Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

Published in Conference on Neural Information Processing Systems (NeurIPS 2026), to appear, 2026

A prior-free framework that formulates multiphase powder X-ray diffraction analysis as set prediction, jointly decomposing mixtures and identifying their constituent phases without candidate phase lists or templates.

Recommended citation: Hanyu Gao, Bin Cao, Yunyue Su, Tong-Yi Zhang, Qiang Liu. (2026). "XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction." Conference on Neural Information Processing Systems (NeurIPS), to appear.
Download Paper

Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update

Published in Findings of the Association for Computational Linguistics: EMNLP 2026, 2026

A two-turn evaluation framework that separates unsupported yielding from rational updating, showing that anti-sycophancy methods often reduce one at the cost of the other.

Recommended citation: Huanhuan Ma, Henry Peng Zou, Chengze Li, Enze Ma, Yunyue Su, Philip S. Yu. (2026). "Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update." Findings of the Association for Computational Linguistics: EMNLP 2026, pp. 25499-25515.
Download Paper

SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data

Published in International Conference on Learning Representations (ICLR 2026), 2026

A large language model that performs end-to-end molecular structure elucidation by reasoning over one or multiple spectra (IR, Raman, UV-Vis, NMR and MS) in a shared language space.

Recommended citation: Yunyue Su, Jiahui Chen, Zao Jiang, Zhenyi Zhong, Liang Wang, Qiang Liu, Zhaoxiang Zhang. (2026). "SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data." International Conference on Learning Representations (ICLR), pp. 25079-25117.
Download Paper

ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models

Published in International Conference on Learning Representations (ICLR 2026), 2026

A generative tool learning framework that encodes tools into hierarchical code sequences, so that vocabulary growth is logarithmic in the number of tools and the LLM can learn collaborative tool relationships.

Recommended citation: Bowen Fang, Wen Ye, Yunyue Su, Jinghao Zhang, Qiang Liu, Yesheng Liu, Xin Sun, Shu Wu, Jiabing Yang, Baole Wei, Liang Wang. (2026). "ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models." International Conference on Learning Representations (ICLR), pp. 90654-90684.
Download Paper

Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization

Published in Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Enables LLMs to call large-scale toolkits (over 47,000 tools) by unifying tool representation, retrieval and calling in a single generative process, using structure-aware semantic tokenization and post-guided iterative training.

Recommended citation: Yunyue Su, Zhang Jinshuai, Bowen Fang, Wen Ye, Jinghao Zhang, Bowen Song, Weiqiang Wang, Qiang Liu, Liang Wang. (2025). "Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization." Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 556-578.
Download Paper

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation

Published in Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

A plug-and-play multi-agent system that optimizes text-to-image prompts at test time through error analysis, clustering-based adaptive exploration and fine-grained verification.

Recommended citation: Wen Ye, Zhaocheng Liu, Yuwei Gui, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang. (2025). "GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation." Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 929-958.
Download Paper

A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction

Published in Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), 2023

Uses separate encoders for event detection and argument extraction, bridged by joint training, to reduce feature interference between the two subtasks. (* Equal contribution)

Recommended citation: Ge Shi*, Yunyue Su*, Yongliang Ma, Ming Zhou. (2023). "A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction." Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 3163-3180.
Download Paper

Journal Articles

GraphFM: Graph Factorization Machines for Feature Interaction Modelling

Published in Machine Intelligence Research, 2025

Integrates graph neural networks into factorization machines, modelling feature interactions from a graph perspective to capture high-order interactions while filtering out noisy ones.

Recommended citation: Shu Wu, Zekun Li, Yunyue Su, Zeyu Cui, Xiaoyu Zhang, Liang Wang. (2025). "GraphFM: Graph Factorization Machines for Feature Interaction Modelling." Machine Intelligence Research, 22(2), 239-253.
Download Paper