Dujian Ding

Research Scientist at Meta Superintelligence Lab.

I am interested in making AI accessible to everyone.

Resume | Github | Google-Scholar | DBLP| LinkedIn | Contact

Recent Papers

1. ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries
   Keke Huang, Yimin Shi, Dujian Ding, Yifei Li, Yang Fei, Laks V.S. Lakshmanan, Xiaokui Xiao
   51st International Conference on Very Large Data Bases (VLDB), 2025
2. Navigating the Prompt Space: Supervision Matters in CoT When Reasoning Misleads
   Xiang Zhang, Juntai Cao, Chenyu You, Dujian Ding
   The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
3. BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
   Dujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang, Daniel Madrigal, Mirian Del Carmen Hipolito Garcia, Menglin Xia, Laks V.S. Lakshmanan, Qingyun Wu, Victor Rühle
   Forty-Second International Conference on Machine Learning (ICML), 2025
4. EcoAct: Economic Agent Determines When to Register What Action
   Shaokun Zhang, Jieyu Zhang, Dujian Ding, Mirian Del Carmen Hipolito Garcia, Ankur Mallick, Daniel Madrigal, Menglin Xia, Victor Rühle, Qingyun Wu, Chi Wang
   Reasoning and Planning for LLMs Workshop @ ICLR, 2025
5. OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference
   Dujian Ding, Bicheng Xu, Laks V.S. Lakshmanan
   The Thirteenth International Conference on Learning Representations (ICLR), 2025
6. Pruning Attention Heads with Almost-sure Sparsity Targets
   Dujian Ding, Ganesh Jawahar, Laks V.S. Lakshmanan
   Transactions on Machine Learning Research (TMLR), 2024
7. LLM Performance Predictors are good initializers for Architecture Search
   Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan, Dujian Ding
   Findings of the Association for Computational Linguistics (ACL), 2024
8. Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
   Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V.S. Lakshmanan, Ahmed Hassan Awadallah
   The Twelfth International Conference on Learning Representations (ICLR), 2024
9. On Efficient Approximate Queries over Machine Learning Models (paper, code)
   Dujian Ding, Sihem Amer-Yahia, Laks V.S. Lakshmanan
   49th International Conference on Very Large Data Bases (VLDB), 2023
10. Uncovering the subtype-specific temporal order of cancer pathway dysregulation (paper, code)
    Sahand Khakabimamaghani, Dujian Ding, Oliver Snow, Martin Ester
    PLOS Computational Biology, 2019
11. Collaborative Intra-tumor Heterogeneity Detection (paper, code)
    Sahand Khakabimamaghani, Salem Malikic, Jeffrey Tang, Dujian Ding, Ryan Morin, Leonid Chindelevitch, Martin Ester
    Bioinformatics, 2019