- Top-tier list from google scholar
- Artificial Intelligence : ICLR, NeurIPS, ICML, AAAI
- Computational Linguistics : ACL, EMNLP, NAACL
- Computer Vision & Pattern Recognition : CVPR, ICCV, ECCV
- Signal Processing : ICASSP, INTERSPEECH
- Interesting papers may also be reviewed, even though they're not in the above list
- Useful blogs may also be reviewed
- Personal review, so don't contain all the contents of the paper
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2024 | NeurIPS (Spotlight) | MotionBooth: Motion-Aware Customized Text-to-Video Generation | Paper, Official Pytorch Code, Summary |
| 2024 | arXiv | Revisiting Feature Prediction for Learning Visual Representations from Video | Paper, Official Pytorch Code, Open Review, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2024 | CVPR (Highlight) | CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation | Paper, Official Pytorch Code, Summary |
| 2024 | CVPR | Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation | Paper, Official Pytorch Code, Summary |
| 2024 | ICLR (Spotlight) | Ferret: Refer and Ground Anything Anywhere at Any Granularity | Paper, Official Pytorch Code, Open Review, Summary |
| 2024 | ICLR (Spotlight) | Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks | Paper, Open Review, Summary |
| 2023 | INTERSPEECH | Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition | Paper, Summary |
| 2023 | INTERSPEECH | Language-specific Acoustic Boundary Learning for Mandarin-English Code-switching Speech Recognition | Paper, Summary |
| 2023 | NeurIPS Datasets and Benchmarks (Spotlight) | Stable Bias: Evaluating Societal Representations in Diffusion Models | Paper, Open Review, Summary |
| 2023 | CVPR | Towards Universal Fake Image Detectors that Generalize Across Generative Models | Paper, Official Pytorch Code, Summary |
| 2023 | NeurIPS | SEGA: Instructing Text-to-Image Models using Semantic Guidance | Paper, Official Pytorch Code, Open Review, Summary |
| 2023 | CVPR | Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture | Paper, Official Pytorch Code, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2023 | CVPR | Reproducible scaling laws for contrastive language-image learning | Paper, Official Pytorch Code, Summary |
| 2022 | ECCV (Workshop, Oral) | You Only Need a Good Embeddings Extractor to Fix Spurious Correlations | Paper, Summary |
| 2023 | ICML | Robust Speech Recognition via Large-Scale Weak Supervision | Paper, Official Pytorch Code, Summary |
| 2023 | NeurIPS (Spotlight) | Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases | Paper, Open Review, Summary |
| 2023 | ICASSP | Towards Zero-Shot Code-Switched Speech Recognition | Paper, Summary |
| 2022 | NeurIPS | Characterizing Datapoints via Second-Split Forgetting | Paper, Official Pytorch Code, Open Review, Summary |
| 2023 | ICASSP | Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization | Paper, Summary |
| 2023 | ICML (Oral) | Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models | Paper, Official Pytorch Code, Summary |
| 2022 | NeurIPS | On Feature Learning in the Presence of Spurious Correlations | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | NeurIPS (Workshop) | Classifier-Free Diffusion Guidance | Paper, Summary |
| 2022 | ECCV | CelebV-HQ: A Large-Scale Video Facial Attributes Dataset | Paper, Official Code, Summary |
| 2023 | ICLR (Spotlight) | Distilling Model Failures as Directions in Latent Space | Paper, Official Pytorch Code, Open Review, Summary |
| 2022 | NeurIPS (Oral) | Beyond neural scaling laws: beating power law scaling via data pruning | Paper, Official Code, Open Review, Summary |
| 2022 | CVPR (Oral) | Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR (Workshop) | VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution | Paper, Summary |
| 2022 | TMLR | CoCa: Contrastive Captioners are Image-Text Foundation Models | Paper, Open Review, Summary |
| 2022 | CVPR (Oral) | Detecting Deepfakes with Self-Blended Images | Paper, Official Pytorch Code, Summary |
| 2022 | ECCV | No Token Left Behind: Explainability-Aided Image Classification and Generation | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR | Unified Contrastive Learning in Image-Text-Label Space | Paper, Official Pytorch Code, Summary |
| 2022 | NeurIPS | Video Diffusion Models | Paper, Open Review, Summary |
| 2023 | ICLR (Spotlight) | Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations | Paper, Official Pytorch Code, Open Review, Summary |
