Xixiang He

Xixiang He

National University of Defense Technology

About Me

I am a Ph.D. student (Sep. 2022 – present) at the National University of Defense Technology (NUDT), jointly trained with the Intelligent Game and Decision Lab (IGDL), where I am fortunate to work with Prof. Qingyong Hu. I received my Bachelor's degree from NUDT in 2022. My work is on large language models and their post-training.

My research is about making large models more efficient and more reliable: which data is worth fine-tuning on, why reinforcement learning for reasoning collapses and how to fix it, how to tell when a model is hallucinating, and how well multimodal models actually reason rather than pattern-match. Recently I have been especially interested in distillation and multi-teacher supervision for multi-domain LLMs.

I am always glad to talk about research or collaboration — feel free to reach out by email.
Research Interests
📊 Data-Centric Post-Training 🎯 RL for LLM Reasoning 🧪 Knowledge Distillation 🔍 Trustworthy LLMs 👁️ Multimodal Reasoning

🔥 News

  • 2026.09:  🔥🔥 MT-SDPO is released on arXiv, together with the SciKnowEval-L3 data, training code and evaluation protocol.

  • 2026.05:  🔥🔥 StemBind is released on arXiv, with a project page and public leaderboard.

  • 2026.05:  🎉🎉 AVSPO is accepted by ICML 2026.

  • 2026.04:  🎉🎉 CALRD is accepted by IJCAI-ECAI 2026.

  • 2026.02:  🎉🎉 ENC-Bench is accepted by CVPR 2026 as a Highlight.

  • 2025.11:  🎉🎉 Efficient Hallucination Detection is accepted by AAAI 2026 as an Oral.

  • 2025.03:  🎉🎉 TACOS is accepted by ICME 2025.

📝 Publications

* denotes the corresponding author. Full list on Google Scholar.
  1. Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs
    Xixiang He, Xingming Li, Baiqi Wu, Qiyao Sun, Xuanyu Ji, Ao Cheng, Qingyong Hu*
    Preprint arXiv preprint arXiv:2609.02548, 2026
    arXivCode
  2. StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning
    Xixiang He, Baiqi Wu, Xingming Li, Ao Cheng, Qiyao Sun, Xuanyu Ji, Qingyong Hu*
    Preprint arXiv preprint arXiv:2606.00148, 2026
    arXivProject Page
  3. Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
    Xixiang He, Qiyao Sun, Ao Cheng, Xingming Li, Xuanyu Ji, Hailun Lu, Runke Huang, Qingyong Hu*
    ICML 2026 International Conference on Machine Learning, 2026
    arXiv
  4. TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection
    Xixiang He, Hao Yu, Qiyao Sun, Ao Cheng, Tailai Zhang, Cong Liu, Shuxuan Guo*
    ICME 2025 IEEE International Conference on Multimedia and Expo, 2025
    arXiv
  5. ENC-Bench: A Benchmark for Evaluating Multimodal Large Language Models in Electronic Navigational Chart Understanding
    Ao Cheng, Xingming Li, Xuanyu Ji, Xixiang He, Qiyao Sun, Chunping Qiu, Runke Huang, Qingyong Hu*
    CVPR 2026 Highlight IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    arXivCode
  6. Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration
    Qiyao Sun, Xingming Li, Xixiang He, Ao Cheng, Xuanyu Ji, Hailun Lu, Runke Huang, Qingyong Hu*
    AAAI 2026 Oral AAAI Conference on Artificial Intelligence, 2026
    arXiv
  7. MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias
    Xingming Li, Ao Cheng, Qiyao Sun, Xixiang He, Xuanyu Ji, Runke Huang, Qingyong Hu*
    IJCAI-ECAI 2026 International Joint Conference on Artificial Intelligence, 2026
    Project Page

📖 Educations