cs.CVNov 15, 2026

When Does Reusing Layers Help Multimodal Embeddings?

Authors: Zhizhang Hu, Yue Zhang

Organizations: Amazon · University of California, Merced

Abstract

We ask whether a compact universal multimodal embedding models can produce better search embeddings by running the same layers again. Looped transformers add computation with nearly unchanged model size, making them an appealing alternative to a larger encoder. Their success in language-model reasoning and recent use for retrieval motivate the idea, but higher retrieval scores alone do not reveal what an extra pass contributes. We study eleven loop designs and training variants on three checkpoints of one vision-language architecture. Our protocol distinguishes whether a model uses its extra pass, whether its image states respond to the query, and whether those updates improve retrieval. We prove that an image placed before the query remains query-independent through repeated layers when information only travels forward. We then open a query-to-image path in three ways, including order-alternating recurrence, which places the query first on the next pass. Each path produces query-sensitive image states. For bidirectional attention and order alternation, freezing later visual updates does not lower accuracy. On all 78 datasets of the Massive Multimodal Embedding Benchmark version 2 (MMEB-V2), a standard added loop loses 0.46 points against its trained control; an intermediate generative stage changes the effect to +0.36. A model pretrained with recurrence gains +4.23 points over its own loop-removed control and benefits from query-conditioned image updates when answering visual questions or locating objects from text.

Figures & tables

Explore similar work

Jul 30, 2026

ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding

Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding or add computation through explicit rationale tokens and latent autoregressive states. Although token expansion can improve complex matching, serial generation increases retrieval latency and makes the final embedding depend on generated intermediate states. This raises a different question: can useful computation be expanded along model depth while keeping the token workspace fixed? We analyze positive-negative similarity separation at every layer of independently trained UME models and observe a shared progression: early layers contextualize multimodal inputs, a contiguous middle-to-late stage forms retrieval-discriminative features, and the final layers map them into the embedding space. Based on this finding, we propose ReLoop-UME, which executes the early layers once, recurrently reuses a parameter-shared retrieval-forming block, and applies the final mapping layers after the last loop. Learnable Retrieval Registers provide persistent retrieval-specific states that accumulate and exchange evidence across loops, with the final register serving as the embedding readout. On MMEB-V2 and MRMR, ReLoop-UME consistently improves retrieval across different backbones while running 44.9x faster than UME-R1 and 1.5x faster than PLUME.
Nov 4, 2026

Loop Before You Leap: What Recurrent Depth Can and Cannot Buy in Data-Limited Pretraining

Multimodal models have often scored below text-only baselines in the BabyLM Challenge (Klerings et al., 2024; Takmaz et al., 2025). We test whether additional recurrent computation helps close this gap. Recurrence increases computation by reusing layers without adding parameters or training data. Using a single implementation, we compare standard and looped Transformers under a 100M-word budget, with three seeds per main condition. Each image is represented by one feature vector from a frozen DINOv2 encoder, used as a prefix token. Caption words count toward the budget, so multimodal training also changes the language data. In a pre-registered text-only comparison, a 12-layer stack repeated four times exceeds a standard 48-layer Transformer by 5.4 BLiMP percentage points at matched inference compute. However, multimodal training lowers BLiMP accuracy by about 3.8 points in both architectures, with no clear mitigation from recurrence. An exploratory loop-side no-image control, trained with the multimodal language data and batching schedule, scores 5.7 points below the text-only baseline. Adding the visual prefix raises accuracy by 1.85 points on average, but this contrast is uncertain with three seeds. These results suggest that changes in language data and its presentation are a major source of the drop. Diagnostic tests show that the models use visual information; its contribution to grammatical generalization remains uncertain under this single-vector interface.
Sep 27, 2026

VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings

Universal multimodal retrieval requires compact embeddings that preserve task-relevant semantic information across diverse modalities. Prior works have incorporated latent reasoning into multimodal embedding learning to refine this information before embedding extraction. However, most existing approaches remain confined to deterministic latent paths, without exploring alternative trajectories to discover better embeddings. Thus, we propose VaME (Variational Multimodal Embeddings), a framework that models latent reasoning as a learnable distribution over trajectories. Specifically, we first introduce Variational Latent Reasoning (VLR) to enable autoregressive exploration in latent space, guided by answer reconstruction through a lightweight decoder. Meanwhile, we augment the original embedding-token readout with a latent-fused embedding to facilitate exploration during subsequent reinforcement learning. Finally, we optimize latent reasoning over stochastic variational trajectories through reinforcement learning, using Semantic Decoding Reward (SDR) to favor semantically meaningful trajectories with interpretable decoded outcomes. On the 78-task MMEB-V2 benchmark, spanning image, video, and visual-document retrieval, VaME outperforms most explicit CoT-based models and all latent-reasoning baselines. VaME also demonstrates robust performance on reasoning-intensive benchmarks such as MRMR, with substantial gains after reinforcement learning. Importantly, VaME achieves these gains with at least a 4.25x inference speedup over the deterministic latent autoregressive baselines. The code will be made publicly available.