talk-data.com talk-data.com

Topic

compression

1

tagged

Activity Trend

1 peak/qtr
2020-Q1 2026-Q1

Activities

1 activities · Newest first

Abstract: The talk introduces Any Compression via Iterative Pruning (ACIP), a novel approach designed to give users intuitive control over the compression-performance trade-off. ACIP uses a single gradient descent run of iterative pruning to establish a global parameter ranking, enabling immediate materialization of models of any target size. It demonstrates strong predictive performance on downstream tasks without costly fine-tuning and achieves state-of-the-art compression for open-weight LLMs, often complementing common quantization techniques.