| 2022 | ICLR (Oral) | Domino: Discovering Systematic Errors with Cross-Modal Embeddings | Paper, Official Pytorch Code, Open Review, Summary |
| 2022 | CVPR | Long-Tailed Recognition via Weight Balancing | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR (Oral) | Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection | Paper, Official Pytorch Code, Summary |
| 2022 | arXiv | RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training | Paper, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2022 | CVPR (Oral) | High-Resolution Image Synthesis with Latent Diffusion Models | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR | RegionCLIP: Region-based Language-Image Pretraining | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR | PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR | FLAVA: A Foundational Language And Vision Alignment Model | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR (Oral) | Grounded Language-Image Pre-training | Paper, Official Pytorch Code, Summary |
| 2022 | ICASSP | Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorization | Paper, Summary |
| 2021 | arXiv | Florence: A New Foundation Model for Computer Vision | Paper, Summary |
| 2022 | CVPR | SimMIM: A Simple Framework for Masked Image Modeling | Paper, Official Pytorch Code, Summary |
| 2021 | NeurIPS Datasets and Benchmarks | The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage | Paper, Official Pytorch Code, Open Review, Summary |
| 2022 | CVPR | LiT: Zero-Shot Transfer with Locked-image text Tuning | Paper, Official JAX Code, Summary |
| 2022 | CVPR (Oral) | Masked Autoencoders Are Scalable Vision Learners | Paper, Official Pytorch Code, Summary |
| 2022 | ICLR | Trivial or impossible - dichotomous data difficulty masks model differences (on ImageNet and beyond) | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | NeurIPS | Deep Learning on a Data Diet: Finding Important Examples Early in Training | Paper, Official JAX Code, Open Review, Summary |
| 2021 | NeurIPS (Oral) | Learning Debiased Representation via Disentangled Feature Augmentation | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | arXiv | Unsupervised Topic Segmentation of Meetings with BERT Embeddings | Paper, Official Pytorch Code, Summary |
| 2021 | NeurIPS | Deep Learning Through the Lens of Example Difficulty | Paper, Open Review, Summary |
| 2022 | ICLR (Oral) | BEiT: BERT Pre-Training of Image Transformers | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | INTERSPEECH | GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio | Paper, Official Code, Summary |
| 2022 | CVPR | Backdoor Attacks on Self-Supervised Learning | Paper, Official Pytorch Code, Summary |
| 2021 | NeurIPS (Spotlight) | Diffusion Models Beat GANs on Image Synthesis | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | NeurIPS | FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | ASRU | Non-autoregressive Mandarin-English Code-switching Speech Recognition | Paper, Summary |
| 2021 | ICCV (Oral) | An Empirical Study of Training Self-Supervised Vision Transformers | Paper, Official Pytorch Code, Summary |
| 2021 | INTERSPEECH (Oral) | SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition | Paper, Summary |
| 2021 | CVPR | Scale-aware Automatic Augmentation for Object Detection | Paper, Official Pytorch Code, Summary |
| 2021 | ICML (Spotlight) | Barlow Twins: Self-Supervised Learning via Redundancy Reduction | Paper, Official Pytorch Code, Summary |
| 2021 | ICML (Oral) | Learning Transferable Visual Models From Natural Language Supervision | Paper, Official Pytorch Code, Summary |
| 2021 | ICML (Spotlight) | Improved Denoising Diffusion Probabilistic Models | Paper, Official Pytorch Code, Summary |
| 2021 | ICML (Oral) | Delving into Deep Imbalanced Regression | Paper, Official Pytorch Code, Summary |
| 2021 | ICML (Oral) | Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision | Paper, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2020 | NeurIPS | CompRess: Self-Supervised Learning by Compressing Representations | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | ICASSP | Improved Mask-CTC for Non-Autoregressive End-to-End ASR | Paper, Summary |
| 2021 | ICLR (Oral) | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | Paper, Official Code, Open Review, Summary |
