Skip to content

Author

Yu-Jin Wang

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Nov 2026

The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory

This work investigates why irrelevant historical audio changes answers even when the queried event remains represented, and shows that source-role information can influence a decision without exclusively controlling which historical values affect it.

Hong-Jin Song, Weiqiao Shan, Run-Wu Shi et al. · 0 citations
Preprint Sep 2026

UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation

Text-to-audio (TTA) generation aims to synthesize realistic audio that faithfully reflects natural-language descriptions. Most TTA systems adopt a two-stage latent paradigm: an audio tokenizer is optimized for reconstruction and then frozen, after which a generative model is trained in the resulting latent space. Howev...

Run-Wu Shi, Kai Li, Yu-Jin Wang et al. · 0 citations
#natural language process... Preprint Sep 2026

Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models

This work provides a systematic analysis protocol for studying length-based training in variable-length speech models through matched comparisons, and results are consistent with a link between chunk-length variation and token weighting.

Hong-Jin Song, Run-Wu Shi, Weiqiao Shan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.