DSCA turns concept isolation into an architectural property by dynamically creating orthogonal subspaces for non-interfering lifelong edits in vision-language models, sustaining over 95% success after 1000 sequential edits.
Lawrence Zitnick
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
FSNet detects unknown invisible watermarks via adaptive frequency gating and multi-spectral attention on the UniFreq-100K dataset, claiming superior zero-shot performance.
A differentiable fuzzy logic module called DKU discovers implicit concepts from image classification supervision and applies logical adjustments to improve class probabilities on PASCAL-VOC, COCO, and MedMNIST.
XD-MAP generates pseudo labels for LiDAR semantic segmentation from camera images using parametric maps, improving 2D and 3D segmentation performance by up to 32.3 mIoU without manual labeling.
citing papers explorer
-
DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
DSCA turns concept isolation into an architectural property by dynamically creating orthogonal subspaces for non-interfering lifelong edits in vision-language models, sustaining over 95% success after 1000 sequential edits.
-
AWPD: Frequency Shield Network for Agnostic Watermark Presence Detection
FSNet detects unknown invisible watermarks via adaptive frequency gating and multi-spectral attention on the UniFreq-100K dataset, claiming superior zero-shot performance.
-
Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition
A differentiable fuzzy logic module called DKU discovers implicit concepts from image classification supervision and applies logical adjustments to improve class probabilities on PASCAL-VOC, COCO, and MedMNIST.
-
XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation
XD-MAP generates pseudo labels for LiDAR semantic segmentation from camera images using parametric maps, improving 2D and 3D segmentation performance by up to 32.3 mIoU without manual labeling.