| Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape | Jan 20, 2022 | | CodeCode Available | 3 |
| Stitch it in Time: GAN-Based Facial Editing of Real Videos | Jan 20, 2022 | Facial Editing | CodeCode Available | 3 |
| Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next | Jan 14, 2022 | Multi-Task Learning | CodeCode Available | 3 |
| Datasheet for the Pile | Jan 13, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 3 |
| DM-VIO: Delayed Marginalization Visual-Inertial Odometry | Jan 11, 2022 | | CodeCode Available | 3 |
| MAXIM: Multi-Axis MLP for Image Processing | Jan 9, 2022 | DeblurringDenoising | CodeCode Available | 3 |
| Detecting Twenty-thousand Classes using Image-level Supervision | Jan 7, 2022 | Cross-Domain Few-Shot Object Detectionimage-classification | CodeCode Available | 3 |
| NeROIC: Neural Rendering of Objects from Online Image Collections | Jan 7, 2022 | Neural RenderingNovel View Synthesis | CodeCode Available | 3 |
| SNR-Aware Low-Light Image Enhancement | Jan 1, 2022 | Image EnhancementLow-Light Image Enhancement | CodeCode Available | 3 |
| PP-MSVSR: Multi-Stage Video Super-Resolution | Dec 6, 2021 | Image Super-ResolutionSuper-Resolution | CodeCode Available | 3 |
| Detect Faces Efficiently: A Survey and Evaluations | Dec 3, 2021 | Deep LearningFace Detection | CodeCode Available | 3 |
| Channel Permutations for N:M Sparsity | Dec 1, 2021 | | CodeCode Available | 3 |
| OCR-free Document Understanding Transformer | Nov 30, 2021 | Document Image Classificationdocument understanding | CodeCode Available | 3 |
| Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities | Nov 17, 2021 | regression | CodeCode Available | 3 |
| CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms | Nov 16, 2021 | BenchmarkingDeep Reinforcement Learning | CodeCode Available | 3 |
| Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction | Nov 15, 2021 | Compressive SensingImage Reconstruction | CodeCode Available | 3 |
| On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning | Nov 10, 2021 | Multi-agent Reinforcement Learningreinforcement-learning | CodeCode Available | 3 |
| Personalized Benchmarking with the Ludwig Benchmarking Toolkit | Nov 8, 2021 | BenchmarkingHyperparameter Optimization | CodeCode Available | 3 |
| Benchmarking Multimodal AutoML for Tabular Data with Text Fields | Nov 4, 2021 | AutoMLBenchmarking | CodeCode Available | 3 |
| LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs | Nov 3, 2021 | Few-Shot Learning | CodeCode Available | 3 |
| OneFlow: Redesign the Distributed Deep Learning Framework from Scratch | Oct 28, 2021 | Deep Learning | CodeCode Available | 3 |
| Training Verifiers to Solve Math Word Problems | Oct 27, 2021 | GSM8KMath | CodeCode Available | 3 |
| WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing | Oct 26, 2021 | DenoisingSelf-Supervised Learning | CodeCode Available | 3 |
| 8-bit Optimizers via Block-wise Quantization | Oct 6, 2021 | Language ModelingLanguage Modelling | CodeCode Available | 3 |
| Towards General-purpose Infrastructure for Protecting Scientific Data Under Study | Oct 4, 2021 | | CodeCode Available | 3 |
| Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates | Sep 27, 2021 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 3 |
| Resolution-robust Large Mask Inpainting with Fourier Convolutions | Sep 15, 2021 | Image InpaintingSeeing Beyond the Visible | CodeCode Available | 3 |
| Datasets: A Community Library for Natural Language Processing | Sep 7, 2021 | Image ClassificationObject Recognition | CodeCode Available | 3 |
| Finetuned Language Models Are Zero-Shot Learners | Sep 3, 2021 | ARCCommon Sense Reasoning | CodeCode Available | 3 |
| DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions | Aug 27, 2021 | Causal Discovery | CodeCode Available | 3 |
| Robust High-Resolution Video Matting with Temporal Guidance | Aug 25, 2021 | 4kGPU | CodeCode Available | 3 |
| SwinIR: Image Restoration Using Swin Transformer | Aug 23, 2021 | Color Image DenoisingDenoising | CodeCode Available | 3 |
| W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training | Aug 7, 2021 | Contrastive LearningLanguage Modeling | CodeCode Available | 3 |
| Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction | Aug 1, 2021 | | CodeCode Available | 3 |
| Optimal Variable Speed Limit Control Strategy on Freeway Segments under Fog Conditions | Jul 30, 2021 | | CodeCode Available | 3 |
| Tianshou: a Highly Modularized Deep Reinforcement Learning Library | Jul 29, 2021 | Deep Reinforcement LearningMuJoCo | CodeCode Available | 3 |
| Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge | Jul 27, 2021 | 2D Object DetectionAutonomous Driving | CodeCode Available | 3 |
| Declarative Machine Learning Systems | Jul 16, 2021 | BIG-bench Machine Learning | CodeCode Available | 3 |
| Highly accurate protein structure prediction with AlphaFold | Jul 15, 2021 | PredictionProtein Folding | CodeCode Available | 3 |
| SoundStream: An End-to-End Neural Audio Codec | Jul 7, 2021 | CPUDecoder | CodeCode Available | 3 |
| Evaluating Large Language Models Trained on Code | Jul 7, 2021 | Code GenerationHumanEval | CodeCode Available | 3 |
| Alias-Free Generative Adversarial Networks | Jun 23, 2021 | Image Generation | CodeCode Available | 3 |
| Multi-objective Asynchronous Successive Halving | Jun 23, 2021 | FairnessHyperparameter Optimization | CodeCode Available | 3 |
| Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples | Jun 18, 2021 | Adversarial Robustness | CodeCode Available | 3 |
| XCiT: Cross-Covariance Image Transformers | Jun 17, 2021 | image-classificationImage Classification | CodeCode Available | 3 |
| UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation | Jun 15, 2021 | Speech Synthesistext-to-speech | CodeCode Available | 3 |
| SimSwap: An Efficient Framework For High Fidelity Face Swapping | Jun 11, 2021 | Face SwappingVocal Bursts Intensity Prediction | CodeCode Available | 3 |
| Pivotal Tuning for Latent-based Editing of Real Images | Jun 10, 2021 | Facial EditingImage Manipulation | CodeCode Available | 3 |
| Compacter: Efficient Low-Rank Hypercomplex Adapter Layers | Jun 8, 2021 | parameter-efficient fine-tuning | CodeCode Available | 3 |
| Spectral Pruning for Recurrent Neural Networks | May 23, 2021 | Edge-computing | CodeCode Available | 3 |