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.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
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…