Matteo Attimonelli
PulseAugur coverage of Matteo Attimonelli — every cluster mentioning Matteo Attimonelli across labs, papers, and developer communities, ranked by signal.
-
New research explores efficient multimodal retrieval with adaptive embeddings
Three new research papers explore advancements in multimodal retrieval, focusing on improving efficiency and performance. The first paper introduces ReT-2, a unified retrieval model using a recurrent Transformer archite…
-
New StyleFlow model generates fashion images from free-form text instructions
Researchers have introduced a new method for generating fashion images that complement a given seed item, based on natural language instructions. This approach, named StyleFlow, utilizes a Rectified Flow Matching model …
-
CIR benchmarks overestimate AI model composition abilities
A new research paper questions the effectiveness of current benchmarks for Composed Image Retrieval (CIR), a task requiring models to combine image and text information. The study found that many existing CIR benchmarks…