CORTEXA
← Browse
arxivcs.CV2026-07-03

BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

Geng Li, Yuxin Peng

While Multimodal Large Language Models (MLLMs) demonstrate impressive general capabilities, they struggle with fine-grained perception in ultra-high-resolution (UHR) images, particularly for tiny objects in cluttered scenes. Existing methods face a dilemma: they either rely on inefficient prior-free scanning, or depend on static prior-driven heuristics that lack posterior correction to rectify initial model biases. To address this, we propose BVS (Bayesian Visual Search), a framework that formulates perception as a global optimization problem over a continuous spatial-scale manifold. Specifically, BVS bridges prior guidance with posterior correction: it utilizes an early-stop attention rollout of MLLM to construct reasoning-aware priors, while employing a scale-aware non-stationary kernel and GP-UCB to dynamically rectify noise and recover missing information in the prior through iterative local observations. We provide theoretical guarantees via sub-linear regret bounds, and extensive experiments demonstrate that BVS significantly outperforms state-of-the-art baselines with a superior trade-off between accuracy and efficiency.

View free PDFSource page

Related papers

arxivcs.CV2026-07-19

SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing

Kaiwen Jing, Ruixu Jia, Bingyao Li, Ruizhe Ou, Ming Wu, Chuang Zhang

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved remote sensing (RS) multimodal understanding. Language-conditioned segmentation is crucial for fine-grained target understanding in Unmanned Aerial Vehicle (UAV) videos. However, this task rem…

View free PDFSource page
arxivcs.CVcs.AI2026-07-17

SLAPBench: Benchmarking Multimodal Large Language Models for Four-Finger SLAP Fingerprint Verification

Bibesh Pyakurel, M. G. Sarwar Murshed

Four-finger SLAP fingerprints are flat live-scan impressions of the index, middle, ring, and little fingers of one hand, used for identity verification in border control and law enforcement. No benchmark has evaluated whether multimodal large language models (MLLMs) can verify id…

View free PDFSource page
arxivcs.CV2026-07-20

FlexiGrad: Adaptive Gradient Modulation for Hierarchical Fine-Grained Classification

Zilu Zhou, Dongliang Chang, Junhan Chen, Zhanyu Ma

Many fine-grained recognition tasks contain hierarchical labels such as order, family and species. Although this supervision should be beneficial, jointly optimising all levels often leads to unstable training because coarse and fine classifiers impose inconsistent gradients on t…

View free PDFSource page
arxivcs.CV2026-07-17

IoUPD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models

Xiuyuan Zhu, Ke Lu, Hao Wu, Zijin Du, Dongming Zhang, Jian Xue

Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prompt. While this interface is simple and compatible with instr…

View free PDFSource page
arxivcs.CVcs.AI2026-07-22

Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos

Penglei Sun, Yehua Huang, Zhuoli Tao, Xiang Li, Runwei Guan, Yaoxian Song, et al.

Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployment, the UAV must respond while it flies, so such perception runs in an online streaming manner, where frames arrive sequentially a…

View free PDFSource page
arxivcs.CVcs.CL2026-07-18

Can Multimodal Large Language Models Understand OCT?

Baochen Fu, Wenzhi Deng, Baihao Jin, Yang Li, Zihan Nie, Kailin Jiang, et al.

Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases. Although multimodal large language models (MLLMs) have demonstrated considerable potential in medical image analysis, existing benchmarks largely reduce OCT understanding…

View free PDFSource page