| DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio | May 11, 2022 | CPUData Augmentation | CodeCode Available | 4 |
| Reducing Activation Recomputation in Large Transformer Models | May 10, 2022 | | CodeCode Available | 4 |
| Flamingo: a Visual Language Model for Few-Shot Learning | Apr 29, 2022 | Few-Shot LearningGenerative Visual Question Answering | CodeCode Available | 4 |
| ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models | Apr 19, 2022 | FairnessFew-Shot Image Classification | CodeCode Available | 4 |
| NAFSSR: Stereo Image Super-Resolution Using NAFNet | Apr 19, 2022 | Image RestorationImage Super-Resolution | CodeCode Available | 4 |
| TRUE: Re-evaluating Factual Consistency Evaluation | Apr 11, 2022 | Question GenerationQuestion-Generation | CodeCode Available | 4 |
| Simple Baselines for Image Restoration | Apr 10, 2022 | DeblurringDenoising | CodeCode Available | 4 |
| Sparse Tensor-based Point Cloud Attribute Compression | Apr 3, 2022 | Attribute | CodeCode Available | 4 |
| BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers | Mar 31, 2022 | 3D Object DetectionAutonomous Driving | CodeCode Available | 4 |
| PP-YOLOE: An evolved version of YOLO | Mar 30, 2022 | 2D Object DetectionDense Object Detection | CodeCode Available | 4 |
| Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation | Mar 29, 2022 | Binary ClassificationSegmentation | CodeCode Available | 4 |
| Brain-inspired Multilayer Perceptron with Spiking Neurons | Mar 28, 2022 | Inductive Bias | CodeCode Available | 4 |
| Thin-Plate Spline Motion Model for Image Animation | Mar 27, 2022 | Face ReenactmentImage Animation | CodeCode Available | 4 |
| GriTS: Grid table similarity metric for table structure recognition | Mar 23, 2022 | | CodeCode Available | 4 |
| A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation | Mar 18, 2022 | Music Transcription | CodeCode Available | 4 |
| Prototypical Verbalizer for Prompt-based Few-shot Tuning | Mar 18, 2022 | Contrastive LearningEntity Typing | CodeCode Available | 4 |
| TensoRF: Tensorial Radiance Fields | Mar 17, 2022 | Low-Dose X-Ray Ct ReconstructionNeRF | CodeCode Available | 4 |
| Context-Aware Drift Detection | Mar 16, 2022 | Drift Detection | CodeCode Available | 4 |
| Deepchecks: A Library for Testing and Validating Machine Learning Models and Data | Mar 16, 2022 | BIG-bench Machine Learning | CodeCode Available | 4 |
| The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models | Mar 14, 2022 | CPUQuantization | CodeCode Available | 4 |
| Conditional Prompt Learning for Vision-Language Models | Mar 10, 2022 | Domain GeneralizationPrompt Engineering | CodeCode Available | 4 |
| Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets | Mar 9, 2022 | BenchmarkingGraph Regression | CodeCode Available | 4 |
| Kubric: A scalable dataset generator | Mar 7, 2022 | FairnessNeRF | CodeCode Available | 4 |
| DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection | Mar 7, 2022 | Object DetectionReal-Time Object Detection | CodeCode Available | 4 |
| Highly Accurate Dichotomous Image Segmentation | Mar 6, 2022 | 2k3D Reconstruction | CodeCode Available | 4 |
| DN-DETR: Accelerate DETR Training by Introducing Query DeNoising | Mar 2, 2022 | DecoderObject Detection | CodeCode Available | 4 |
| Learning the Beauty in Songs: Neural Singing Voice Beautifier | Feb 27, 2022 | Dynamic Time Warping | CodeCode Available | 4 |
| Visual Attention Network | Feb 20, 2022 | image-classificationImage Classification | CodeCode Available | 4 |
| Transformers in Time Series: A Survey | Feb 15, 2022 | Anomaly DetectionSurvey | CodeCode Available | 4 |
| Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content? | Feb 14, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 4 |
| FILM: Frame Interpolation for Large Motion | Feb 10, 2022 | Optical Flow EstimationVideo Frame Interpolation | CodeCode Available | 4 |
| Competition-Level Code Generation with AlphaCode | Feb 8, 2022 | Code Generation | CodeCode Available | 4 |
| PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts | Feb 2, 2022 | | CodeCode Available | 4 |
| Locally Typical Sampling | Feb 1, 2022 | Abstractive Text SummarizationStory Generation | CodeCode Available | 4 |
| Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning | Jan 28, 2022 | | CodeCode Available | 4 |
| Fairness Implications of Encoding Protected Categorical Attributes | Jan 27, 2022 | FairnessFeature Engineering | CodeCode Available | 4 |
| RePaint: Inpainting using Denoising Diffusion Probabilistic Models | Jan 24, 2022 | DenoisingImage Inpainting | CodeCode Available | 4 |
| Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets | Jan 6, 2022 | Memorization | CodeCode Available | 4 |
| High-Resolution Image Synthesis with Latent Diffusion Models | Dec 20, 2021 | DenoisingGPU | CodeCode Available | 4 |
| Self-attention Does Not Need O(n^2) Memory | Dec 10, 2021 | | CodeCode Available | 4 |
| Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training | Oct 28, 2021 | Deep LearningGPU | CodeCode Available | 4 |
| On the Contribution of Per-ICD Attention Mechanisms to Classify Health Records in Languages with Fewer Resources than English | Sep 1, 2021 | Language Modelling | CodeCode Available | 4 |
| Detectron2 Object Detection & Manipulating Images using Cartoonization | Aug 1, 2021 | Autonomous VehiclesData Visualization | CodeCode Available | 4 |
| Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data | Jul 22, 2021 | Blind Super-ResolutionSuper-Resolution | CodeCode Available | 4 |
| Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport | Jun 24, 2021 | Stock Prediction | CodeCode Available | 4 |
| Dive into Deep Learning | Jun 21, 2021 | Deep LearningMath | CodeCode Available | 4 |
| MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask | Feb 9, 2021 | Click-Through Rate PredictionRecommendation Systems | CodeCode Available | 4 |
| What Makes Good In-Context Examples for GPT-3? | Jan 17, 2021 | Few-Shot LearningNatural Language Understanding | CodeCode Available | 4 |
| Towards Real-World Blind Face Restoration with Generative Facial Prior | Jan 11, 2021 | Blind Face RestorationVideo Super-Resolution | CodeCode Available | 4 |
| RegNet: Self-Regulated Network for Image Classification | Jan 3, 2021 | ClassificationGeneral Classification | CodeCode Available | 4 |