MaxSimum
PulseAugur coverage of MaxSimum — every cluster mentioning MaxSimum across labs, papers, and developer communities, ranked by signal.
-
EigenLI framework offers spectral approximation for late-interaction models
Researchers have developed EigenLI, a novel framework for approximating late-interaction models in information retrieval. This method leverages the intrinsic low-rank structure of document token embeddings to compress r…
-
New methods boost visual document retrieval efficiency
Two new research papers propose methods to improve the efficiency of late-interaction visual document retrieval systems. The first paper introduces Generative Late-Interaction Embeddings (GLIE), which uses a small set o…
-
New RAG framework automates civil plan analysis using visual-first approach
Researchers have developed PlanSightRAG, a novel multimodal retrieval-augmented generation (RAG) framework designed to automate the analysis of civil infrastructure plans. This system processes plan imagery directly, in…
-
Hugging Face introduces MultiVectorEncoder for advanced retrieval
Hugging Face has introduced MultiVectorEncoder, a new tool within its sentence-transformers library that enables the use of multi-vector embedding models. These models, inspired by the ColBERT architecture, process text…
-
New H+ Embedding system harmonizes global and token-level retrieval
Researchers have developed H+ Embedding, a novel retrieval system designed to improve the accuracy of information retrieval, particularly for specialized domains like medicine. This system addresses the limitations of e…
-
New theory explains late-interaction retrieval models, introduces Signed MaxSim
Researchers have theoretically quantified the representational power of late-interaction retrieval models, specifically those using the MaxSim similarity function. The study demonstrates that MaxSim can precisely replic…
-
TileMaxSim kernel boosts GPU retrieval model speed by 220x
Researchers have developed TileMaxSim, a new IO-aware kernel for GPUs designed to significantly accelerate the MaxSim scoring process used in multi-vector retrieval models like ColBERT. Existing implementations are inef…
-
Spectral Retrieval enhances LLM agent localized search accuracy
Researchers have introduced Spectral Retrieval, a novel plug-in re-ranking stage for large language model (LLM) multi-agent systems. This method utilizes multi-scale sinc convolution over token embeddings to improve loc…