arxivJul 31bullish

BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels

arXiv:2604.15591v2 Announce Type: replace-cross Abstract: Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers build on coarse binary relevance signals, limiting their ability to

BIBI2 models #biomedical #information-retrieval #contrastive-learning

arxivJul 10bullish

Contrastive Order Learning: A General Framework for Ordinal Regression

arXiv:2607.08109v1 Announce Type: new Abstract: We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, i

CO1 model #machine-learning #ordinal-regression #contrastive-learning Read on arxiv →

arxivMay 29

OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment

arXiv:2605.29900v1 Announce Type: new Abstract: Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively underexplored. Pairwise CLIP-style losses decompose multi-modal alignment into independent two-way comp

#multi-modal #contrastive-learning #information-theory Read on arxiv →