Scholar
Jikai Jin
Google Scholar ID: xQqZt2AAAAAJ
Stanford University
Citations & Impact
Citations
422
H-index
10
i10-index
10
Publications
13
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- Papers: 'It’s Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation' (with Lester Mackey, Vasilis Syrgkanis); 'Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning' (with Vasilis Syrgkanis, Sham Kakade, Hanlin Zhang); 'Solving Inequality Proofs with Large Language Models' (with Jiayi Sheng, Luna Lyu, Tony Xia, Alex Gu, James Zou, Pan Lu). Among them, 'Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation' was accepted by COLT 2025, and 'Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity' was accepted as a spotlight presentation at NeurIPS 2024.
Research Experience
- Starting a research scientist internship at Meta’s Central Applied Science group since June 2025.
Education
- Ph.D. student, Institute for Computational and Mathematical Engineering (ICME), Stanford University, 2023 - 2027 (expected); Advisor: Prof. Vasilis Syrgkanis; BSc in Computational Mathematics, School of Mathematical Sciences, Peking University, 2019 - 2023; Advisor: Prof. Liwei Wang; High School Diploma, No.2 High School of East China Normal University, 2017 - 2019.
Background
- Research Interests: Research questions that combine theoretical insights with real-world impact, including understanding fundamental limits of ML-empowered estimation methods and applying statistical tools to enhance LLM evaluation. Professional Field: Computational Mathematics.
Miscellany
- Personal interests not mentioned
