[go: up one dir, main page]

Zixia Jia

prof_pic.jpg

I am a researcher at Beijing Institute for General Artificial Intelligence (BIGAI).

I received my Ph.D. degree from the School of Information Science and Technology at ShanghaiTech University, advised by Prof. Kewei Tu.

My research interests include:

  • natural language processing
  • embodied AI
  • information extraction
  • reasoning and reinforcement learning for language agents
  • value-based communication and cognitive-inspired AI

This website contains my latest publications and research news.
You can also find my profile on DBLP.

news

Mar 22, 2026 We released a new preprint: Make an Offer They Can’t Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment.
Jan 31, 2026 Our latest work The AI Hippocampus: How Far are We From Human Memory? is now available on TMLR (with arXiv version: 2601.09113).
Jan 26, 2026 We released a new preprint: BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts.
Jan 24, 2026 We released a new preprint: Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning.
Aug 20, 2025 Our three papers Context Faithfulness in MoE LLMs, Reinforced Query Reasoners, and Adaptive Preference Optimization were accepted to EMNLP 2025.

selected publications

2025

  1. jia2025aihippocampus.png
    TMLR
    The AI Hippocampus: How Far are We From Human Memory?
    Paper|Project Page
    Zixia Jia, Jiaqi Li, Yipeng Kang, and 12 more authors
    Transactions on Machine Learning Research, 2025
    HTML
  2. bai2025moefaithfulness.jpg
    EMNLP
    Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
    Paper|GitHub
    Jun Bai, Minghao Tong, Yang Liu, and 2 more authors
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
    Code
  3. qin2025rqr.jpg
    EMNLP
    Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks
    Paper|GitHub|Project Page
    Xubo Qin, Jun Bai, Jiaqi Li, and 2 more authors
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
    Code Website
  4. wang2025apo.jpg
    EMNLP-F
    Adaptive Preference Optimization with Uncertainty-aware Utility Anchor
    Paper
    Xiaobo Wang, Zixia Jia, Jiaqi Li, and 2 more authors
    In Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
  5. he2025offer.png
    arXiv
    Make an Offer They Can’t Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
    Paper
    Buwei He, Yang Liu, Zhaowei Zhang, and 5 more authors
    arXiv preprint arXiv:2510.13387, 2025
  6. lin2025look.jpg
    ACL
    Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training
    Paper
    Ziyong Lin, Haoyi Wu, Shu Wang, and 3 more authors
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025
  7. wu2025tokenswift.png
    ICML
    TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
    Paper|GitHub|Project Page
    Tong Wu, Junzhe Shen, Zixia Jia, and 2 more authors
    In Proceedings of the 42nd International Conference on Machine Learning, 2025
    Code Website

2024

  1. jia2024langsuite.jpg
    ACL-F
    LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments
    Paper|GitHub
    Zixia Jia, Mengmeng Wang, Baichen Tong, and 2 more authors
    In Findings of the Association for Computational Linguistics: ACL 2024, 2024
    Code

2023

  1. jia2023crfie.jpg
    ACL
    Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field
    Paper
    Zixia Jia, Zhaohui Yan, Wenjuan Han, and 2 more authors
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023