3 papers
cs.AI2026
DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
Aozhong Zhang, Selcuk Gurses, Yanxia Deng +8
Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory growth. While recent evicti…
cs.LG2026
Is Finer Better? The Limits of Microscaling Formats in Large Language Models
Andrea Fasoli, Monodeep Kar, Chi-Chun Liu +4
Microscaling data formats leverage per-block tensor quantization to enable aggressive model compression with limited loss in accuracy. Unlocking their potential for efficient train…
q-fin.GN2025
Attribution Locus and the Timeliness of Long-lived Asset Write-downs
Yao-Lin Chang, Chun-Yang Lin, Chi-Chun Liu +1
We examine the relative timeliness with which write-downs of long-lived assets incorporate adverse macroeconomic and industry outcomes versus adverse firm-specific outcomes. We pos…