Ko-VDR Train Public Collection Training Dataset for Korean Visual Document Retrieval • 4 items • Updated about 7 hours ago
Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2 Text Generation • 25B • Updated 2 days ago • 3.72k • 117
KoViDoRe Benchmark (BEIR) v2 Collection Korean Vision Document Retrieval Benchmark • 4 items • Updated Mar 2 • 6
Ko-VDR Train Public Collection Training Dataset for Korean Visual Document Retrieval • 4 items • Updated about 7 hours ago
Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval Paper • 2604.04734 • Published 9 days ago • 10
view article Article Multimodal Embedding & Reranker Models with Sentence Transformers 6 days ago • 40