Sebastian Böck — accepted AI-conference papers

2026

xLSTM Distillation: Achieving Teacher-Student Parity Through Efficient Hybrid Architectures

Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied, Anamaria-Roberta Hartl, David Stap, Pieter-Jan Hoedt +3

ICML 2026poster

There have been numerous attempts to distill quadratic attention-based LLMs into sub-quadratic linearized architectures. However, despite extensive research, such distilled models often fail to match the performance of their teacher LLMs on various downstream tasks. We set out the goal of lossless d…

Cited by 0 Source ↗Scholar ↗

2026

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

Maximilian Beck, Kajetan Schweighofer, Sebastian Böck, Sebastian Lehner, Sepp Hochreiter

ICLR 2026poster

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant architecture, recent alternatives such as xLSTM offer linear complexity with respe…

Cited by 0 Source ↗code ↗Scholar ↗

2025

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Andreas Auer, Patrick Podest, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter

NeurIPS 2025poster

In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerfu…

Cited by 0 Source ↗code ↗Scholar ↗

2025

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle, Patrick M Blies, Günter Klambauer +2

ICML 2025poster

Recent breakthroughs in solving reasoning, math and coding problems with Large Language Models (LLMs) have been enabled by investing substantial computation budgets at inference time. Therefore, inference speed is one of the most critical properties of LLM architectures, and there is a growing need…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2019

Deep Polyphonic ADSR Piano Note Transcription

Rainer Kelz, Sebastian Böck, Gerhard Widmer

ICASSP 2019accepted

We investigate a late-fusion approach to piano transcription, combined with a strong temporal prior in the form of a handcrafted Hidden Markov Model (HMM). The network architecture under consideration is compact in terms of its number of parameters and easy to train with gradient descent. The networ…

Cited by 0 Source ↗Scholar ↗