spacehunterinf.github.io Open in urlscan Pro
2606:50c0:8001::153  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Toggle navigation
 * about (current)
 * blog
 * publications
 * projects
 * repositories
 * cv
 * teaching
 * people
 * submenus
   publications
   
   projects
   
   blog
 * ctrl k
 * 




XIAOCHEN ZHU

University of Cambridge. GS06 William Gates Building. xz479 [at] cam [dot] ac
[dot] uk. I can hear Gaussian noise.

Greetings!

I am Xiaochen Zhu, PhD student in Computer Science at the University of
Cambridge, working under the supervision of Prof. Andreas Vlachos. My research
focuses on natural language processing, particularly large language models and
dialogue systems. My current projects covers diffusion for controllable dialogue
generation, multi-party dialogues, and computational social science
(Deliberation for better collective decision).


SELECTED PUBLICATIONS

 1. Segment-Level Diffusion: A Framework for Controllable Long-Form Generation
    with Diffusion Language Models
    Xiaochen Zhu, Georgi Karadzhov, Chenxi Whitehouse, and 1 more author
    arXiv preprint arXiv:2412.11333, 2024
    
    
 2. Conformity in Large Language Models
    Xiaochen Zhu, Caiqi Zhang, Tom Stafford, and 2 more authors
    arXiv preprint arXiv:2410.12428, 2024
    
    
 3. ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
    Qi Zhu, Christian Geishauser, Hsien-chin Lin, and 11 more authors
    In Proceedings of the 2023 Conference on Empirical Methods in Natural
    Language Processing: System Demonstrations, Dec 2023
    
    Abs DOI
    
    Task-oriented dialogue (TOD) systems function as digital assistants, guiding
    users through various tasks such as booking flights or finding restaurants.
    Existing toolkits for building TOD systems often fall short in delivering
    comprehensive arrays of data, model, and experimental environments with a
    user-friendly experience. We introduce ConvLab-3: a multifaceted dialogue
    system toolkit crafted to bridge this gap. Our unified data format
    simplifies the integration of diverse datasets and models, significantly
    reducing complexity and cost for studying generalization and transfer.
    Enhanced with robust reinforcement learning (RL) tools, featuring a
    streamlined training process, in-depth evaluation tools, and a selection of
    user simulators, ConvLab-3 supports the rapid development and evaluation of
    robust dialogue policies. Through an extensive study, we demonstrate the
    efficacy of transfer learning and RL and showcase that ConvLab-3 is not only
    a powerful tool for seasoned researchers but also an accessible platform for
    newcomers.

 4. Speaking with our Sources— The Possibilities and Pitfalls of AI Language
    Models in Historical Research
    Jacob Forward, and Xiaochen Zhu
    PASSPORT THE SOCIETY FOR HISTORIANS OF AMERICAN FOREIGN RELATIONS REVIEW,
    Sep 2023
    
    


© Copyright 2024 Xiaochen Zhu. Powered by Jekyll with al-folio theme. Hosted by
GitHub Pages. Photos from Unsplash.