Topics

Text Embeddings

Methods for turning text into dense vectors for retrieval, similarity, and search, including using LLMs as encoders.

E5: Weakly-Supervised Contrastive Text Embeddings

E5 turns general-purpose text embeddings into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.

Text Embeddings · Independent Researcher

Sentence-BERT: Sentence Embeddings with Siamese BERT

Sentence-BERT turns sentence embeddings for semantic similarity into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.

Text Embeddings · Princeton University

SimCSE: Contrastive Learning for Sentence Embeddings

SimCSE turns contrastive sentence embedding learning into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.

AI Agents · University of Waterloo

Direct Corpus Interaction: Letting Agents grep Instead of a Retriever

Direct Corpus Interaction (DCI) lets a search agent grep the raw corpus instead of calling a retriever. On BrowseComp-Plus it lifts accuracy from 69.0% to 80.0% while cutting cost 29.4%.

Multimodal Models · NVIDIA

MulTaBench: A 40-Dataset Benchmark for Multimodal Tabular Learning

MulTaBench is a 40-dataset benchmark (20 image-tabular, 20 text-tabular) where each task needs both the table and the image or text. Its finding: tuning embeddings to the target beats frozen embeddings on every learner.

Text Embeddings · Renmin University of China

EmbFilter: Turning an LLM's UnEmbedding Matrix Into a Feature Lens

EmbFilter reads the LLM unembedding matrix as a lens, strips the subspace that ties text embeddings to high-frequency junk tokens, and lifts zero-shot retrieval while shrinking dimensions.