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.
Llavanext: Improved reasoning, ocr, and world knowledge,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
Introduces CompliVision dataset and active learning framework for rule-based hazard compliance assessment using vision-language models grounded in safety standards.
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.
-
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
-
General Hazard Detection
Introduces CompliVision dataset and active learning framework for rule-based hazard compliance assessment using vision-language models grounded in safety standards.