| Learning Tracking Representations via Dual-Branch Fully Transformer Networks | Dec 5, 2021 | GPUObject Tracking | CodeCode Available | 1 |
| Logic Shrinkage: Learned FPGA Netlist Sparsity for Efficient Neural Network Inference | Dec 4, 2021 | Efficient Neural NetworkGPU | CodeCode Available | 1 |
| 3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity Challenge | Dec 4, 2021 | GPURetrieval | CodeCode Available | 1 |
| TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs | Dec 3, 2021 | GPUTranslation | CodeCode Available | 1 |
| Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer | Dec 3, 2021 | GPUHuman-Object Interaction Detection | CodeCode Available | 1 |
| Mesh Convolution with Continuous Filters for 3D Surface Parsing | Dec 3, 2021 | GPUScene Parsing | CodeCode Available | 1 |
| MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment | Dec 2, 2021 | GPU | CodeCode Available | 1 |
| Fast Neural Representations for Direct Volume Rendering | Dec 2, 2021 | GPUSuper-Resolution | CodeCode Available | 1 |
| CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction | Dec 1, 2021 | GPUSurface Reconstruction | CodeCode Available | 1 |
| 360MonoDepth: High-Resolution 360° Monocular Depth Estimation | Nov 30, 2021 | 2kDepth Estimation | CodeCode Available | 1 |
| EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs | Nov 30, 2021 | GPUImage Generation | CodeCode Available | 1 |
| NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning | Nov 27, 2021 | BIG-bench Machine LearningGPU | CodeCode Available | 1 |
| Bayesian Optimization for auto-tuning GPU kernels | Nov 26, 2021 | Bayesian OptimizationGPU | CodeCode Available | 1 |
| Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction | Nov 26, 2021 | 3D geometry3D Reconstruction | CodeCode Available | 1 |
| On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features | Nov 23, 2021 | GPUNode Classification | CodeCode Available | 1 |
| FastDOG: Fast Discrete Optimization on GPU | Nov 19, 2021 | Cell TrackingGPU | CodeCode Available | 1 |
| Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari | Nov 19, 2021 | Atari GamesGPU | CodeCode Available | 1 |
| You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling | Nov 18, 2021 | GPU | CodeCode Available | 1 |
| Rethinking Dilated Convolution for Real-time Semantic Segmentation | Nov 18, 2021 | DecoderGPU | CodeCode Available | 1 |
| Benchmarking and scaling of deep learning models for land cover image classification | Nov 18, 2021 | BenchmarkingClassification | CodeCode Available | 1 |
| Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation | Nov 18, 2021 | GPU | CodeCode Available | 1 |
| CGX: Adaptive System Support for Communication-Efficient Deep Learning | Nov 16, 2021 | Deep LearningGPU | CodeCode Available | 1 |
| User Allocation in Mobile Edge Computing: A Deep Reinforcement Learning Approach | Nov 11, 2021 | CPUDeep Reinforcement Learning | CodeCode Available | 1 |
| ParaFold: Paralleling AlphaFold for Large-Scale Predictions | Nov 11, 2021 | CPUGPU | CodeCode Available | 1 |
| MQBench: Towards Reproducible and Deployable Model Quantization Benchmark | Nov 5, 2021 | CPUGPU | CodeCode Available | 1 |
