understanding human language commands.
• (2016) Learning language games through interaction
  • TLDR: Introduces a novel setting for interacting with computers to accomplish a task where only natural language can be used to communicate with the system!
• (2017) Naturalizing a programming language via interactive learning
  • TLDR: Very cool work allowing a community of workers to iteratively naturalize a language starting with a core set of commands in an interactive task.

Language Modelling

• (1996) An Empirical Study of Smoothing Techniques for Language Modelling
  • TLDR: Performs an extensive survey of smoothing techniques in traditional language modelling systems.
• (2003) A Neural Probabilistic Language Model :bulb:
  • TLDR: A seminal work in deep learning for NLP, introducing one of the earliest effective models for neural network-based language modelling.
• (2014) One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling :vhs:
  • TLDR: Introduces the Google One Billion Word language modelling benchmark.
• (2015) Character-Aware Neural Language Models
  • TLDR: Proposes a language model using convolutional neural networks that can employ character-level information, performing on-par with word-level LSTM systems.
• (2016) Exploring the Limits of Language Modeling
  • TLDR: Introduces a mega language model system using deep learning that uses a variety of techniques and significantly performs the SOTA on the One Billion Words Benchmark.
• (2018) Deep contextualized word representations :bulb: :vhs:
  • TLDR: This paper introduces ELMO, a super powerful collection of word embeddings learned from the intermediate representations of a deep bidirectional LSTM language model. Achieved SOTA on 6 diverse NLP tasks.
• (2018) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding :bulb:
  • TLDR: One of the most important papers of 2018, introducing BERT a powerful architecture pretrained using language modelling which is then effectively transferred to other domain-specific tasks.
• (2019) XLNet: Generalized Autoregressive Pretraining for Language Understanding :bulb:
  • TLDR: Generalized autoregressive pretraining method that improves upon BERT by maximizing the expected likelihood over all permutations of the factorization order.

Miscellanea

• (1997) Long Short-Term Memory :bulb:
  • TLDR: Introduces the LSTM recurrent unit, a cornerstone of modern neural network-based NLP
• (2000) Maximum Entropy Markov Models for Information Extraction and Segmentation :bulb:
  • TLDR: Introduces Markov Entropy Markov models for information extraction, a commonly used ML technique in classical NLP.
• (2010) From Frequency to Meaning: Vector Space Models of Semantics
  • TLDR: A wonderful survey of existing vector space models for learning semantics in text.
• (2012) An Introduction to Conditional Random Fields
  • TLDR: A nice, in-depth overview of conditional random fields, a commonly-used sequence-labelling model.
• (2014) Glove: Global vectors for word representation :bulb: :vhs:
  • TLDR: Introduces Glove word embeddings, one of the most commonly used pretrained word embedding techniques across all flavors of NLP models
• (2014) Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors
  • TLDR: Important paper demonstrating that context-predicting distributional semantics approaches outperform count-based techniques.
• (2015) Improving Distributional Similarity with Lessons Learned From Word Embeddings :bulb:
  • TLDR: Demonstrates that traditional distributional semantics techniques can be enhanced with certain design choices and hyperparameter optimizations that make their performance rival that of neural network-based embedding methods.
• (2018) Universal Language Model Fine-tuning for Text Classification
  • TLDR: Provides a smorgasbord of nice techniques for finetuning language models that can be effectively transferred to text classification tasks.
• (2019) Analogies Explained: Towards Understanding Word Embeddings
  • TLDR: Very nice work providing a mathematical formalism for understanding some of the paraphrasing properties of modern word embeddings.

Deep learning Paper Reading Meeting Archive

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<br> Paper	NLP
NLP	BERT	Youtube <br> paper	NLP, Laguage representation
NLP	ERNIE	Youtube <br> paper	NLP, Laguage representation
NLP	RoBERTa	Youtube <br> paper	NLP, Laguage representation
NLP	XLNET	Youtube <br> paper	NLP, Laguage representation
NLP	SentenceBert	Youtube
NLP	Defending Against neural fake news	Youtube
NLP	TransformerXL	Youtube <br> blog
NLP	Understanding back translation at scale	Youtube <br> 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
Vision	YOLO	Youtube <br> paper	Object detection
Vision	YOLO-v2	Youtube
Vision	Resnet	Youtube <br> 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 <br> 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
Recommend System	Matrix Factorization Technique for Recommender System	Youtube <br> paper	Recommendation system
Recommend System	Collaborative Filtering for Implicit Feedback Dataset	Youtube
Speech	A comparison of S2S models for speech recognition	Youtube <br> paper	Speech Recognition
Fundamental	RAdam	Youtube <br> blog <br> paper	Regularization
Fundamental	Stacked Auto Encoder for the P300 Component Detection	Youtube
Fundamental	A survey on Image Data Augmentation for DL	Youtube <br>paper	Data augmentation
Fundamental	Training Confidence-calibrated classifiers for detecting out of distribution samples	Youtube
Fundamental	AdamW	Youtube <br> 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