| FlowR: Flowing from Sparse to Dense 3D Reconstructions | Apr 2, 2025 | GPUNovel View Synthesis | —Unverified | 0 |
| A Truncated Newton Method for Optimal Transport | Apr 2, 2025 | GPU | CodeCode Available | 0 |
| Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries | Apr 2, 2025 | BenchmarkingComputational Efficiency | —Unverified | 0 |
| SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching | Apr 1, 2025 | Computational EfficiencyCPU | —Unverified | 0 |
| SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Models | Apr 1, 2025 | CPUGPU | —Unverified | 0 |
| Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources | Apr 1, 2025 | GPULarge Language Model | —Unverified | 0 |
| Adapting Vision Foundation Models for Real-time Ultrasound Image Segmentation | Mar 31, 2025 | GPUImage Segmentation | —Unverified | 0 |
| Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables | Mar 31, 2025 | 8kComputational Efficiency | —Unverified | 0 |
| Orchestrate Multimodal Data with Batch Post-Balancing to Accelerate Multimodal Large Language Model Training | Mar 31, 2025 | GPULanguage Modeling | —Unverified | 0 |
| StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting | Mar 31, 2025 | 3DGSGPU | —Unverified | 0 |
