Han Zhou

PhD student in NLP

University of Cambridge

Biography

I am a final-year PhD student in Computation, Cognition, and Language (NLP) at Language Technology Lab, University of Cambridge. I am supervised by Prof. Anna Korhonen and Dr. Ivan Vulić. Currently, I am an AI Scientist Intern in the Reasoning team in Mistral AI. Previously, I interned as a Student Researcher at Google DeepMind, Google Cloud AI Research, and Google Research.

I am always interested in modular and reward-driven intelligence. I am open to full-time Research Scientist roles.

Featured Publications

Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Rajarishi Sinha, Sercan Ö. Arık

September, 2025 arXiv preprint arXiv:2509.10704

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration

Self-evolving T2I through iterative evolution of prompts.

Yi Xu, Chengzu Li, Han Zhou, Xingchen Wan, Caiqi Zhang, Anna Korhonen, Ivan Vulić

May, 2025 arXiv preprint arXiv:2505.11409

Visual Planning: Let's Think Only with Images

Visual Planning enables thinking through purely visual representations, independent of text.

Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, Sercan Ö. Arık

February, 2025 arXiv preprint arXiv:2502.02533

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Automatic multi-agent design via joint prompt and topology optimization.

Xingchen Wan, Han Zhou, Ruoxi Sun, Sercan Ö. Arık

February, 2025 International Conference on Learning Representations (ICLR)

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Self-improving reasoners taking advantage of long-context capabilities (ICLR 2025)

Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy

January, 2024 International Conference on Learning Representations (ICLR)

Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

Mitigating prompt biases and unifying existing calibration approaches without labeled data.

Publications

Quickly discover relevant content by filtering publications.

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen (2025). Agentic Policy Optimization via Instruction-Policy Co-Evolution. arXiv preprint arXiv:2512.01945.

PDF Cite Abstract

Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Rajarishi Sinha, Sercan Ö. Arık (2025). Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration. arXiv preprint arXiv:2509.10704.

PDF Cite Abstract

Yi Xu, Chengzu Li, Han Zhou, Xingchen Wan, Caiqi Zhang, Anna Korhonen, Ivan Vulić (2025). Visual Planning: Let's Think Only with Images. arXiv preprint arXiv:2505.11409.

PDF Cite Abstract

Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, Sercan Ö. Arık (2025). Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies. arXiv preprint arXiv:2502.02533.

PDF Cite Abstract

Xingchen Wan, Han Zhou, Ruoxi Sun, Sercan Ö. Arık (2025). From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation. International Conference on Learning Representations (ICLR).

PDF Cite Abstract OpenReview

Han Zhou, Xingchen Wan, Yinhong Liu, Nigel Collier, Ivan Vulić, Anna Korhonen (2024). Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Cite Code Abstract ACL Anthology

Chengzu Li, Caiqi Zhang, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulić (2024). TopViewRS: Vision-Language Models as Top-View Spatial Reasoners. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Cite Code Abstract Project Page ACL Anthology

Yinhong Liu, Han Zhou, Zhijiang Guo, Ehsan Shareghi, Ivan Vulić, Anna Korhonen, Nigel Collier (2024). Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators. The First Conference on Language Modeling (COLM).

PDF Cite Code Abstract OpenReview

Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy (2024). Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering. International Conference on Learning Representations (ICLR).

PDF Cite Abstract (Google Research) OpenReview Blog (Google AI) Talk (NeurIPS Spotlight)

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen (2024). AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning. Transactions of the Association for Computational Linguistics (TACL).

PDF Cite Code Abstract MIT Press ACL Anthology

Chengzu Li, Han Zhou, Goran Glavaš, Anna Korhonen, Ivan Vulić (2023). Large Language Models are Miscalibrated In-Context Learners. Findings of the Association for Computational Linguistics (ACL 2025).

PDF Cite Code Abstract OpenReview

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen (2023). Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning. Findings of the Association for Computational Linguistics (EMNLP).

PDF Cite Code Abstract OpenReview ACL Anthology

Songbo Hu, Han Zhou, Zhangdie Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić (2023). A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Cite Code Abstract OpenReview ACL Anthology

Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen (2023). Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems. Transactions of the Association for Computational Linguistics (TACL).

PDF Cite Dataset Abstract MIT Press ACL Anthology

Han Zhou, Ignacio Iacobacci, Pasquale Minervini (2023). XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking. Findings of the Association for Computational Linguistics (EACL).

PDF Cite Code Abstract ACL Anthology