Tetris decomposes stationary videos into tile polyominoes and applies classifier plus ILP pruning to cut detector calls, staying within 5% accuracy loss while delivering up to 17.4x throughput gains over priors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Query-centric AQP and proxy-model strategies reduce expensive model calls by 60-90% with under 10% error on TPC-DS and LLM tasks.
citing papers explorer
-
Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models
Query-centric AQP and proxy-model strategies reduce expensive model calls by 60-90% with under 10% error on TPC-DS and LLM tasks.