← Search

Xingjian Zhao

2 accepted papers

2026

Towards True Speech-to-Speech Models Without Text Guidance

ICLR 2026poster

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and better preserve these cues, yet still rely on text intermediates…

Cited by 0SourcecodeScholar
2024

L-Eval: Instituting Standardized Evaluation for Long Context Language Models

ACL 2024long

Recently, there has been growing interest in long-context scaling of large language models (LLMs). To facilitate research in this field, we propose L-Eval to institute a more standardized evaluation for Long-Context Language Models (LCLMs) addressing two key aspects: dataset construction and evaluat…