| Hybrid-Regressive Neural Machine Translation | Oct 19, 2022 | CPUDecoder | —Unverified | 0 |
| Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction | Oct 19, 2022 | GPU | CodeCode Available | 1 |
| High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registration | Oct 19, 2022 | Depth EstimationGPU | —Unverified | 0 |
| High-efficient Bloch simulation of magnetic resonance imaging sequences based on deep learning | Oct 19, 2022 | Deep LearningGPU | —Unverified | 0 |
| Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference | Oct 17, 2022 | CPUGPU | —Unverified | 0 |
| A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models | Oct 17, 2022 | CPUGPU | CodeCode Available | 3 |
| An efficient deep neural network to find small objects in large 3D images | Oct 16, 2022 | AnatomyGPU | CodeCode Available | 1 |
| HQNAS: Auto CNN deployment framework for joint quantization and architecture search | Oct 16, 2022 | GPUNeural Architecture Search | —Unverified | 0 |
| AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks | Oct 14, 2022 | BIG-bench Machine LearningGPU | CodeCode Available | 1 |
| An Efficient FPGA Accelerator for Point Cloud | Oct 14, 2022 | Autonomous DrivingComputational Efficiency | —Unverified | 0 |
| A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking | Oct 14, 2022 | BenchmarkingGPU | CodeCode Available | 1 |
| Pareto-aware Neural Architecture Generation for Diverse Computational Budgets | Oct 14, 2022 | CPUGPU | CodeCode Available | 0 |
| WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis | Oct 13, 2022 | Efficient Neural NetworkGPU | CodeCode Available | 1 |
| RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer | Oct 13, 2022 | GPUReal-Time Semantic Segmentation | —Unverified | 0 |
| Behavioral graph fraud detection in E-commerce | Oct 13, 2022 | Fraud DetectionGPU | —Unverified | 0 |
| Latency-aware Spatial-wise Dynamic Networks | Oct 12, 2022 | GPUimage-classification | CodeCode Available | 1 |
| An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification | Oct 11, 2022 | Document ClassificationGPU | CodeCode Available | 0 |
| Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training | Oct 11, 2022 | GPUKnowledge Graphs | —Unverified | 0 |
| DPANET:Dual Pooling Attention Network for Semantic Segmentation | Oct 11, 2022 | GPUImage Segmentation | —Unverified | 0 |
| VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement | Oct 11, 2022 | GPUNavigate | —Unverified | 0 |
| RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks | Oct 11, 2022 | Adversarial RobustnessGPU | CodeCode Available | 0 |
| Rieoptax: Riemannian Optimization in JAX | Oct 10, 2022 | CPUGPU | CodeCode Available | 0 |
| Fine-Tuning Pre-trained Transformers into Decaying Fast Weights | Oct 9, 2022 | GPU | CodeCode Available | 1 |
| Deep Learning Inference Frameworks Benchmark | Oct 9, 2022 | CPUDeep Learning | CodeCode Available | 0 |
| Noise-Robust De-Duplication at Scale | Oct 9, 2022 | ArticlesGPU | CodeCode Available | 1 |
