43 citations · 148 across the 15 of their papers we have counts for
15 papers
Stealing Reasoning Traces from Proprietary LLM APIs
Alexander Panfilov, David Schmotz, Ilia Shumailov +5
Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather…
CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov +4
AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untru…
Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety
Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad +3
An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but unt…
Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability
Luca Baroni, Galvin Khara, Joachim Schaeffer +2
Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its r…
Diagnostic-free onboard battery health assessment
Yunhong Che, Vivek N. Lam, Jinwook Rhyu +5
Diverse usage patterns induce complex and variable aging behaviors in lithium-ion batteries, complicating accurate health diagnosis and prognosis. Separate diagnostic cycles are of…
Interpretation of High-Dimensional Regression Coefficients by Comparison with Linearized Compressing Features
Joachim Schaeffer, Jinwook Rhyu, Robin Droop +2
Linear regression is often deemed inherently interpretable; however, challenges arise for high-dimensional data. We focus on further understanding how linear regression approximate…
Systematic Feature Design for Cycle Life Prediction of Lithium-Ion Batteries During Formation
Jinwook Rhyu, Joachim Schaeffer, Michael L. Li +4
Optimization of the formation step in lithium-ion battery manufacturing is challenging due to limited physical understanding of solid electrolyte interphase formation and the long…
Safe Learning-Based Optimization of Model Predictive Control: Application to Battery Fast-Charging
Sebastian Hirt, Andreas Höhl, Johannes Pohlodek +4
Model predictive control (MPC) is a powerful tool for controlling complex nonlinear systems under constraints, but often struggles with model uncertainties and the design of suitab…
Gaussian process-based online health monitoring and fault analysis of lithium-ion battery systems from field data
Joachim Schaeffer, Eric Lenz, Duncan Gulla +3
Health monitoring, fault analysis, and detection are critical for the safe and sustainable operation of battery systems. We apply Gaussian process resistance models on lithium iron…
Accounting for the Effects of Probabilistic Uncertainty During Fast Charging of Lithium-ion Batteries
Minsu Kim, Joachim Schaeffer, Marc D. Berliner +3
Batteries are nonlinear dynamical systems that can be modeled by Porous Electrode Theory models. The aim of optimal fast charging is to reduce the charging time while keeping batte…
Learning Model Predictive Control Parameters via Bayesian Optimization for Battery Fast Charging
Sebastian Hirt, Andreas Höhl, Joachim Schaeffer +3
Tuning parameters in model predictive control (MPC) presents significant challenges, particularly when there is a notable discrepancy between the controller's predictions and the a…
Cycle Life Prediction for Lithium-ion Batteries: Machine Learning and More
Joachim Schaeffer, Giacomo Galuppini, Jinwook Rhyu +4
Batteries are dynamic systems with complicated nonlinear aging, highly dependent on cell design, chemistry, manufacturing, and operational conditions. Prediction of battery cycle l…
Interpretation of High-Dimensional Linear Regression: Effects of Nullspace and Regularization Demonstrated on Battery Data
Joachim Schaeffer, Eric Lenz, William C. Chueh +3
High-dimensional linear regression is important in many scientific fields. This article considers discrete measured data of underlying smooth latent processes, as is often obtained…
Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra
Joachim Schaeffer, Paul Gasper, Esteban Garcia-Tamayo +10
Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and th…
Latent Variable Method Demonstrator -- Software for Understanding Multivariate Data Analytics Algorithms
Joachim Schaeffer, Richard Braatz
The ever-increasing quantity of multivariate process data is driving a need for skilled engineers to analyze, interpret, and build models from such data. Multivariate data analytic…