20 results for “learnable embeddings”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long +4 more
The paper introduces UEmbed, a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one forward pass.
Kehang Jia, Teng Liu, Juntao Li, Hua Chen +3 more
The paper proposes AntEmbed, a dual-mode multimodal embedding model for efficient retrieval and reasoning-enhanced fine-grained matching.
This paper reviews various mechanisms for calculating word embeddings, investigates popular toolkits and matrices, and experiments with selected implementations.
This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.
Zhen Li, Xin Huang, Liang Wang, Nan Yang +7 more
BITEMBED presents a low-bit framework for efficient LLM-based text embedding that balances encoding efficiency and vector storage.
Ziying Chen, Yang Cao, He Sun, Beining Yang +1 more
The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…
Marek Šuppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková +1 more
This paper introduces SkMTEB, a comprehensive text embedding benchmark for Slovak, and develops efficient, locally-deployable Slovak embeddings.
This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…
Prashant Gokhale, Piotr Indyk, Yuhao Liu, Sandeep Silwal +2 more
This paper investigates compact reachability embeddings for hierarchical data and provides theoretical guarantees for representing hierarchies using embeddings with dimensions dependent on graph param…
This paper proposes a new method, EGIM, to improve high-granularity topic modeling by separating semantically similar but distinct topics.
A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…
This paper explains how discarded norms in contrastive embedding models correlate with semantic properties and provides a theoretical framework.
The paper proposes and evaluates a novel embedding model for bidirectional function association between source code and decompiled/stripped code, significantly outperforming existing models.
This paper presents Fusion Embedding family, which adds audio to a pre-trained vision-language embedding base using a connector and deep adapters.
The paper proposes an extended version of Hypencoder, a retrieval approach that encodes queries as shallow neural networks, achieving comparable effectiveness with fewer active parameters and higher s…
Yu-Che Tsai, Kuan-Yu Chen, Yuan-Hao Chen, Yu-Han Chang +3 more
PromptEmbedder introduces a dual-LLM framework that efficiently and transferably adapts text embeddings by decoupling task-specific knowledge from the backbone model, significantly reducing computatio…