Hung-yi Lee

2 articles on SOTA Papers

TurnBench Exposes Turn-Taking Failures Across Conversation Types

A 30-hour triple-annotated benchmark separates end-of-turn and interruption decisions, showing that low-latency interruption detection still produces excessive false positives.

Aug 27, 20264 min2608.25218

Audio LLM Feedback Improves Text-to-Audio Instruction Following

ALLM-judged DPO turns event-presence and temporal-order checks into preferences, raising AudioCaps-test joint accuracy to 71.0% from 67.4%.

Jul 28, 20265 min2607.13408