News

2026

• 2026.07: I am attending ICML in Seoul, South Korea.
  • I’ll be at the poster for our recent work on The Information Geometry of Softmax: Probing and Steering (w/ Kiho Park, Todd Nief, and Victor Veitch).
• 2026.07: I am attending the SAVI Conference at University of Twente.
  • With Sebastian Arnold, I will co-present our recent work on Betting on Bets: Anytime-Valid Tests for Stochastic Dominance.
• 2026.06: I am attending the INFORMS ADA Conference at Duke Fuqua.
  • I will present our OR paper on Comparing Sequential Forecasters, joint with Aaditya Ramdas, with a focus on the betting framework.
• 2026.06: I am attending the IMS New Researchers Conference Asia at HKU.
  • I will present our recent work on Betting on Bets: Anytime-Valid Tests for Stochastic Dominance.
• 2026.04: New preprint titled Betting on Bets: Anytime-Valid Tests for Stochastic Dominance is now available on arXiv! (paper page)
  • Joint with Sebastian Arnold (co-first author), Marco Scarsini, and Ilia Tsetlin.
  • This work develops a novel family of anytime-valid & powerful e-processes for testing stochastic dominance (in its various forms).
• 2026.04: I attended the EEO Workshop at Harvard Business School.
  • I presented our recent work on Betting on Bets: Anytime-Valid Tests for Stochastic Dominance.
• 2026.04: I was a panel speaker on “AI Challenges & Opportunities” at INSEAD ESRI Workshop on Research Integrity.
  • Panel shared with Anton Ovchinnikov, Nihar Shah, and Phanish Puranam.
• 2026.04: I visited CWI Amsterdam (Peter Grünwald’s group).
  • Sebastian Arnold and I co-presented our recent work on Betting on Bets: Anytime-Valid Tests for Stochastic Dominance.
• 2026.02: Our paper, Combining Evidence Across Filtrations, is accepted to JRSS-B!
  • Click here for links to the preprint, slides, code, and blog for this paper.
  • This is joint work with Aaditya Ramdas.
• 2026.02: New preprint is out on arXiv: The Information Geometry of Softmax: Probing and Steering, joint work with Kiho Park, Todd Nief, and Victor Veitch.
  • We leverage information geometry to formalize the semantic structure of LLM and CLIP embedding spaces, which are induced by the softmax model.
• 2026.01: Kiho, Yibo, and I co-wrote a short JRSS-B discussion piece on “Statistical Exploration of the Manifold Hypothesis” by Whiteley, Gray and Rubin-Delanchy.
  • Available on the JRSS-B website.
• 2025–2026: I served as a Workflow Chair for AISTATS 2026 (joint with Prakhar Verma).

2025

• 2025.11: I was invited to give a talk at NUS IMS Young Mathematical Scientists Forum (Statistics & Data Science) 2025.
  • I presented our recent work on Combining Evidence Across Filtrations, joint with Aaditya Ramdas.
• 2025.10: I gave a talk at Singapore Analytics & Operations Day 2025, hosted by Singapore Management University.
  • I presented our OR paper on Comparing Sequential Forecasters, joint with Aaditya Ramdas.
• 2025.08: I started as an Assistant Professor of Decision Sciences at INSEAD!
  • I am a resident faculty in INSEAD’s Asia Campus (Singapore); I will also teach regularly in its Europe Campus (Fontainebleau, France).
• 2025.07: I was invited to give a talk at Yonsei University in Seoul, South Korea.
  • I presented our recent work on Combining Evidence Across Filtrations, joint with Aaditya Ramdas.
• 2025.06: I am honored to receive this year’s Faraco Family Postdoctoral Fellowship for Outstanding Research at the UChicago Data Science Institute!
  • Much of the credit goes to my postdoc mentor, Victor Veitch, and my wonderful collaborators.
• 2025.06: I was at the the 3rd Workshop on Game-theoretic Statistics and Sequential, Anytime-Valid Inference (SAVI 2025), in Chennai, India.
  • My slides are avaliable here.
• 2025.04: I was at ICLR 2025 to give oral & poster presentations of our recent work, The Geometry of Categorical and Hierarchical Concepts in LLMs.
  • This is joint work with Kiho Park, Yibo Jiang, and Victor Veitch.
  • Video recording is available here.
• 2025.04: I was at the Singapore Alignment Workshop 2025.
• 2025.02: I am excited to announce that I will join INSEAD as an Assistant Professor of Decision Sciences this Fall!
• 2025.02: Our paper, The Geometry of Categorical and Hierarchical Concepts in LLMs, is accepted to ICLR 2025 for an oral presentation (top 1.8%)!
  • Building upon our recent ICML paper, we formalize the representations of categorical concepts in LLMs and show that hierarchical relations between concepts are represented as orthogonality.
  • Joint work with Kiho Park, Yibo Jiang, and Victor Veitch.
• 2025.02: A fully revised version of our paper, Combining Evidence Across Filtrations, is now on arXiv.
  • The updated preprint includes new empirical results on financial data.
  • Joint work with Aaditya Ramdas.

