3 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.LG2025
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…