The paper introduces SRAIN, a framework that learns sample‑wise, rank‑aware interpolation weights for composed visual data retrieval. Instead of relying on complex multimodal large language models, SRAIN uses simple linear interpolation in embedding space, dynamically predicting query‑specific weights through batch‑wise rank‑aware estimation and a compact memory bank for hard negatives. This approach achieves state‑of‑the‑art performance on composed video retrieval and competitive results on composed image retrieval while significantly reducing query‑time latency.
arXiv:2607. 25266v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible.
CORE improves compositional reasoning in multimodal language models by distilling a cross‑attentive reranker’s fine‑grained judgments into the embedding model. It generates candidate lists across five compositional matching levels and trains with a Rank‑KL objective to replicate the reranker’s ranking. Experiments on COLA, SUGARCREPE++, and NEGBENCH show CORE‑RERANKER‑8B outperforms Jina‑Reranker by 10.7 points, while CORE‑EMBED‑8B achieves the best overall average among evaluated embeddings, with gains also transferring to the MCMR benchmark without harming COCO or Flickr30K retrieval.
arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.
arXiv:2608.23102v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) is an emerging paradigm in content-based image retrieval that enables users to formulate compositional queries by combin...
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text describing the desired modification. Recent ZS-CIR studies have relied on projection-based methods that map a reference image into pseudo-word tokens in the text embedding space.
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eith...
Upgrading embedding models typically requires expensive database re-indexing, as new query embeddings are incompatible with existing database embeddings. While Backward Compatible Training (BCT) mitig...
The paper introduces the AutoRegressive Retriever (ARR), a multimodal retrieval model that iteratively refines a query embedding by selecting informative items and incorporating their content. ARR alternates between retrieval and query update, using stepwise contrastive supervision and reinforcement learning to optimize item selection and final ranking. Experiments show ARR outperforms baselines on in‑domain and zero‑shot benchmarks, with feedback improving both inference performance and initial query embeddings.
The paper introduces CERES, a closed‑loop multimodal indexing framework that addresses semantic collapse in multimodal generation by building a three‑level semantic pyramid and using scale‑routed cross‑attention to generate images that remain retrievable by their original queries. CERES employs a co‑occurrence‑aware router, a lightweight U‑Net generator, and a soft‑Jaccard coverage objective to ensure generated images cover the intended concepts, verified by re‑indexing with a frozen vision‑language model and an external DINOv2 probe. Experiments on four pansharpening benchmarks show state‑of‑the‑art performance, especially under extreme scale variation, and significant improvements in concept‑query retrieval and image‑text ranking metrics.
arXiv:2608. 20810v1 Announce Type: cross Abstract: Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, so the output must remain retrievable by the queries it was meant to serve.
arXiv:2609.10008v1 Announce Type: new Abstract: Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gal...
arXiv:2607. 23052v1 Announce Type: cross Abstract: Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable.