| LMLT: Low-to-high Multi-Level Vision Transformer for Image Super-Resolution | Sep 5, 2024 | GPUImage Super-Resolution | CodeCode Available | 1 |
| LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones | Sep 5, 2024 | CPUGPU | CodeCode Available | 1 |
| TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval | Sep 2, 2024 | GPURetrieval | CodeCode Available | 1 |
| TinyTNAS: GPU-Free, Time-Bound, Hardware-Aware Neural Architecture Search for TinyML Time Series Classification | Aug 29, 2024 | CPUDiagnostic | CodeCode Available | 1 |
| GPU-Accelerated Counterfactual Regret Minimization | Aug 27, 2024 | counterfactualGPU | CodeCode Available | 1 |
| Efficient fine-tuning of 37-level GraphCast with the Canadian global deterministic analysis | Aug 26, 2024 | GPU | CodeCode Available | 1 |
| S4D: Streaming 4D Real-World Reconstruction with Gaussians and 3D Control Points | Aug 23, 2024 | 3D Reconstruction4D reconstruction | CodeCode Available | 1 |
| EdgeNAT: Transformer for Efficient Edge Detection | Aug 20, 2024 | Edge DetectionGPU | CodeCode Available | 1 |
| HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models | Aug 20, 2024 | GPULanguage Modelling | CodeCode Available | 1 |
| Image-to-LaTeX Converter for Mathematical Formulas and Text | Aug 7, 2024 | DecoderGPU | CodeCode Available | 1 |