Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
Abstract
Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence into discrete textual thoughts, creating an information bottleneck for fine-grained perception. Recent latent visual reasoning methods attempt to reason in continuous hidden states, but we find that they suffer from insufficient manifold compatibility: latent trajectories drift away from pretrained reasoning circuits, collapse into instance-agnostic patterns, and are often bypassed during answer generation. To address these issues, we propose RIS (Retrieve, Integrate, and Synthesize), a spatial-semantic grounded framework that develops latent reasoning as a compatible extension of pretrained MLLM computation. We first construct a step-wise grounded reasoning dataset with bounding boxes and region-specific semantic descriptions. Built on this supervision, RIS anchors latent tokens to both spatial and semantic evidence, enforces their causal role through a progressive attention bottleneck, and introduces short language transition tokens to bridge synthesized latent states back to vocabulary-aligned decoding. Experiments on V*, HRBench4K, HRBench8K, MMVP, and BLINK show consistent improvements over closed/open-source and latent reasoning baselines. Further analyses demonstrate that RIS learns diverse, interpretable, and progressively integrated latent trajectories, offering a practical path toward faithful internal visual reasoning in MLLMs.
Cite
@article{arxiv.2605.07106,
title = {Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning},
author = {Jin Cui and Xinyue Long and Xunyong Zhang and Yadong Zhang and Chuanchang Su and Jingye Gan and Boran Zhao and Pengju Ren},
journal= {arXiv preprint arXiv:2605.07106},
year = {2026}
}
Comments
19 pages, 8 figures