# AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal Retrieval

arXiv: https://arxiv.org/abs/2608.25412 · HTML: https://mlsanity.com/paper/2608.25412/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 4 of 4)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents](https://mlsanity.com/paper/2507.04590/) (2025)
- [Col-Bandit: Query-Time Top-K Estimation for Late-Interaction Retrieval](https://mlsanity.com/paper/2602.02827/) (2026)

## Abstract (arXiv)

Multi-vector representations have emerged as an effective paradigm for multimodal retrieval, representing each sample with multiple complementary embeddings to capture fine-grained cross-modal information. However, existing approaches typically employ a fixed representation capacity, assigning the same number of vectors to all samples regardless of their individual retrieval demands. Such a fixed-capacity formulation overlooks the fact that different samples may require different amounts of representation capacity for effective retrieval. In this work, we introduce Sample-Adaptive Multi-Vector Representation (SAMVR), a new problem setting for multimodal retrieval that studies how multi-vector representation capacity can be allocated at the sample level. Under SAMVR, each sample is represented by a content-adaptive embedding set (CAES), whose capacity is determined according to the sample-specific retrieval utility of additional representation vectors. To instantiate SAMVR, we propose AdaptiveEmbed, a unified framework for learning sample-adaptive multi-vector representations. AdaptiveEmbed learns structured multi-vector representations through Multi-Group Contrastive Learning (MGCL) with the symmetric set-to-set similarity (SetSim), and further employs Utility Policy Optimization (UPO) to determine sample-specific representation capacity via Marginal Utility Allocation (MUA). Experiments across multimodal retrieval benchmarks involving image, text, video, and audio show that sample-adaptive capacity allocation achieves overall better retrieval performance than fixed-capacity multi-vector representations, validating the effectiveness of SAMVR for multimodal retrieval. These results establish SAMVR as a viable formulation for adaptive capacity allocation in multi-vector multimodal retrieval.