collaborators

6 papers

cs.LG2026

KVpop -- Key-Value Cache Compression with Predictive Online Pruning

Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl +5

Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV eviction methods often rely on…

cs.LG2026

Effective Distillation to Hybrid xLSTM Architectures

Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied +7

There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures. However, despite extensive research…

cs.LG2026

TiRex-2: Generalizing TiRex to Multivariate Data and Streaming

Patrick Podest, Marco Pichler, Elias Bürger +7

We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. R…

cs.CV2026

MUFASA: A Multi-Layer Framework for Slot Attention

Sebastian Bock, Leonie Schüßler, Krishnakant Singh +2

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vector…

cs.LG2026

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

Maximilian Beck, Kajetan Schweighofer, Sebastian Böck +2

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 T…

cs.LG2025

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

Andreas Auer, Patrick Podest, Daniel Klotz +3

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 p…