News

One paper accepted to NeurIPS 2026.

• Zhaomin Wu, Jiayi Li, and Bingsheng He. EmoTrack: Clinical-Semantic Modeling for Text-Based Depression Severity Estimation

Two papers accepted to EMNLP 2026 Findings.

• Haodong Zhao, Jidong Li, Zhaomin Wu†, Tianjie Ju, Zhuosheng Zhang, Bingsheng He, Gongshen Liu†. Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion
• Qian Wang, Zhongyi Tong, Nuo Chen, Zhaomin Wu, Bingsheng He. CrossAlpha: An Annual-Report Benchmark for Cross-Market Factor Research

Invited talk: “Managing Data and Model Silos for Real-World AI Systems” at Hong Kong Baptist University.

I received the ICML 2026 Gold Reviewer Award (top 25% of reviewers).

Invited talk: “When Data and Models Stay Hidden: Toward Trustworthy AI Collaboration” at Université de Montréal (UdeM) and Mila.

I received the Google Cloud Research Credit Award to support my research.

I received the NRF Postdoctoral Award to support my research on AI-powered psychological counselling systems.

One paper accepted to ICDE 2026.

• Zhaomin Wu*, Ziyang Wang*, Bingsheng He. WikiDBGraph: A Data Management Benchmark Suite for Collaborative Learning over Database Silos

Two papers accepted to ICLR 2026 for Oral Presentation (1%).

• [Oral] Zhaomin Wu, Haodong Zhao, Ziyang Wang, Jizhou Guo, Qian Wang, Bingsheng He. LLM DNA: Tracing Model Evolution via Functional Representations
• [Oral] Zhaomin Wu, Mingzhe Du, Ng See-Kiong, Bingsheng He. Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts

Keynote: “Bridging Data Silos with Practical Federated Learning” at the AAAI 2026 FLCA Workshop.

One paper accepted to WWW 2026 (Oral).

• Yicheng Zhang, Zhen Qin, Zhaomin Wu, Jian Hou, Shuiguang Deng. Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures.

One paper accepted to KDD 2026.

• Jizhou Guo, Zhaomin Wu, Hanchen Yang, Philip S. Yu. Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling

One paper accepted to EMNLP 2025.

• Zhaomin Wu*, Jizhou Guo*, Junyi Hou, Bingsheng He, Lixin Fan, Qiang Yang. Model-based Large Language Model Customization as Service

Invited talk: “Towards Practical Vertical Federated Learning Systems” at DASFAA 2025 Trust Day, on behalf of Prof. Bingsheng He.

One paper accepted to ACL 2025.

• Zhen Qin, Zhaomin Wu, Bingsheng He, Shuiguang Deng. Federated Data-Efficient Instruction Tuning for Large Language Models.

Invited talk: “Bridging Private Data Silo with Machine Learning” at NUS Open House 2025.

I received the Best Research Staff Award from the NUS Institute of Data Science.

One paper accepted to NeurIPS 2024.

• Zhaomin Wu, Junyi Hou, Yiqun Diao, and Bingsheng He. Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data

I received an Honorable Mention for the Best Ph.D. Thesis Award from the NUS School of Computing.

Our paper “DeltaBoost: Gradient Boosted Trees with Efficient Machine Unlearning” received the Honorable Mention for Best Artifact at SIGMOD 2023.

I passed my Ph.D. defense.

One paper accepted to ICLR 2024.

• Zhaomin Wu, Junyi Hou, Bingsheng He. VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks

I received the Dean’s Graduate Research Excellence Award from the NUS School of Computing for 2022/2023.