activity
20242026
collaborators

6 papers

cs.CL2026

Locality Matters for Training-Free Audio Token Compression in Audio-Language Models

Jiale Luo, Xiaoyu Liang, Haoji Hu

Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio in…

cs.AI2026

Echo: Learning from Experience Data via User-Driven Refinement

Hande Dong, Xiaoyun Liang, Jiarui Yu +15

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions bet…

cs.LG2026

Reading Calibrated Uncertainty from Language Model Trajectories

Aliai Eusebi, Alexander Herzog, Xiaoyu Liang +3

The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with structured output. Although cheap,…

cs.IR2026

Learn Before Represent: Bridging Generative and Contrastive Learning for Domain-Specific LLM Embeddings

Xiaoyu Liang, Yuchen Peng, Jiale Luo +3

Large Language Models (LLMs) adapted via contrastive learning excel in general representation learning but struggle in vertical domains like chemistry and law, primarily due to a l…

cs.HC2025

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

Guangyi Liu, Pengxiang Zhao, Yaozhen Liang +17

With the rapid rise of large language models (LLMs), phone automation has undergone transformative changes. This paper systematically reviews LLM-driven phone GUI agents, highlight…

cs.CR2024

KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server

Wenhao Wang, Xiaoyu Liang, Rui Ye +3

The success of large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. However, this practice raises privacy concerns due to the memorizat…