Research Interests
π Information Retrieval
- βΈ LLM-based Generative Retrieval
- βΈ Multimodal Generative Retrieval
π¬ Conversational Recommendation Systems
- βΈ Query Reformulation
- βΈ Query Expansion
π€ Large Language Models
- βΈ Multimodal Large Language Models
- βΈ LLM Test-Time Scaling
πΈοΈ Graph Neural Networks
- βΈ Heterogeneous Graph Learning
- βΈ Graph-based RAG
π I am very familiar with the following new and notable papers that are highly relevant to my ongoing research on multimodal conversational retrieval
Multimodal Retrieval and Multimodal Generative Retrieval
- Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation (also known as AVG)Yongqi Li, Hongru Cai, Wang Wenjie, Leigang Qu, Yinwei Wei, Wenjie Li, Liqiang Nie, and Tat-Seng Chua. SIGIR 2025.
- SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMsHaoxuan Li, Yi Bin, Yunshan Ma, Guoyin Wang, Yang Yang, See-Kiong Ng, and Tat-Seng Chua. arXiv preprint (2025).
- Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond (also known as GRACE)Yongqi Li, Nan Yang, Liang Wang, Furu Wei, and Wenjie Li. ACL 2024.
Research Experience
Research Assistant, CFDA Lab, CITI, Academia Sinica Apr. 2024 - Present
- Leading the Information Retrieval (IR) research project in collaboration with NVIDIA Research (Taiwan and US) under the supervision of Prof. Chuan-Ju Wang and Prof. Ming-Feng Tsai. Focused on conversational retrieval and Multimodal-LLMs.
- Participated twice in NIST's Text Retrieval Conference (TREC) tracks starting from 2024: Product Recommendations and Interactive Knowledge Assistance (iKAT). Led and coordinated the competition teams with up to 6 direct reports.
Data Scientist Intern - R&D, Cathay Financial Holdings Feb. 2024 - Apr. 2024
- Developed an enterprise-level Chinese legal retrieval pipeline leveraging LangChain, increasing recall@50 performance from 23% to 39% compared to LangChain's basic two-staged retrieval settings through a novel legal articles pre-classification approach.
Research Assistant, SNAC Lab, CITI, Academia Sinica Sep. 2021 - Feb. 2024
- Developed novel GAN-based data augmentation frameworks for heterogeneous graphs, addressing critical node class imbalance issues in graph neural networks.
- Achieved 14.4% improvement in F-score and 12.3% in PR-AUC over SOTA baseline GraphSMOTE through innovative handling of structured graph G=(V,E,X). Published research in IEEE ICASSP with ongoing follow-up studies.
Peer Review Experiences
I have experience reviewing 15 manuscripts, including 14 conference papers and 1 journal paper:
- WWW 2026 - The ACM Web Conference 2026 (Nov 2025)
- ICLR 2026 - The 14th International Conference on Learning Representations (Oct 2025)
- ARR July 2025 - Association for Computational Linguistics Rolling Review July 2025 (Sep 2025)
- AAAI 2026 - The 40th Annual AAAI Conference on Artificial Intelligence (Sep 2025)
- NeurIPS 2025 - The 39th Conference on Neural Information Processing Systems (May 2025)
- CIKM 2025 - The 34th ACM International Conference on Information and Knowledge Management - short paper (May 2025)
- ARR May 2025 - Association for Computational Linguistics Rolling Review May 2025 (July 2025)
- IJCAI 2025 - The 34th International Joint Conference on Artificial Intelligence (Jan 2025)
- PAKDD 2025 - The 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining (Dec 2024)
- ICLR 2025 - The 13th International Conference on Learning Representations (Oct 2024)
- WWW 2025 - The ACM Web Conference 2025 (Oct 2024)
- AAAI 2025 - The 39th Annual AAAI Conference on Artificial Intelligence (Aug 2024)
- Knowledge-Based Systems, Elsevier (Jul 2024)
- NeurIPS 2024 - The 38th Conference on Neural Information Processing Systems (May 2024)