CORTEXA
← Browse
arxivcs.CV2026-07-16

Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding

Xiao Lin, Xiaohu Huang, Kai Han

Multimodal Large Language Models (MLLMs) have demonstrated substantial promise in spatial understanding. Existing works typically incorporate prior knowledge extracted from a pre-trained foundation model to further enhance the spatial awareness of MLLMs. In this paper, we first reveal that when integrating diverse foundation models into MLLMs, different models provide complementary spatial priors that benefit different tasks. Motivated by this, we propose $\textbf{ViPS}$, a novel multi-model prior framework designed to fully unleash the potential of incorporating multiple $\textbf{Vi}$sual $\textbf{P}$riors from diverse models into MLLMs for $\textbf{S}$patial understanding. Specifically, ViPS introduces an Efficient Prior Proxy to generate multiple foundational priors with minimal inference overhead, and a Dynamic Prior Fusion mechanism to achieve harmonious and context-aware prior fusion and injection from the prior proxies. Extensive experiments demonstrate that ViPS successfully harmonizes diverse visual priors, establishing new state-of-the-art performance across multiple complex spatial reasoning and 3D spatial understanding benchmarks. Project page: https://visual-ai.github.io/vips

View free PDFSource page

Related papers

arxivcs.CV2026-07-23

ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?

Han Li, Si Liu, Zehao Huang, Dongxin Lyu, Longfei Xu, Jiahui Fu, et al.

Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse expert-level tasks, but they still struggle with fundamental abilities that humans naturally develop through continuous observation of the real world, such as spatial perception and dynamic r…

View free PDFSource page
arxivcs.CV2026-07-22

Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?

Qiwei Ma, Chunping Qiu, Xinjun Cheng, Xiaoyu Zhang, Puhong Duan, Ke Yang, et al.

The rapid development of multimodal large language models (MLLMs) has introduced a flexible paradigm for remote sensing image scene understanding (RSISU), enabling natural-language interaction with remote sensing imagery. However, a systematic understanding of the capability boun…

View free PDFSource page
arxivcs.CVcs.AI2026-07-31

When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration

Kesheng Chen, Yamin Hu, Wenjian Luo

In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypical state. For example, a model may report that a visibly six-fingered hand has five fingers. We show that these errors are system…

View free PDFSource page
arxivcs.CV2026-07-24

RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understanding

Jianqin Liu, Weiwei Cao, Wanxing Chang, Ruifeng Yuan, Bowen Shi, Zhilin Zheng, et al.

Medical multimodal large language models (MLLMs) are increasingly expected to perform complex image understanding tasks, yet their reliability is often compromised by frequent errors in visual interpretation. To systematically trace these failures, we traverse the hierarchy from…

View free PDFSource page
arxivcs.CV2026-07-23

Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models

Mingyu Wang, Weilin Jin, Wenbo Li, Haoyang Huang, Tong Jia, Ying Li

Despite remarkable progress in visual understanding, Multimodal Large Language Models (MLLMs) remain prone to hallucinations when reasoning about spatial relationships, often producing judgments that contradict the true 3D structure of the scene. Though several existing works hav…

View free PDFSource page
arxivcs.CV2026-07-31

MoRoute: Dynamic Routing for In-Context Multimodal Video Generation

Chong Gao, Jie Ma, Zhan Peng, Chongxiao Wang, Haoxue Wu, Jun Liang, et al.

Multimodal video generation aims to generate and edit videos conditioned on arbitrary combinations of text, images, and videos within a single model, allowing diverse tasks to share complementary data and generative priors. Unifying these tasks requires multimodal understanding o…

View free PDFSource page