| Separable Self and Mixed Attention Transformers for Efficient Object Tracking | Sep 7, 2023 | CPUGPU | CodeCode Available | 1 |
| CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra | Sep 6, 2023 | CoLAGaussian Processes | CodeCode Available | 2 |
| Patched Line Segment Learning for Vector Road Mapping | Sep 6, 2023 | GPU | —Unverified | 0 |
| Efficient Training for Visual Tracking with Deformable Transformer | Sep 6, 2023 | DecoderDenoising | —Unverified | 0 |
| Comparative Analysis of CPU and GPU Profiling for Deep Learning Models | Sep 5, 2023 | CPUGPU | —Unverified | 0 |
| TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models | Sep 5, 2023 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| QuantEase: Optimization-based Quantization for Language Models | Sep 5, 2023 | GPUQuantization | —Unverified | 0 |
| Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesis | Sep 5, 2023 | DiversityGPU | CodeCode Available | 0 |
| Approximating High-Dimensional Minimal Surfaces with Physics-Informed Neural Networks | Sep 5, 2023 | GPU | —Unverified | 0 |
| TensorBank: Tensor Lakehouse for Foundation Model Training | Sep 5, 2023 | GPUmodel | —Unverified | 0 |
| nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources | Sep 5, 2023 | DecoderGPU | CodeCode Available | 3 |
| An FPGA smart camera implementation of segmentation models for drone wildfire imagery | Sep 4, 2023 | GPU | —Unverified | 0 |
| SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices | Sep 4, 2023 | Autonomous VehiclesGPU | —Unverified | 0 |
| FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs | Sep 3, 2023 | CPUGPU | —Unverified | 0 |
| Geometry-Informed Neural Operator for Large-Scale 3D PDEs | Sep 1, 2023 | GPU | —Unverified | 0 |
| Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images | Aug 31, 2023 | GPUImage Generation | —Unverified | 0 |
| SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills | Aug 31, 2023 | GPULanguage Modelling | —Unverified | 0 |
| Diffusion Models for Interferometric Satellite Aperture Radar | Aug 31, 2023 | GPUImage Generation | CodeCode Available | 1 |
| Latency-aware Unified Dynamic Networks for Efficient Image Recognition | Aug 30, 2023 | GPUScheduling | CodeCode Available | 1 |
| Everything Perturbed All at Once: Enabling Differentiable Graph Attacks | Aug 29, 2023 | AllGPU | —Unverified | 0 |
| Learning to Upsample by Learning to Sample | Aug 29, 2023 | Depth EstimationFeature Upsampling | CodeCode Available | 1 |
| CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs | Aug 29, 2023 | CPUGPU | CodeCode Available | 2 |
| ABS-SGD: A Delayed Synchronous Stochastic Gradient Descent Algorithm with Adaptive Batch Size for Heterogeneous GPU Clusters | Aug 29, 2023 | GPU | —Unverified | 0 |
| Massively Parallel Continuous Local Search for Hybrid SAT Solving on GPUs | Aug 29, 2023 | CPUGPU | CodeCode Available | 1 |
| Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance | Aug 28, 2023 | Contrastive LearningFew-Shot Text Classification | —Unverified | 0 |