Hung-yi Lee

CUEES (Correlation-gUided Encoder Selection), a lightweight heuristic that estimates complementarity through task- and category-level Pearson correlations between encoders'performance profiles, scoring a candidate set from single-encoder evaluations alone--without fusion training during selection.

AudioICL-Bench is introduced, a diagnostic benchmark whose per-episode rules are resampled so that no correct answer is recoverable from prior knowledge, and its nine tasks are organized along two axes that separate what must be learned from demonstrations from what must be perceived in the signal, enabling failures to be attributed to either source.

The first systematic characterization of explicit paralinguistic control in a TASTE based model is provided, which establishes TASTE based modeling as a practical route toward full-duplex systems while identifying natural conversation robustness, speech generation latency, and feature general paralinguistic control as open challenges.

TurnBench reveals that human-like turn-taking in dialogue remains elusive for AI, with systems struggling to balance accuracy and false positives in interruption detection.

Jointly training tool creation and use allows LLMs to achieve unprecedented accuracy on procedural reasoning tasks, outperforming larger models and enhancing smaller ones.

Speech quality assessment is skewed: male listeners consistently give higher scores than female listeners, and standard MOS models learn and perpetuate this bias.