| UKAN: Unbound Kolmogorov-Arnold Network Accompanied with Accelerated Library | Aug 20, 2024 | BenchmarkingComputational Efficiency | —Unverified | 0 |
| ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining | Aug 20, 2024 | 3DGSGPU | —Unverified | 0 |
| HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models | Aug 20, 2024 | GPULanguage Modelling | CodeCode Available | 1 |
| Fine-Tuning a Local LLaMA-3 Large Language Model for Automated Privacy-Preserving Physician Letter Generation in Radiation Oncology | Aug 20, 2024 | GPULanguage Modeling | —Unverified | 0 |
| EdgeNAT: Transformer for Efficient Edge Detection | Aug 20, 2024 | Edge DetectionGPU | CodeCode Available | 1 |
| LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models | Aug 20, 2024 | GPU | CodeCode Available | 0 |
| Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches | Aug 20, 2024 | GPUModel Compression | —Unverified | 0 |
| Near, far: Patch-ordering enhances vision foundation models' scene understanding | Aug 20, 2024 | GPUScene Understanding | —Unverified | 0 |
| Accelerating Goal-Conditioned RL Algorithms and Research | Aug 20, 2024 | GPUreinforcement-learning | CodeCode Available | 3 |
| Stream-Based Ground Segmentation for Real-Time LiDAR Point Cloud Processing on FPGA | Aug 19, 2024 | CPUGPU | —Unverified | 0 |