2024

• 2024.12: I attended ICSDS 2024 to give an invited talk titled “Mind the Filtration: E-processes vs. P-processes at Stopping Times.”
  • Slides are available here.
  • Based on our recent work on Combining Evidence Across Filtrations.
• 2024.10: New blog post in the UChicago DSI Blog: a non-technical intro to game-theoretic statistics, e-values, and my recent work with Aaditya Ramdas on Combining Evidence Across Filtrations.
  • It is cross-posted on my webpage as well: see here.
• 2024.10: I attended INFORMS 2024 to present our NeurIPS'23 paper titled Counterfactually Comparing Abstaining Classifiers (Session: “Causal Inference”).
  • Slides are available here.
• 2024.09: I am on the 2024–2025 academic job market for faculty positions in Statistics, Data Science, Machine Learning, and Operations Research.
  • Please refer to my CV for more details.
• 2024.08: I attended JSM 2024 to present our recent work on Combining Evidence Across Filtrations.
  • Slides are available here.
• 2024.07: Our recent preprint, titled The Geometry of Categorical and Hierarchical Concepts in LLMs, just won the Best Paper Award at the ICML 2024 Workshop on Mechanistic Interpretability!
  • Joint work with Kiho Park, Yibo Jiang, and Victor Veitch.
• 2024.06: A substantially revised version of our paper, Combining Evidence Across Filtrations, is now on arXiv.
  • The updated preprint includes new results, including a formal characterization of adjusters as “e-lifters”.
  • Joint work with Aaditya Ramdas.
• 2024.05: Our paper on The Linear Representation Hypothesis and the Geometry of LLMs is accepted to ICML 2024!
  • This is an exciting foundational work on how we can formalize different notions of linear representations in LLMs (e.g., linear probes and steering vectors) and unify those notions by identifying an inner product that encodes semantic structure.
  • Joint work with Kiho Park and Victor Veitch.
• 2024.02: Our new preprint, titled Combining Evidence Across Filtrations, is now available on arXiv.
  • We address an intriguing challenge for sequential inference that arises when combining e-processes constructed on different information sets.
  • Joint work with Aaditya Ramdas.

2023

• 2023.11: Our new preprint (my first one at UChicago DSI), titled The Linear Representation Hypothesis and the Geometry of LLMs, is now available on arXiv.
  • Joint work with Kiho Park and Victor Veitch.
  • The paper is also accepted for oral and poster presentations at the NeurIPS 2023 Workshop on Causal Representation Learning (CRL).
• 2023.09: Our recent paper, titled Counterfactually Comparing Abstaining Classifiers, is accepted to NeurIPS 2023!
  • This work develops an interesting connection between abstaining classifiers, causal inference, and black-box evaluation in ML.
  • Joint work with Aditya Gangrade and Aaditya Ramdas.
• 2023.09: I am excited to start my new position as a Postdoctoral Scholar at the UChicago Data Science Institute! My mentor is Victor Veitch.

• 2023.07: Our paper on Comparing Sequential Forecasters is now accepted for publication in Operations Research!
  • This is joint work with Aaditya Ramdas.
• 2023.06: I defended my Ph.D. Thesis at Carnegie Mellon University!
  • Here are the slides from my thesis defense.
  • I am grateful to my committee members: Aaditya Ramdas (Chair), Aarti Singh, Edward Kennedy, Johanna Ziegel, and Alexander D’Amour.