Encoding user interactions into visual in-context example pairs turns static models into controllable systems that improve IoU, PSNR, and LPIPS on guided tasks without retraining.
arXiv preprint arXiv:2402.04841 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
A capacity-capped 1M-param VICL model is used to expose gaps in how adaptive capabilities are measured in visual in-context learning.
citing papers explorer
-
From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks
Encoding user interactions into visual in-context example pairs turns static models into controllable systems that improve IoU, PSNR, and LPIPS on guided tasks without retraining.
-
Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
-
Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model
A capacity-capped 1M-param VICL model is used to expose gaps in how adaptive capabilities are measured in visual in-context learning.