4 papers
What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities
Hua-Hsuan Chen, Xuanjun Chen, Wei-Chung Lu +5
Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvements may reflect adaptation to s…
MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses
Xuanjun Chen, Hua-Hsuan Chen, Wei-Chung Lu +3
Rapid progress in Large Language Models (LLMs) is saturating static benchmarks faster than they can be designed. While existing automated evolution frameworks attempt to generate h…
Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech
Xuanjun Chen, Yun-Shing Wu, Wei-Chung Lu +4
Recent neural audio codec-based speech generation (CodecFake) produces highly realistic audio, posing a challenge to existing deepfake countermeasure models. While using codec resy…
OmniCode: A Benchmark for Evaluating Software Engineering Agents
Atharv Sonwane, Eng-Shen Tu, Wei-Chung Lu +11
LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require challenging benchmarks that can rigoro…