GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing ericavanee.github.io — Erica Zhang AboutHello :) I am Erica, currently a Ph.D. candidate in Operations Research in the Department of Management Science & Engineering (MS&E) at Stanford University, co-advised by Prof. Jose H. Blanchet (MS&E) and Prof. Mert Pilanci (Electrical Engineering). My work has been shaped by close collaborations with Prof. James Zou and Prof. Robert Tibshirani. I am grateful to be supported by the Stanford Graduate Fellowship (SGF) in Sciences and Engineering via the Koret Foundation and a PhD Fellowship from Jump Trading in the AI/ML track. At Stanford, I am affiliated with Stanford Center for AI Safety and Advanced Financial Technologies Laboratory (AFTLab). As part of my Ph.D., I completed a co-enrolled M.S. degree in Electrical Engineering, specializing in Control & Optimization. Prior to Stanford, I earned a dual B.A. in Mathematics and Statistics from Columbia College, Columbia University, graduating summa cum laude with honors from both departments. This past summer (2025), I interned as an Applied Scientist working on Agentic AI with Amazon Science at the Bellevue office. This summer (2026), I interned at Two Sigma as a Quantitative Researcher working on post-training for alpha modeling at the New York headquarters. NewsI will be back at Google Ventures giving a talk on building verifiers for agentic markets at the San Francisco headquarters on Oct. 1st, 2026! Check out out latest work: TERMS-Bench and leaderboard! TERMS-Bench introduces a new way to evaluate agentic capabilities in non- or semi-verifiable domains, where structure is loose and no native verifier exists: constructing the environment itself as the verifier. We focus on agentic negotiation, including commercial extensions such as stateful agentic procurement chains, and evaluate the most capable high-reasoning models from major providers as of May 2026. Excited to share that I received the Jump Trading Fellowship in the AI/ML track (2026), supporting my research on reliable modern learning and agentic AI systems. Check out our latest work: Statsformer! Statsformer bridges LLM guidance with statistical rigor, delivering provable safety guarantees that mitigate performance degradation from LLM hallucinations while consistently outperforming strong AutoML baselines (e.g., AutoGluon, LLM-Agent–style systems). ResearchI am a researcher building at the intersection of foundation models, agentic systems, and markets. I began as a theorist and statistician, and still draw heavily on optimization, probability, and statistical learning, but increasingly my work centers on a broader question: what structures do intelligent systems need in order to learn, act, and interact reliably in messy real-world environments? My recent work spans post-training under noisy learning signals, verifier-based evaluation for semi- and non-verifiable domains, LLM-integrated learning with formal guarantees, and multi-agent systems for strategic and economic interaction. Across these settings, I am especially interested in long-horizon, strategic domains, where the clean verification story of mathematics and coding breaks down, and where progress may require reasoning from first principles about the structures beyond engineering more harnesses. Philosophically, I’m inspired by mathematician Hans Hahn’s view of mathematics as a precise, elegantly constructed conceptual framework: one that enables us to abstract information and perform tautological transformations to uncover fundamental laws governing our world [1]. What I find beautiful in this view is that it captures both the power and the limit of formal languages such as mathematics: they let us make hidden structure explicit, but they can only take us as far as the framework itself allows. Some of the questions I find most interesting begin at that boundary: when progress requires not just solving within a framework, but building a better one. Feel free to reach out if you’re interested in my work 🙂 Selected Industry Projects
Open-Source Projects
Scholarly Works
Invited Talks
Academic Service
Honors
References [1] Hahn, Hans (1933). Logic, Mathematics and Knowledge of Nature (Logik, Mathematik und Naturerkenntnis). In B. McGuinness (Ed.), Unified Science: The Vienna Circle Monograph Series (pp. 24–45). Dordrecht: Springer. Springer Link. |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |