Sebastian Pokutta

LinearPFN: Amortized Variable Selection for Linear Models with Interactions

Spike-and-slab regression is a standard Bayesian formulation of variable selection: it returns a posterior distribution over which candidate effects are active rather than a single selected subset, so that every candidate effect carries an inclusion probability. Its cost grows exponentially with the number of candidate...

Discrete eigenvalue optimization from entropic smoothing and first-order methods

We study the maximization of the minimum eigenvalue under combinatorial and integrality constraints. We propose a new approach based on branch-and-bound combines entropic smoothing of the minimum eigenvalue function and Frank-Wolfe methods over concave relaxations of the constraints, thereby exploiting combinatorial st...

Structured Creativity Methods for Multi-Agent LLMs: Brainwriting Outperforms Disney and Double Diamond on LLM-Judged Originality

The Missing Drive: Functional Analogs of Intrinsic Motivation in Large Language Models for Creative Tasks

Robot Programming with Augmented Reality: The Role of Spatial Ability

Overall, AR did not significantly improve cognitive load or usability compared with conventional instruction, but exploratory analyses revealed a compensatory effect: spatial ability predicted higher usability and lower extraneous cognitive load in the control group, but not in the AR condition, suggesting AR mitigated...

Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations

Simulating student personas with large language models (LLMs) enables scalable evaluation of educational systems. However, behavioral drift, a progressive decline in persona consistency, can emerge over extended conversations, limiting the validity of such simulations. We evaluate five prompt-level mechanisms using sep...

Neural Field Tokenizations with Hierarchy and Spatial Locality Priors

It is argued that locality and hierarchy are useful priors for learning field representations that can be injected without compromising modality-agnosticism in LH-NeF, a framework to learn general-purpose tokenized representations of continuous signals.

Optimal Gradient-Norm Minimization in Non-Euclidean H\"older-Smooth Convex Optimization

Minimizing gradients of a convex function is an important problem across optimization and learning tasks. The gradient provides a directly computable certificate of approximate stationarity, and its minimization usually implies stronger results than those for minimization of function values. In this work, we study grad...

Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation

A scalable noise-learning framework for Lindblad dissipation rates that combines a stochastic simulation method, the Tensor Jump Method (TJM), with gradient-free optimization of a least-squares cost-function defined on time series of local-observable expectation values is proposed.