| Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization | Sep 13, 2021 | GPUImage Harmonization | CodeCode Available | 1 |
| RAMA: A Rapid Multicut Algorithm on GPU | Sep 4, 2021 | 3D Instance SegmentationClustering | CodeCode Available | 1 |
| Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters | Sep 3, 2021 | GPUManagement | CodeCode Available | 1 |
| FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation | Sep 2, 2021 | Autonomous DrivingDecoder | CodeCode Available | 1 |
| Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools | Aug 31, 2021 | GPU | CodeCode Available | 1 |
| WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU | Aug 31, 2021 | CPUDecision Making | CodeCode Available | 1 |
| FOVEA: Foveated Image Magnification for Autonomous Navigation | Aug 27, 2021 | Autonomous DrivingAutonomous Navigation | CodeCode Available | 1 |
| Recall@k Surrogate Loss with Large Batches and Similarity Mixup | Aug 25, 2021 | GPUImage Retrieval | CodeCode Available | 1 |
| Transformer for Single Image Super-Resolution | Aug 25, 2021 | GPUImage Super-Resolution | CodeCode Available | 1 |
| Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems | Aug 24, 2021 | Collision AvoidanceDecoder | CodeCode Available | 1 |
| MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching | Aug 22, 2021 | Depth EstimationDisparity Estimation | CodeCode Available | 1 |
| Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance | Aug 20, 2021 | DecoderGPU | CodeCode Available | 1 |
| SquiggleFilter: An Accelerator for Portable Virus Detection | Aug 14, 2021 | Dynamic Time WarpingGPU | CodeCode Available | 1 |
| PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds | Aug 14, 2021 | 3D Single Object TrackingGPU | CodeCode Available | 1 |
| EEEA-Net: An Early Exit Evolutionary Neural Architecture Search | Aug 13, 2021 | GPUImage Classification | CodeCode Available | 1 |
| PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management | Aug 12, 2021 | CPUGPU | CodeCode Available | 1 |
| Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation | Aug 10, 2021 | GPUNeural Architecture Search | CodeCode Available | 1 |
| Disentangled High Quality Salient Object Detection | Aug 8, 2021 | GPUObject | CodeCode Available | 1 |
| Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance | Aug 2, 2021 | CPUGPU | CodeCode Available | 1 |
| Efficient Neural Network Approximation of Robust PCA for Automated Analysis of Calcium Imaging Data | Jul 31, 2021 | Efficient Neural NetworkGPU | CodeCode Available | 1 |
| Out-of-Core Surface Reconstruction via Global TGV Minimization | Jul 30, 2021 | DiversityGPU | CodeCode Available | 1 |
| Video Based Fall Detection Using Human Poses | Jul 29, 2021 | Action RecognitionGPU | CodeCode Available | 1 |
| Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning | Jul 20, 2021 | continuous-controlContinuous Control | CodeCode Available | 1 |
| Discriminator-Free Generative Adversarial Attack | Jul 20, 2021 | Adversarial AttackDisentanglement | CodeCode Available | 1 |
| Megaverse: Simulating Embodied Agents at One Million Experiences per Second | Jul 17, 2021 | GPUReinforcement Learning (RL) | CodeCode Available | 1 |
| Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines | Jul 14, 2021 | GPUScheduling | CodeCode Available | 1 |
| Fine-tuning giant neural networks on commodity hardware with automatic pipeline model parallelism | Jul 14, 2021 | GPUTransfer Learning | CodeCode Available | 1 |
| Fast and Slow Enigmas and Parental Guidance | Jul 14, 2021 | GPU | CodeCode Available | 1 |
| BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym | Jul 9, 2021 | GPUReinforcement Learning (RL) | CodeCode Available | 1 |
| Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints | Jul 5, 2021 | Computational EfficiencyGPU | CodeCode Available | 1 |
| Vision Xformers: Efficient Attention for Image Classification | Jul 5, 2021 | ClassificationGPU | CodeCode Available | 1 |
| Memory Efficient Meta-Learning with Large Images | Jul 2, 2021 | Few-Shot Image ClassificationGPU | CodeCode Available | 1 |
| Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets | Jul 2, 2021 | GPUMeta-Learning | CodeCode Available | 1 |
| Privacy Budget Scheduling | Jun 29, 2021 | CPUFairness | CodeCode Available | 1 |
| Fast computation of mutual information in the frequency domain with applications to global multimodal image alignment | Jun 28, 2021 | GPU | CodeCode Available | 1 |
| Lettuce: PyTorch-based Lattice Boltzmann Framework | Jun 24, 2021 | BIG-bench Machine LearningGPU | CodeCode Available | 1 |
| APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores | Jun 23, 2021 | GPUQuantization | CodeCode Available | 1 |
| Randomness In Neural Network Training: Characterizing The Impact of Tooling | Jun 22, 2021 | GPU | CodeCode Available | 1 |
| CPM-2: Large-scale Cost-effective Pre-trained Language Models | Jun 20, 2021 | DecoderGPU | CodeCode Available | 1 |
| Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation | Jun 19, 2021 | Autonomous DrivingGPU | CodeCode Available | 1 |
| AKG: Automatic Kernel Generation for Neural Processing Units using Polyhedral Transformations | Jun 19, 2021 | Code GenerationCPU | CodeCode Available | 1 |
| Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources | Jun 19, 2021 | Face RecognitionGPU | CodeCode Available | 1 |
| Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning | Jun 19, 2021 | 4kGPU | CodeCode Available | 1 |
| Metamorphic image registration using a semi-Lagrangian scheme | Jun 16, 2021 | GPUImage Registration | CodeCode Available | 1 |
| MetaCache-GPU: Ultra-Fast Metagenomic Classification | Jun 14, 2021 | ClassificationCPU | CodeCode Available | 1 |
| SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes | Jun 12, 2021 | Gaussian ProcessesGPU | CodeCode Available | 1 |
| Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems | Jun 12, 2021 | Birds Eye View Object DetectionCPU | CodeCode Available | 1 |
| GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings | Jun 10, 2021 | GPU | CodeCode Available | 1 |
| Accelerating Neural Architecture Search via Proxy Data | Jun 9, 2021 | GPUNeural Architecture Search | CodeCode Available | 1 |
| Shape As Points: A Differentiable Poisson Solver | Jun 7, 2021 | 3D ReconstructionGPU | CodeCode Available | 1 |
