| RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem | Nov 25, 2020 | reinforcement-learningReinforcement Learning | CodeCode Available | 4 |
| ControlVAE: Tuning, Analytical Properties, and Performance Analysis | Oct 31, 2020 | DisentanglementImage Generation | CodeCode Available | 4 |
| GPUTreeShap: Massively Parallel Exact Calculation of SHAP Scores for Tree Ensembles | Oct 27, 2020 | BIG-bench Machine LearningCPU | CodeCode Available | 4 |
| Qlib: An AI-oriented Quantitative Investment Platform | Sep 22, 2020 | Portfolio OptimizationStock Market Prediction | CodeCode Available | 4 |
| A Framework For Contrastive Self-Supervised Learning And Designing A New Approach | Aug 31, 2020 | Data AugmentationImage Classification | CodeCode Available | 4 |
| Attention Mesh: High-fidelity Face Mesh Prediction in Real-time | Jun 19, 2020 | Vocal Bursts Intensity Prediction | CodeCode Available | 4 |
| BlazePose: On-device Real-time Body Pose tracking | Jun 17, 2020 | 2D Human Pose Estimation3D Human Pose Estimation | CodeCode Available | 4 |
| Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | May 22, 2020 | Fact VerificationQuestion Answering | CodeCode Available | 4 |
| DeepFaceLab: Integrated, flexible and extensible face-swapping framework | May 12, 2020 | Face Swapping | CodeCode Available | 4 |
| CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset | Feb 27, 2020 | Dialogue State TrackingTask-Oriented Dialogue Systems | CodeCode Available | 4 |
| Predicting Subjective Features of Questions of QA Websites using BERT | Feb 24, 2020 | Community Question AnsweringQuestion Answering | CodeCode Available | 4 |
| fastai: A Layered API for Deep Learning | Feb 11, 2020 | Deep LearningGPU | CodeCode Available | 4 |
| DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection | Jan 1, 2020 | AttributeDeepFake Detection | CodeCode Available | 4 |
| Fast Transformer Decoding: One Write-Head is All You Need | Nov 6, 2019 | AllLanguage Modelling | CodeCode Available | 4 |
| Character Region Awareness for Text Detection | Apr 3, 2019 | Scene Text DetectionText Detection | CodeCode Available | 4 |
| Panoptic Feature Pyramid Networks | Jan 8, 2019 | Instance SegmentationPanoptic Segmentation | CodeCode Available | 4 |
| XGBoost: Scalable GPU Accelerated Learning | Jun 29, 2018 | Cloud ComputingData Compression | CodeCode Available | 4 |
| Link and code: Fast indexing with graphs and compact regression codes | Apr 26, 2018 | Image Similarity SearchQuantization | CodeCode Available | 4 |
| An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting | Apr 20, 2018 | | CodeCode Available | 4 |
| RLlib: Abstractions for Distributed Reinforcement Learning | Dec 26, 2017 | reinforcement-learningReinforcement Learning | CodeCode Available | 4 |
| Ray: A Distributed Framework for Emerging AI Applications | Dec 16, 2017 | reinforcement-learningReinforcement Learning | CodeCode Available | 4 |
| Stock Price Prediction via Discovering Multi-Frequency Trading Patterns | Aug 13, 2017 | PredictionStock Price Prediction | CodeCode Available | 4 |
| SmoothGrad: removing noise by adding noise | Jun 12, 2017 | Interpretable Machine LearningSensitivity | CodeCode Available | 4 |
| Learning Important Features Through Propagating Activation Differences | Apr 10, 2017 | Interpretable Machine Learning | CodeCode Available | 4 |
| Billion-scale similarity search with GPUs | Feb 28, 2017 | GPUImage Similarity Search | CodeCode Available | 4 |
| Polysemous codes | Sep 7, 2016 | Quantization | CodeCode Available | 4 |
| XGBoost: A Scalable Tree Boosting System | Mar 9, 2016 | BIG-bench Machine LearningClustering | CodeCode Available | 4 |
| Deep Residual Learning for Image Recognition | Dec 10, 2015 | Classification | CodeCode Available | 4 |
| An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition | Jul 21, 2015 | Optical Character Recognition (OCR)Scene Text Recognition | CodeCode Available | 4 |
| LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans | Mar 19, 2026 | | —Unverified | 3 |
| Tree Search for LLM Agent Reinforcement Learning | Mar 18, 2026 | | —Unverified | 3 |
| Generative Refocusing: Flexible Defocus Control from a Single Image | Mar 18, 2026 | | —Unverified | 3 |
| SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation | Mar 17, 2026 | | —Unverified | 3 |
| χ_0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies | Mar 17, 2026 | | —Unverified | 3 |
| UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections | Mar 16, 2026 | | —Unverified | 3 |
| ReactMotion: Generating Reactive Listener Motions from Speaker Utterance | Mar 16, 2026 | | —Unverified | 3 |
| Grounding World Simulation Models in a Real-World Metropolis | Mar 16, 2026 | | —Unverified | 3 |
| SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis | Mar 16, 2026 | | —Unverified | 3 |
| OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data | Mar 16, 2026 | | —Unverified | 3 |
| AI Can Learn Scientific Taste | Mar 15, 2026 | | —Unverified | 3 |
| LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels | Mar 13, 2026 | | —Unverified | 3 |
| VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction | Mar 12, 2026 | | —Unverified | 3 |
| Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights | Mar 12, 2026 | | —Unverified | 3 |
| DVD: Deterministic Video Depth Estimation with Generative Priors | Mar 12, 2026 | | —Unverified | 3 |
| InstantSfM: Towards GPU-Native SfM for the Deep Learning Era | Mar 11, 2026 | | —Unverified | 3 |
| Qianfan-OCR: A Unified End-to-End Model for Document Intelligence | Mar 11, 2026 | | —Unverified | 3 |
| LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination | Mar 11, 2026 | | —Unverified | 3 |
| InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing | Mar 10, 2026 | | —Unverified | 3 |
| Light of Normals: Unified Feature Representation for Universal Photometric Stereo | Mar 9, 2026 | | —Unverified | 3 |
| Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence | Mar 8, 2026 | | —Unverified | 3 |