2 papers
cs.SD2026
MMAE: A Massive Multitask Audio Editing Benchmark
Ziyang Ma, Ruiqi Yan, Ruiyang Xu +35
We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.…
cs.SE2025
Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation
Xinkai Zou, Yan Liu, Xiongbo Shi +1
As requirements drift with rapid iterations, agile development becomes the dominant paradigm. Goal-driven Requirements Elicitation (RE) is a pivotal yet challenging task in agile p…