Publications

Last updated: October 2026. Latest papers: Google Scholar
‡ indicating corresponding author; * indicating equal contribution.

(Co-)First

• Qiyu Wu, Shuyang Cui, Satoshi Hayakawa, Wei-Yao Wang, Hiromi Wakaki, Yuki Mitsufuji. “MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval”, EMNLP 2026 Main, Oral.
• Qiyu Wu, Mengjie Zhao, Yutong He, Lang Huang, Junya Ono, Hiromi Wakaki, Yuki Mitsufuji. “Towards Reporting Bias in Visual-language Datasets: Bi-modal Data Augmentation by Decoupling Object-attribute Association”, ICCV 2025 Workshop on Multimodal Representation and Retrieval.
• Qiyu Wu, Masaaki Nagata, Zhongtao Miao, Yoshimasa Tsuruoka. “Word Alignment as Preference for Machine Translation”, EMNLP 2024 Main, Oral.
• Qiyu Wu, Zilong Wu, Yoshimasa Tsuruoka. “SGA: Scene Graph Alignment for Evaluation of Text-to-Image Generation”, KDD 2024 Workshop HI-AI.
• Kaiyan Zhao*, Qiyu Wu*, Xin-Qiang Cai, Yoshimasa Tsuruoka. “Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding”, EACL 2024 Main.
• Qiyu Wu, Masaaki Nagata, Yoshimasa Tsuruoka. “WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction”, ACL 2023 Main.
• Qiyu Wu, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng and Daxin Jiang. “PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings”, EMNLP 2022 Main.
• Qiyu Wu*, Chen Xing*, Yatao Li, Guolin Ke, Di He and Tie-Yan Liu. “Taking Notes on the Fly Helps Language Pre-Training”, ICLR 2021.
• Hao Liu*, Qiyu Wu*, Fuzhen Zhuang, Xinjiang Lu, Dejing Dou and Hui Xiong. “Community-Aware Multi-Task Transportation Demand Prediction”, AAAI 2021.
• Dechuan Yang*, Qiyu Wu*, Wei Chen, Tengjiao Wang, Zhen Qiu, Di Liu and Yingbao Cui. “Stance Detection with Stance-Wise Convolution Network”, NLPCC 2020.

Advised Research

• Dominick Reilly, Qiyu Wu‡, Hiromi Wakaki, Srijan Das, Yuki Mitsufuji. “Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing”, NeurIPS 2026.
• Jongsuk Kim, Qiyu Wu‡, Zhuoyuan Mao, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji. “MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations”, EMNLP 2026 Main.
• Youngtaek Oh, Qiyu Wu‡, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji. “Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings”, EMNLP 2026 Findings. [Code]
• Daeyong Kwon, Qiyu Wu‡, Shinobu Kuriya, Junghyun Koo, Shuyang Cui, Zhi Zhong, Wei-Hsiang Liao, Hiromi Wakaki, Yuki Mitsufuji. “MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs”, Manuscript (2026). [Project] [Code] [Data]
• Zhongtao Miao, Qiyu Wu, Yoshimasa Tsuruoka. “GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression”, Manuscript (2026).
• Zhongtao Miao, Qiyu Wu, Masaaki Nagata, and Yoshimasa Tsuruoka. “Improving Word Alignment Using Semi-Supervised Learning”, ACL 2025 Findings.
• Kaiyan Zhao, Qiyu Wu, Zhongtao Miao, Yoshimasa Tsuruoka. “Prompt Tuning Can Simply Adapt Large Language Models to Text Encoders”, RepL4NLP 2025.
• Zhongtao Miao, Qiyu Wu, Kaiyan Zhao, Zilong Wu, Yoshimasa Tsuruoka. “Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment”, NAACL 2024 Findings.
• Yutao Xie, Qiyu Wu, Wei Chen and Tengjiao Wang. “Stable Contrastive Learning for Self-Supervised Sentence Embeddings With Pseudo-Siamese Mutual Learning”, IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) 30 (2022): 3046-3059.

Collaborative

• Ce Zhang, Ziyang Wang, Yulu Pan, Oluwatumininu Oguntola, Pranav Wagh, Qiyu Wu, Hiromi Wakaki, Mohit Bansal, Gedas Bertasius. “Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA”, NeurIPS 2026. [Code] [Data]
• Silin Gao, Hao Zhao, Zeming Chen, Sepideh Mamooler, Antara Raaghavi Bhattacharya, Qiyu Wu, Hiromi Wakaki, Yuki Mitsufuji, Li Mi, Syrielle Montariol, Antoine Bosselut. “DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics”, ICML 2026. [Code]
• Shaomu Tan, Ryosuke Mitani, Ritvik Choudhary, Qiyu Wu, Toshiyuki Sekiya, Christof Monz. “Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations”, ACL 2026. [Code]
• Shuyang Cui, Zhi Zhong, Qiyu Wu, Zachary Novack, et al. “BREAK-THE-BEAT! Controllable MIDI-to-Drum Audio Synthesis”, ICASSP 2026. [Demo]
• Seungheon Doh, Junghyun Koo, Marco A Martinez-Ramirez, Woosung Choi, Wei-Hsiang Liao, Qiyu Wu, Juhan Nam, Yuki Mitsufuji. “LLM2Fx-Tools: Tool Calling For Music Post-Production”, ICLR 2026. [Code] [Demo]
• Wei-Yao Wang, Kazuya Tateishi, Qiyu Wu, Shusuke Takahashi, Yuki Mitsufuji. “VIRTUE: Visual-Interactive Text-Image Universal Embedder”, ICLR 2026. [Code] [Data] [Project]
• Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu, Hiromi Wakaki, Yuki Mitsufuji. “DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning”, EMNLP 2025 Main. [Code]
• Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu, Zhi Zhong, Wei-Hsiang Liao, Hiromi Wakaki, Yuki Mitsufuji. “Cross-Modal Learning for Music-to-Music-Video Description Generation”, RepL4NLP 2025.
• Yuting Tang, Xin-Qiang Cai, Yao-Xiang Ding, Qiyu Wu, Guoqing Liu, Masashi Sugiyama. “Reinforcement Learning from Bagged Reward”, Transactions on Machine Learning Research (2025); ICML 2026 Poster Track.
• Guangyi Liu, Yu Wang, Zeyu Feng, Qiyu Wu, Liping Tang, Yuan Gao, Zhen Li, Shuguang Cui, Julian McAuley, Eric P. Xing, Zichao Yang, Zhiting Hu. “Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding”, ICML 2024.
• Shiwen Wu, Qiyu Wu, Honghua Dong, Wen Hua, Xiaofang Zhou. “Blocker and Matcher Can Mutually Benefit: A Co-Learning Framework for Low-Resource Entity Resolution”, VLDB 2024 Research Track.