2 papers
cs.CL2025
Surprise Calibration for Better In-Context Learning
Zhihang Tan, Jingrui Hou, Ping Wang +2
In-context learning (ICL) has emerged as a powerful paradigm for task adaptation in large language models (LLMs), where models infer underlying task structures from a few demonstra…
cs.AR2025
MERE: Hardware-Software Co-Design for Masking Cache Miss Latency in Embedded Processors
Dean You, Jieyu Jiang, Xiaoxuan Wang +9
Runahead execution is a technique to mask memory latency caused by irregular memory accesses. By pre-executing the application code during occurrences of long-latency operations an…