| Revisiting PCA for time series reduction in temporal dimension | Dec 27, 2024 | Computational EfficiencyDimensionality Reduction | CodeCode Available | 7 |
| MBQ: Modality-Balanced Quantization for Large Vision-Language Models | Dec 27, 2024 | GPUQuantization | CodeCode Available | 2 |
| Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference | Dec 25, 2024 | CPUGPU | —Unverified | 0 |
| KunServe: Efficient Parameter-centric Memory Management for LLM Serving | Dec 24, 2024 | GPULanguage Modeling | —Unverified | 0 |
| GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network | Dec 24, 2024 | GPUgraph construction | CodeCode Available | 1 |
| GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference | Dec 23, 2024 | GPULanguage Modeling | —Unverified | 0 |
| Power- and Fragmentation-aware Online Scheduling for GPU Datacenters | Dec 23, 2024 | CPUGPU | CodeCode Available | 0 |
| CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction | Dec 23, 2024 | 3DGSGPU | —Unverified | 0 |
| Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling | Dec 23, 2024 | 3DGSGPU | —Unverified | 0 |
| Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition | Dec 23, 2024 | GPUMotion Synthesis | —Unverified | 0 |
| Resource-Aware Arabic LLM Creation: Model Adaptation, Integration, and Multi-Domain Testing | Dec 23, 2024 | ArabicMMLUDialect Identification | CodeCode Available | 1 |
| Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry Locality | Dec 21, 2024 | GPU | CodeCode Available | 1 |
| Lillama: Large Language Models Compression via Low-Rank Feature Distillation | Dec 21, 2024 | GPUMamba | —Unverified | 0 |
| Less is More: Towards Green Code Large Language Models via Unified Structural Pruning | Dec 20, 2024 | Computational EfficiencyGPU | —Unverified | 0 |
| WebLLM: A High-Performance In-Browser LLM Inference Engine | Dec 20, 2024 | CPUGPU | CodeCode Available | 11 |
| CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up | Dec 20, 2024 | 8kGPU | CodeCode Available | 3 |
| MUSTER: Longitudinal Deformable Registration by Composition of Consecutive Deformations | Dec 19, 2024 | GPUImage Registration | CodeCode Available | 0 |
| Taming the Memory Beast: Strategies for Reliable ML Training on Kubernetes | Dec 19, 2024 | GPUManagement | —Unverified | 0 |
| IDOL: Instant Photorealistic 3D Human Creation from a Single Image | Dec 19, 2024 | GPU | —Unverified | 0 |
| SqueezeMe: Efficient Gaussian Avatars for VR | Dec 19, 2024 | DecoderGPU | —Unverified | 0 |
| HashAttention: Semantic Sparsity for Faster Inference | Dec 19, 2024 | GPUSemantic Similarity | —Unverified | 0 |
| DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation | Dec 19, 2024 | 3D GenerationDenoising | —Unverified | 0 |
| Channel Merging: Preserving Specialization for Merged Experts | Dec 18, 2024 | Code GenerationGPU | —Unverified | 0 |
| Language verY Rare for All | Dec 18, 2024 | AllDecoder | —Unverified | 0 |
| Comparative Analysis of YOLOv9, YOLOv10 and RT-DETR for Real-Time Weed Detection | Dec 18, 2024 | CPUGPU | —Unverified | 0 |