Text-to-CAD retrieval is introduced as a cross-modal task with a baseline that learns joint embeddings from CAD construction sequences, point clouds, and text queries via a masked feature decoder.
Evaluating retrieval quality in retrieval- augmented generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Assigning higher redundancy to semantically important query features reduces retrieval error probability under token erasures, via multivariate Gaussian approximations of similarity margins and supporting numerical results.
citing papers explorer
-
Text-to-CAD Retrieval: a Strong Baseline
Text-to-CAD retrieval is introduced as a cross-modal task with a baseline that learns joint embeddings from CAD construction sequences, point clouds, and text queries via a masked feature decoder.
-
Context-Aware Search and Retrieval Under Token Erasure
Assigning higher redundancy to semantically important query features reduces retrieval error probability under token erasures, via multivariate Gaussian approximations of similarity margins and supporting numerical results.