On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “multi-scenario”

Multi-scenario deep learning for multi-speaker source separationcs.LG

Single model performs well across different speaker scenarios.

problem Limited research on multi-scenario deep learning for multi-speaker separation.

method Combining data from different speaker scenarios into a single model.

result Single model outperforms scenario-specific models.

deep learning multi-speaker source separation multi-scenario speaker scenarios

2018-08-24abs ↗pdf ↗

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Expertscs.LG

Automates GPU kernel optimization for diverse applications.

problem Lack of systematic evaluation for multi-scenario GPU kernel optimization.

method Introduces MSKernelBench and CUDAMaster for automated optimization.

result Significant speedups across various operators, outperforming existing tools.

GPU optimization Kernel optimization LLM-driven Benchmarking CUDA

2026-03-07abs ↗pdf ↗