paper

Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

paperactiveprovisionaladaptive-multi-resolution-procedural-knowledge-compression-for-large-language-models-84357d09·1 events·first seen 6d ago

Aliases: Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

Co-occurring entities

SKIM (SKIll coMpression)

More like this (12)

Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models Civil Court Simulation with Large Language Models large language models Multimodal Large Language Models large language model agents Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models Scaling Laws for Neural Language Models Reinforcement Learning for Language Models Automated reproducibility assessments in the social and behavioral sciences using large language models Unintended Effects of Geographic Conditioning in Large Language Models Large Language Models (frontier)multi-turn language models

Recent events (1)

5arXiv · cs.CL·6d ago·source ↗

SKIM: Adaptive soft-token compression for procedural skills in LLM workflows

Researchers introduce SKIM (SKIll coMpression), a multi-resolution soft token compression framework targeting procedural knowledge (skills/workflows) rather than factual documents. SKIM compresses reusable natural language skills to 30–60% of their original token length while preserving task performance, reducing prefill cost and latency when skills are repeatedly invoked. The method adapts compression depth to skill complexity and supports offline compression for frequently updated community skills.

Inference Economics Agent and Tool Ecosystem Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models SKIM (SKIll coMpression)