| FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation | Jun 30, 2025 | Computational EfficiencyDataset Distillation | CodeCode Available | 1 |
| Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorch | Jun 25, 2025 | Computational EfficiencyGPR | CodeCode Available | 1 |
| Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking | Jun 25, 2025 | GPUVisual Tracking | CodeCode Available | 1 |
| DIP: Unsupervised Dense In-Context Post-training of Visual Representations | Jun 23, 2025 | GPUMeta-Learning | CodeCode Available | 1 |
| CommVQ: Commutative Vector Quantization for KV Cache Compression | Jun 23, 2025 | GPUGSM8K | CodeCode Available | 1 |
| ConsumerBench: Benchmarking Generative AI Applications on End-User Devices | Jun 21, 2025 | BenchmarkingCPU | CodeCode Available | 1 |
| Farseer: A Refined Scaling Law in Large Language Models | Jun 12, 2025 | GPU | CodeCode Available | 1 |
| Mutual-Supervised Learning for Sequential-to-Parallel Code Translation | Jun 11, 2025 | Code TranslationGPU | CodeCode Available | 1 |
| Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts | Jun 5, 2025 | GPUScheduling | CodeCode Available | 1 |
| Accelerating AllReduce with a Persistent Straggler | May 29, 2025 | GPU | CodeCode Available | 1 |
