CausalEmbed uses auto-regressive generation with iterative margin loss to produce multi-vector embeddings that reduce visual token counts 30-155x while retaining competitive performance on VDR benchmarks.
Let llms speak embedding languages: Generative text embeddings via iterative contrastive re- finement.arXiv preprint arXiv:2509.24291,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding
CausalEmbed uses auto-regressive generation with iterative margin loss to produce multi-vector embeddings that reduce visual token counts 30-155x while retaining competitive performance on VDR benchmarks.