| SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale | May 26, 2025 | Decision MakingGPU | —Unverified | 0 |
| APE: A Data-Centric Benchmark for Efficient LLM Adaptation in Text Summarization | May 26, 2025 | GPUNews Summarization | CodeCode Available | 0 |
| TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization | May 26, 2025 | CPUGPU | CodeCode Available | 1 |
| FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets | May 26, 2025 | BenchmarkingGPU | —Unverified | 0 |
| Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling | May 26, 2025 | GPUtext-to-speech | —Unverified | 0 |
| eACGM: Non-instrumented Performance Tracing and Anomaly Detection towards Machine Learning Systems | May 25, 2025 | Anomaly DetectionFault Diagnosis | —Unverified | 0 |
| TextDiffuser-RL: Efficient and Robust Text Layout Optimization for High-Fidelity Text-to-Image Synthesis | May 25, 2025 | CPUGPU | —Unverified | 0 |
| Triangle Splatting for Real-Time Radiance Field Rendering | May 25, 2025 | GPUNeRF | —Unverified | 0 |
| Advancing Video Self-Supervised Learning via Image Foundation Models | May 25, 2025 | GPURepresentation Learning | CodeCode Available | 0 |
| FastMamba: A High-Speed and Efficient Mamba Accelerator on FPGA with Accurate Quantization | May 25, 2025 | Computational EfficiencyCPU | —Unverified | 0 |