| 2020 | NeurIPS | Energy-based Out-of-distribution Detection | Paper, Official Pytorch Code, Open Review, Summary |
| 2021 | ICLR | Denoising Diffusion Implicit Models | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | EMNLP | Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics | Paper, Official Pytorch Code, Summary |
| 2022 | CVPR | Estimating Example Difficulty Using Variance of Gradients | Paper, Official TF/Pytorch Code, Summary |
| 2020 | NeurIPS (Spotlight) | What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation | Paper, Official TF Code, Open Review, Summary |
| 2020 | ICML | Concept Bottleneck Models | Paper, Official Pytorch Code, Summary |
| 2020 | NeurIPS | Learning from Failure: Training Debiased Classifier from Biased Classifier | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | INTERSPEECH | Spot the conversation: speaker diarisation in the wild | Paper, Official Code, Summary |
| 2020 | NeurIPS | Early-Learning Regularization Prevents Memorization of Noisy Labels | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | NeurIPS (Spotlight) | Object-Centric Learning with Slot Attention | Paper, Official TF Code, Open Review, Summary |
| 2020 | NeurIPS | Denoising Diffusion Probabilistic Models | Paper, Official TF Code, Open Review, Summary |
| 2020 | NeurIPS (Spotlight) | What Do Neural Networks Learn When Trained With Random Labels? | Paper, Open Review, Summary |
| 2020 | INTERSPEECH | Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition | Paper, Summary |
| 2020 | NeurIPS | Big Self-Supervised Models are Strong Semi-Supervised Learners | Paper, Official TF Code, Open Review, Summary |
| 2020 | NeurIPS | Improved Techniques for Training Score-Based Generative Models | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | NeurIPS (Oral) | Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning | Paper, Official JAX Code, Open Review, Summary |
| 2020 | arXiv | Are we done with ImageNet? | Paper, Official TF Code, Summary |
| 2020 | NeurIPS (Oral) | Rethinking Pre-training and Self-training | Paper, Official TF Code, Open Review, Summary |
| 2020 | INTERSPEECH | Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict | Paper, Summary |
| 2020 | INTERSPEECH | Conformer: Convolution-augmented Transformer for Speech Recognition | Paper, Summary |
| 2020 | NeurIPS | Supervised Contrastive Learning | Paper, Official TF Code, Official Pytorch Code, Open Review, Summary |
| 2020 | CVPR | Designing Network Design Spaces | Paper, Official Pytorch Code, Summary |
| 2020 | INTERSPEECH | In defence of metric learning for speaker recognition | Paper, Official Pytorch Code, Summary |
| 2020 | arXiv | Improved Baselines with Momentum Contrastive Learning | Paper, Official Pytorch Code, Summary |
| 2020 | ICML | A Simple Framework for Contrastive Learning of Visual Representations | Paper, Official TF Code, Summary |
| 2021 | ICML (Oral) | Characterizing Structural Regularities of Labeled Data in Overparameterized Models | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | NeurIPS | Identifying Mislabeled Data using the Area Under the Margin Ranking | Paper, Official Pytorch Code, Open Review, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2020 | ICLR | Adversarial AutoAugment | Paper, Open Review, Summary |
| 2020 | CVPR (Oral) | CNN-generated images are surprisingly easy to spot... for now | Paper, Official Pytorch Code, Summary |
| 2019 | arXiv | Recurrent Neural Networks (RNNs): A gentle Introduction and Overview | Paper, Summary |
| 2020 | ICLR (Oral) | Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | ICLR | Fantastic Generalization Measures and Where to Find Them | Paper, Open Review, Summary |
| 2020 | ECCV | Faster AutoAugment: Learning Augmentation Strategies using Backpropagation | Paper, Official Pytorch Code, Summary |
| 2020 | CVPR (Oral) | Momentum Contrast for Unsupervised Visual Representation Learning | Paper, Official Pytorch Code, Summary |
| 2019 | arXiv | What Do Compressed Deep Neural Networks Forget? | Paper, Summary |
| 2020 | ICLR | Decoupling Representation and Classifier for Long-Tailed Recognition | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | ICML | Learning De-biased Representations with Biased Representations | Paper, Official Pytorch Code, Summary |
| 2020 | NeurIPS | RandAugment: Practical Automated Data Augmentation with a Reduced Search Space | Paper, Official TF Code, Open Review, Summary |
