Publication

[1] SLM-Mod: Small Language Models Surpass LLMs at Content Moderation [PDF]
Xianyang Zhan*, Agam Goyal*, Yilun Chen, Eshwar Chandrasekharan, Koustuv Saha.
Accepted to NAACL 2025 Main Conference (Top 1.5% of the submission, Oral Presentation)

[2] MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance [PDF]
Agam Goyal, Xianyang Zhan, Yilun Chen, Koustuv Saha, Eshwar Chandrasekharan
Accepted to EMNLP 2025 Main Conference (Top 1% of the submission, Oral Presentation)

[3] Simulation Framework for Embodied Conversational Agents in Psychological Counseling [PDF]
Lixiu Wu*, Yuanrong Tang*, Qisen Pan, Xianyang Zhan, Yuchen Han, Lanxi Xiao, Tianhong Wang, Chen Zhong, Jiangtao Gong.
Accepted to AAAI 2026 Conference (Acceptance rate 17.6%)

[4] Large Language Model-based Data Science Agent: A Survey [PDF]
Peiran Wang*, Yaoning Yu*, Ke Chen*, Xianyang Zhan, Haohan Wang.
Accepted to TMLR Transactions on Machine Learning Research

[5] VASTU: Value-Aligned Social Toolkit for Online Content Curation [PDF]
Agam Goyal, Xianyang Zhan, Charlotte Lambert, Koustuv Saha, Eshwar Chandrasekharan.
Under Review

[6] MAGIC: Multi-Armed Bandit Guided Iterative Code Generation
Yaowenqi Liu, Xianyang Zhan, Yanli Wang, Kaidi Xu, Haohan Wang.
Under Review