Daliang Xu — accepted AI-conference papers

2026

MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs

Zhenyan Lu, Daliang Xu, Dongqi Cai, Zexi Li, Wei Liu, Jian Luan +3

ICLR 2026poster

Large language models (LLMs) are deployed on mobile devices to power killer applications such as intelligent assistants. LLMs pre-trained on general corpora often hallucinate when handling personalized or unseen queries, leading to incorrect or outdated responses. Knowledge editing addresses this b…

Cited by 0 Source ↗code ↗Scholar ↗

2026

NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies

Zhiyang Chen, Daliang Xu, Yinyuan Zhang, Chenghua Wang, Mengwei Xu, Yun Ma

ICML 2026poster

The massive vocabulary sizes of large language models, often exceeding 100k tokens, impose a computational bottleneck on the final linear projection layer during speculative decoding. Existing vocabulary pruning solutions rely on static or coarsely-grained sub-vocabularies that necessitate large act…

Cited by 0 Source ↗Scholar ↗