activity
20242026
collaborators

7 papers

eess.SY2026

Stochastic MPC with Online-optimized Policies and Closed-loop Guarantees

Marcell Bartos, Alexandre Didier, Jerome Sieber +2

This paper proposes a stochastic model predictive control method for linear systems affected by additive Gaussian disturbances that optimizes over disturbance feedback matrices onl…

cs.LG2026

A Predictive Law for On-Policy Self-Distillation From World Feedback

Tommy He, Jerome Sieber, Matteo Saponati

Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent appro…

cs.LG2026

Design Principles for Sequence Models via Coefficient Dynamics

Jerome Sieber, Antonio Orvieto, Melanie N. Zeilinger +1

Deep sequence models, ranging from Transformers and State Space Models (SSMs) to more recent approaches such as gated linear RNNs, fundamentally compute outputs as linear combinati…

cs.LG2025

Eigenvalues as a Metric for Memory Dynamics in Sequence Models

Rahel Rickenbach, Jelena Trisovic, Alexandre Didier +2

While softmax attention drives state-of-the-art performance in sequence modeling, its quadratic complexity motivates linear alternatives such as state space models (SSMs). Structur…

eess.SY2025

Computationally Efficient System Level Tube-MPC for Uncertain Systems

Jerome Sieber, Alexandre Didier, Melanie N. Zeilinger

Tube-based model predictive control (MPC) is one of the principal robust control techniques for constrained linear systems affected by additive disturbances. While tube-based metho…

cs.LG2025

Lambda-Skip Connections: the architectural component that prevents Rank Collapse

Federico Arangath Joseph, Jerome Sieber, Melanie N. Zeilinger +1

Rank collapse, a phenomenon where embedding vectors in sequence models rapidly converge to a uniform token or equilibrium state, has recently gained attention in the deep learning…