Tootfinder

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
Dmitry Akulov, Mohamed Sana, Antonio De Domenico, Tareq Si Salem, Nicola Piovesan, Fadhel Ayed
https://arxiv.org/abs/2509.05165

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache compression methods either enforce rigid heuristics, disrupt tensor layouts with per-attention-head variability, or require specialized compute kernels. We propose a simple, yet effective, KV cache compression framework based on attention-guided, layer-adap…

Learning Linear Regression with Low-Rank Tasks in-Context
Kaito Takanami, Takashi Takahashi, Yoshiyuki Kabashima
https://arxiv.org/abs/2510.04548 https://a…

Learning Linear Regression with Low-Rank Tasks in-Context
In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common structure. In this work, we address this problem by analyzing a linear attention model trained on low-rank regression tasks. Within this setting, we precisely characterize the distribution of predictions and the generalization error in the high-dimensional li…