DeCoDrift stabilizes decoder coupling in closed-loop foundation segmentation by constraining prompt updates without retraining or ground truth.
Belongie, Bharath Hariharan, and Ser-Nam Lim
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
BrainROI achieves leading cross-subject brain-captioning results on NSD by combining multi-atlas soft-ROI fusion with interpretable prompt optimization.
PLACE is a prompt-augmented graph framework for attributed community search that integrates learnable tokens with GNNs via alternating training and divide-and-conquer scaling, achieving 22% higher average F1 scores than prior methods on nine real-world graphs.
DIVE combines a self-limiting hinge triplet loss on one head with a head-wise NT-Xent loss on multiple heads, and reports large retrieval gains over prior embedding-compression adapters on six BEIR datasets.
citing papers explorer
-
DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation
DeCoDrift stabilizes decoder coupling in closed-loop foundation segmentation by constraining prompt updates without retraining or ground truth.
-
Unified Multimodal Brain Decoding via Cross-Subject Soft-ROI Fusion
BrainROI achieves leading cross-subject brain-captioning results on NSD by combining multi-atlas soft-ROI fusion with interpretable prompt optimization.
-
PLACE: Prompt Learning for Attributed Community Search in Large Graphs
PLACE is a prompt-augmented graph framework for attributed community search that integrates learnable tokens with GNNs via alternating training and divide-and-conquer scaling, achieving 22% higher average F1 scores than prior methods on nine real-world graphs.
-
DIVE: Embedding Compression via Self-Limiting Gradient Updates
DIVE combines a self-limiting hinge triplet loss on one head with a head-wise NT-Xent loss on multiple heads, and reports large retrieval gains over prior embedding-compression adapters on six BEIR datasets.