collaborators

12 papers

cs.AI2025

Long Term Memory: The Foundation of AI Self-Evolution

Xun Jiang, Feng Li, Han Zhao +12

Large language models (LLMs) like GPTs, trained on vast datasets, have demonstrated impressive capabilities in language understanding, reasoning, and planning, achieving human-leve…

cs.CL2025

Delusions of Large Language Models

Hongshen Xu, Zixv yang, Zichen Zhu +7

Large Language Models often generate factually incorrect but plausible outputs, known as hallucinations. We identify a more insidious phenomenon, LLM delusion, defined as high beli…

cs.SD2024

SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound

Haohe Liu, Xuenan Xu, Yi Yuan +3

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelli…

eess.AS2024

Unified Pathological Speech Analysis with Prompt Tuning

Fei Yang, Xuenan Xu, Mengyue Wu +1

Pathological speech analysis has been of interest in the detection of certain diseases like depression and Alzheimer's disease and attracts much interest from researchers. However,…

cs.SD2024

Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning

Luoyi Sun, Xuenan Xu, Mengyue Wu +1

Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learn…

cs.SD2024

DiveSound: LLM-Assisted Automatic Taxonomy Construction for Diverse Audio Generation

Baihan Li, Zeyu Xie, Xuenan Xu +5

Audio generation has attracted significant attention. Despite remarkable enhancement in audio quality, existing models overlook diversity evaluation. This is partially due to the l…