| 2019 | INTERSPEECH | End-to-End Neural Speaker Diarization with Permutation-Free Objectives | Paper, Official Code, Summary |
| 2019 | NeurIPS (Oral) | Generative Modeling by Estimating Gradients of the Data Distribution | Paper, Official Pytorch Code, Open Review, Summary |
| 2020 | ECCV | Learning Data Augmentation Strategies for Object Detection | Paper, Official TF Code, Summary |
| 2020 | ICASSP | CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition | Paper, Summary |
| 2020 | CVPR | RetinaFace: Single-stage Dense Face Localisation in the Wild | Paper, Official Pytorch Code, Summary |
| 2019 | NeurIPS | Fast AutoAugment | Paper, Official Pytorch Code, Open Review, Summary |
| 2019 | ICCV | Attention Augmented Convolutional Networks | Paper, Summary |
| 2019 | EMNLP | Mask-Predict: Parallel Decoding of Conditional Masked Language Models | Paper, Official TF/Pytorch/JAX Code, Summary |
| 2019 | INTERSPEECH (Oral) | RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification | Paper, Official TF/Pytorch Code, Summary |
| 2019 | ICCV | Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression | Paper, Official Pytorch Code, Summary |
| 2019 | ICLR | Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet | Paper, Official Pytorch Code, Open Review, Summary |
| 2019 | ICML (Oral) | Do ImageNet Classifiers Generalize to ImageNet? | Paper, Official Pytorch Code, Summary |
| 2019 | INTERSPEECH | End-to-end losses based on speaker basis vectors and all-speaker hard negative mining for speaker verification | Paper, Summary |
| 2020 | CVPR | Augment Your Batch: Improving Generalization Through Instance Repetition | Paper, Official Pytorch Code, Open Review, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2019 | PNAS | Reconciling modern machine learning practice and the bias-variance trade-off | Paper, Summary |
| 2019 | ICLR | An Empirical Study of Example Forgetting during Deep Neural Network Learning | Paper, Official Pytorch Code, Open Review, Summary |
| 2019 | ICLR (Oral) | ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness | Paper, Official Code, OpenReview, Summary |
| 2019 | ICCV | Rethinking ImageNet Pre-training | Paper, Summary |
| 2019 | INTERSPEECH | On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition | Paper, Summary |
| 2019 | ICASSP | Towards End-to-End Code-Switching Speech Recognition | Paper, Summary |
| 2018 | NeurIPS | Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks | Paper, Official Code, Open Review, Summary |
| 2018 | NeurIPS | Generalisation in humans and deep neural networks | Paper, Official TF Code, Open Review, Summary |
| 2018 | EMNLP (Demo) | SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing | Paper, Official Code, Summary |
| 2018 | ECCV | Modeling Visual Context is Key to Augmenting Object Detection Datasets | Paper, Official TF Code, Summary |
| 2018 | ECCV | CBAM: Convolutional Block Attention Module | Paper, Official Pytorch Code, Summary |
| 2018 | BMVC (Oral) | BAM: Bottleneck Attention Module | Paper, Official Pytorch Code, Summary |
| 2018 | NeurIPS | An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution | Paper, Official TF Code, Open Review, Summary |
| 2018 | NeurIPS | Glow: Generative Flow with Invertible 1x1 Convolutions | Paper, Official TF Code, Open Review, Summary |
| 2018 | INTERSPEECH | VoxCeleb2: Deep Speaker Recognition | Paper, Summary |
| 2019 | ICLR | Robustness May Be at Odds with Accuracy | Paper, Official TF Code, Open Review, Summary |
| 2018 | CVPR | Look at Boundary: A Boundary-Aware Face Alignment Algorithm | Paper, Official Code, Summary |
| 2018 | CVPR | Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation | Paper, Official Pytorch Code, Summary |
| 2019 | CVPR (Oral) | AutoAugment: Learning Augmentation Strategies From Data | Paper, Official TF Code, Summary |
| 2019 | CVPR (Oral) | Do Better ImageNet Models Transfer Better? | Paper, Summary |
| 2019 | ICLR | Learning What and Where to Attend | Paper, Official TF Code, Open Review, Summary |
| 2018 | ACL (Long) | Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates | Paper, Official Code, Summary |
| 2018 | NeurIPS (Spotlight) | Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs | Paper, Official Pytorch Code, Open Review, Summary |
| 2019 | CVPR (Oral) | ArcFace: Additive Angular Margin Loss for Deep Face Recognition | Paper, Official Pytorch Code, Summary |
