Zhong, Ziqian

5 publications

ICLR 2026 ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases Ziqian Zhong, Aditi Raghunathan, Nicholas Carlini

ICLR 2026 Watch the Weights: Unsupervised Monitoring and Control of Fine-Tuned LLMs Ziqian Zhong, Aditi Raghunathan

NeurIPS 2024 Algorithmic Capabilities of Random Transformers Ziqian Zhong, Jacob Andreas

NeurIPSW 2023 Grokking as Simplification: A Nonlinear Complexity Perspective Ziming Liu, Ziqian Zhong, Max Tegmark

NeurIPS 2023 The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas