Concept Flow Models use hierarchical concept-driven decision trees to mitigate information leakage in concept bottleneck models while matching their predictive performance.
Contrastive localized language-image pre-training
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Proposes Adaptive Tail-Head Alignment (ATHA) that breaks alignment for low-similarity 'tail tokens' in CLIP to boost source-free cross-domain few-shot learning.
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.