| 2018 | CVPR | The Unreasonable Effectiveness of Deep Features as a Perceptual Metric | Paper, Official Pytorch Code, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2018 | ICASSP | An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model | Paper, Summary |
| 2018 | ICASSP | Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models | Paper, Summary |
| 2018 | ICASSP | State-of-the-art Speech Recognition With Sequence-to-Sequence Models | Paper, Summary |
| 2018 | CVPR | Non-local Neural Networks | Paper, Official Code, Summary |
| 2017 | NIPS | Neural Discrete Representation Learning | Paper, Official TF Code, Open Review, Summary |
| 2017 | Distill | Sequence Modeling With CTC | Paper, Summary |
| 2017 | Distill | Feature Visualization | Paper, Summary |
| 2018 | ICASSP | Generalized End-to-End Loss for Speaker Verification | Paper, Official TF Code, Summary |
| 2017 | NIPS | Dynamic Routing Between Capsules | Paper, Open Review, Summary |
| 2018 | ICLR | mixup: Beyond Empirical Risk Minimization | Paper, Official Pytorch Code, Open Review, Summary |
| 2017 | NIPS | Learning to Compose Domain-Specific Transformations for Data Augmentation | Paper, Official TF Code, Open Review, Summary |
| 2018 | CVPR (Oral) | Squeeze-and-Excitation Networks | Paper, Official Code, Summary |
| 2017 | arXiv | Improved Regularization of Convolutional Neural Networks with Cutout | Paper, Official Pytorch Code, Summary |
| 2017 | INTERSPEECH (Oral) | VoxCeleb: a large-scale speaker identification dataset | Paper, Summary |
| 2018 | ICLR | Towards Deep Learning Models Resistant to Adversarial Attacks | Paper, Official TF Code 1, Official TF Code 2, Open Review, Summary |
| 2017 | ICML | A Closer Look at Memorization in Deep Networks | Paper, Summary |
| 2017 | ICML (Oral) | On Calibration of Modern Neural Networks | Paper, Official Pytorch Code, Summary |
| 2018 | ICLR | Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks | Paper, Official Pytorch Code, Open Review, Summary |
| 2017 | arXiv | Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour | Paper, Summary |
| 2017 | NIPS (Oral) | Train longer, generalize better: closing the generalization gap in large batch training of neural networks | Paper, Official Pytorch Code, Open Review, Summary |
| 2016 | NIPS | Understanding the Effective Receptive Field in Deep Convolutional Neural Networks | Paper, Open Review, Summary |
| 2017 | CVPR (Oral) | FC4: Fully Convolutional Color Constancy with Confidence-weighted Pooling | Paper, Official TF Code, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2017 | INTERSPEECH | Towards better decoding and language model integration in sequence to sequence models | Paper, Summary |
| 2017 | PNAS | Overcoming catastrophic forgetting in neural networks | Paper, Summary |
| 2017 | CVPR | Image-to-Image Translation with Conditional Adversarial Networks | Paper, Official Pytorch Code, Summary |
| 2017 | ICLR (Oral) | Understanding Deep Learning requires Rethinking Generalization | Paper, Official Pytorch Code, Open Review, Summary |
| 2017 | ICLR | Categorical Reparameterization with Gumbel-Softmax | Paper, Official TF Code, Summary |
| 2017 | ICLR | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables | Paper, Summary |
| 2017 | ICLR | A Learned Representation For Artistic Style | Paper, Official TF Code, Open Review, Summary |
| 2017 | ICLR | A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks | Paper, Official Code, Open Review, Summary |
| 2016 | arXiv | Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation | Paper, Summary |
| 2017 | ICLR (Oral) | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima | Paper, Official Pytorch Code, Open Review, Summary |
| 2016 | NIPS (Spotlight) | Learning Structured Sparsity in Deep Neural Networks | Paper, Official Code, Open Review, Summary |
| 2016 | arXiv | Gaussian Error Linear Units (GELUs) | Paper, Official Code, Summary |
| 2016 | NIPS | InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets | Paper, Official TF Code, Open Review, Summary |
| 2016 | NIPS (Spotlight) | f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization | Paper, Open Review, Summary |
| 2017 | ICLR | Density estimation using Real NVP | Paper, Open Review, Summary |
| 2016 | BMVC | Wide Residual Networks | Paper, Official Pytorch Code, Summary |
| 2016 | ACCV | Lip Reading in the Wild | Paper, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2016 | CVPR | Learning Deep Features for Discriminative Localization | Paper, Official Pytorch Code, Summary |
