5 papers
TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH
Yu-Han Huang, Yujia Wu, Vincent S. Tseng
Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active. In time-se…
Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI Agents
Yi-Cheng Lin, Yu-Kai Guo, Szu-Chi Chen +15
AI agents can now solve problems, answer like subject experts, and generate long-form multimodal content. However, whether they can adapt a lesson to fit a specified learner, which…
Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models
Yu-Han Huang, Chih-Kai Yang, Ke-Han Lu +2
Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content…
How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang +13
Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-…
TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild
Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou +9
Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we intro…