Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation
Under review at the International Conference on Learning Representations (ICLR 2027)
Publications
You can also find my articles on my Google Scholar profile.
Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness
Accepted at the Annual Conference on Neural Information Processing Systems (NeurIPS 2026)
ASSET: Acquisition-Sensitive Subspace Estimation for Test-Time Adaptation of Medical VLMs
Accepted at the Annual Conference on Neural Information Processing Systems (NeurIPS 2026)
CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation
Under review at the ACM Web Conference (WWW 2027)
ECLAD: An Edge-Cloud Collaborative Agentic Framework for Interpretable Anomaly Detection in Predictive Maintenance
Accepted at the ACM Web Conference (WWW 2026)
Training-Free Time Series Classification via In-Context Reasoning with LLM Agents
Under review at the ACM International Conference on Web Search and Data Mining (WSDM 2027)
Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration
Accepted at the Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL 2025, Oral Presentation)
LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting
Accepted for publication in ACM SIGKDD Explorations Newsletter (SIGKDD Explor. 2025)
Unleashing SmartNIC Packet Processing Performance in P4
Accepted at the Annual Conference of the ACM Special Interest Group on Data Communication (ACM SIGCOMM 2023)