| 2016 | CVPR (Oral) | Deep Residual Learning for Image Recognition | Paper, Official Code, Summary |
| 2016 | ECCV (Oral) | SSD: Single Shot MultiBox Detector | Paper, Official Code, Summary |
| 2016 | ICLR | Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks | Paper, Summary |
| 2016 | ICLR | Importance Weighted Autoencoders | Paper, Summary |
| 2016 | ACL (Long) | Neural Machine Translation of Rare Words with Subword Units | Paper, Official Code, Summary |
| 2016 | AAAI (Oral) | Character-Aware Neural Language Models | Paper, Official Code, Summary |
| 2016 | ICASSP | End-to-End Attention-based Large Vocabulary Speech Recognition | Paper, Summary |
| 2015 | ICCV | Convolutional Color Constancy | Paper, Summary |
| 2015 | ICML (Workshop) | Understanding Neural Networks Through Deep Visualization | Paper, Official Code, Summary |
| 2015 | NIPS (Spotlight) | Spatial Transformer Networks | Paper, Open Review, Summary |
| 2015 | NIPS | Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | Paper, Official Code, Open Review, Summary |
| 2015 | NIPS | Texture Synthesis Using Convolutional Neural Networks | Paper, Official Code, Open Review, Summary |
| 2015 | ICML | Variational Inference with Normalizing Flows | Paper, Summary |
| 2015 | ICCV (Oral) | Fast R-CNN | Paper, Official Code, Summary |
| 2015 | ICML | Deep Unsupervised Learning using Nonequilibrium Thermodynamics | Paper, Official Code, Summary |
| 2015 | ICCV | Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification | Paper, Summary |
| Year | Conference | Paper | Links |
|---|---|---|---|
| 2015 | ICLR (Workshop) | Striving for Simplicity: The All Convolutional Net | Paper, Summary |
| 2015 | ICLR | Explaining and Harnessing Adversarial Examples | Paper, Summary |
| 2015 | ICLR (Oral) | Qualitatively characterizing neural network optimization problems | Paper, Summary |
| 2015 | CVPR (Oral) | Understanding Deep Image Representations by Inverting Them | Paper, Summary |
| 2014 | arXiv | Conditional Generative Adversarial Nets | Paper, Summary |
| 2015 | ICCV | Deep Learning Face Attributes in the Wild | Paper, Summary |
| 2015 | ICLR (Workshop) | NICE: Non-linear Independent Components Estimation | Paper, Official Code, Summary |
| 2015 | CVPR (Oral) | Going Deeper with Convolutions | Paper, Summary |
| 2015 | ICLR (Oral) | Very Deep Convolutional Networks for Large-Scale Image Recognition | Paper, Summary |
| 2014 | ECCV | Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | Paper, Summary |
| 2014 | NIPS | Generative Adversarial Networks | Paper, Official Code, Open Review, Summary |
| 2014 | ICLR | OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | Paper, Official Code, Open Review, Summary |
| 2014 | ICLR | Intriguing properties of neural networks | Paper, Open Review, Summary |
| 2014 | ICLR (Oral) | Auto-Encoding Variational Bayes | Paper, Open Review, Summary |
| 2014 | ICLR (Workshop) | Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps | Paper, Summary |
| 2014 | ICLR | Network In Network | Paper, Official Code, Open Review, Summary |
| 2014 | ECCV (Oral) | Visualizing and Understanding Convolutional Networks | Paper, Summary |
| 2014 | CVPR (Oral) | Rich feature hierarchies for accurate object detection and semantic segmentation | Paper, Official Code, Summary |
| 2013 | NIPS | Distributed Representations of Words and Phrases and their Compositionality | Paper, Official Code, Open Review, Summary |
| 2013 | ICLR (Workshop) | Efficient Estimation of Word Representations in Vector Space | Paper, Official Code, Open Review, Summary |
| 2012 | NIPS (Spotlight) | ImageNet Classification with Deep Convolutional Neural Networks | Paper, Summary |
Format : |20xx|Conference (Oral Spotlight Workshop)|Paper|Paper, Official TF/Pytorch/JAX Code, Open Review, Summary|
| Year | Source | Title | Links |
|---|---|---|---|
| 2022 | OpenAI Blog | DALL-E 2 pre-training mitigations | Blog, Summary |
| 2022 | Personal Blog | How DALL-E 2 Works | Blog, Summary |
| 2018 | Medium | Illustrated Guide to LSTM’s and GRU’s: A step by step explanation | Blog, Summary |
| 2018 | Medium | Illustrated Guide to Recurrent Neural Networks | Blog, Summary |
| 2015 | Google Blog | Inceptionism: Going Deeper into Neural Networks | Blog, Official Code, Summary |
Format : |20xx|Source|Title|Blog, Official TF/Pytorch/JAX Code, Summary|