Zhuofan Josh Ying

I'm a PhD student in the Visual Inference Lab at Columbia University, supervised by Prof. Nikolaus Kriegeskorte.

Previously, I received my B.A. in Computer Science and Philosophy from UNC Chapel Hill. Before that, I briefly pursued a B.S. in Physics at USTC.

I'm generally interested in Computational Neuroscience, AI Safety, and Philosophy of Mind, with a focus on interpretability and efficiency.

Email / Google Scholar / Twitter / Github

Zhuofan Josh Ying

Research

Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
Interpretability AI Safety

Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization

Camila Blank, Zhuofan Ying, Christopher Potts, Peter Hase, Jing Huang

CoLM 2026, Actionable Interpretability Workshop

Macaron V1 Technical Report
Efficiency

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Mind Lab

Technical Report, 2026

Condorcet and Beyond: An Empirical Comparison of Voting Rules
Natural Intelligence

Condorcet and Beyond: An Empirical Comparison of Voting Rules

Igor Douven, Nikolaus Kriegeskorte, Patrick Stinson, Zhuofan Ying

Cognitive Science, 2026

Sample-Level White-Box Monitoring of Alignment Faking
Interpretability AI Safety

Sample-Level White-Box Monitoring of Alignment Faking

Lakshya Chaudhry*, Tianqin Meng*, Anthony Nguyen*, Yashraj Panwar*, Yuqi Sun, Zhuofan Ying

ICML 2026, Mechanistic Interpretability Workshop
ICML 2026, Technical AI Governance Research (TAIGR) Workshop

Comparing Linear Probes with Mahalanobis Cosine Similarity
Interpretability

Comparing Linear Probes with Mahalanobis Cosine Similarity

Zhuofan Ying, Peter Hase, Nikolaus Kriegeskorte

EMNLP 2026 (Main)

On the Scaling of PEFT: Million Personal Models of Trillion Parameters
Efficiency

On the Scaling of PEFT: Million Personal Models of Trillion Parameters

Mind Lab

Technical Report, 2026

MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Efficiency

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Mind Lab

Technical Report, 2026

How attention saves energy in vision
Natural Intelligence Efficiency

How Attention Saves Energy in Vision

Eivinas Butkus, Zhuofan Ying, Nikolaus Kriegeskorte

bioRxiv

truth spectrum
Interpretability AI Safety

The Truthfulness Spectrum Hypothesis

Zhuofan Ying, Shauli Ravfogel, Nikolaus Kriegeskorte, Peter Hase

arXiv

face geometry
Natural Intelligence Efficiency

Efficient Task Generalization and Humanlike Face Perception in Models that Learn to Discriminate Face Geometry

Seojin Lee, Zhuofan Ying, Ahana Dey, You-Nah Jeon, Elias Issa

bioRxiv

Token Entanglement
Interpretability AI Safety

Token Entanglement in Subliminal Learning

Amir Zur, Zhuofan Ying, Alexander Russell Loftus, Kerem Şahin, Steven Yu, Lucia Quirke, Tamar Rott Shaham, Natalie Shapira, Hadas Orgad, David Bau

NeurIPS 2025, Mechanistic Interpretability Workshop

Adaptive Contextual Perception
Interpretability

Adaptive Contextual Perception: How to Generalize to New Backgrounds and Ambiguous Objects

Zhuofan Ying, Peter Hase, Mohit Bansal

NeurIPS 2023

VisFIS
Interpretability

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

Zhuofan Ying*, Peter Hase*, Mohit Bansal

NeurIPS 2022

Deep Learning Recognition
Evaluation Natural Intelligence

Can Deep Learning Recognize Subtle Human Activities?

Vincent Jacquot, Zhuofan Ying, Gabriel Kreiman

CVPR 2020

Experience

Mind Lab
2026 Feb – PresentShenzhen
Resident Researcher
Constellation Institute
2025 Sep – 2025 DecBerkeley
Visiting Fellow
Cambridge Boston Alignment Initiative (CBAI)
2025 Jun – 2025 AugBoston
Supervised by Prof. David Bau
Columbia University, Issa Lab
2022 May – 2023 JunNew York
Supervised by Prof. Elias Issa
UNC Chapel Hill, MURGe-Lab
2021 Aug – 2023 JunChapel Hill
Supervised by Prof. Mohit Bansal
Tsinghua University, Laboratory of Brain and Intelligence (THBI)
2020 Nov – 2021 AprBeijing
Supervised by Prof. Jia Liu
Tencent, Lightspeed & Quantum Studio
2020 May – 2020 OctShenzhen
Supervised by Dr. Runze Zhang
Harvard Medical School, Kreiman Lab
2019 Jan – 2019 JulBoston
Supervised by Prof. Gabriel Kreiman
iFlytek, AI Service Department
2018 Apr – 2018 AugHefei
Supervised by Dr. Xiaowei Fang and Dr. Yu Di

Service