AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

GeoBayes: Probabilistic Image Geo-Localization Inference via Sequential Bayesian Updating

Weimin Shi, Xiang Li, Kaige Li, Junhao Fang, Qiang Zhou, Qichuan Geng, Zhong Zhou

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes GeoBayes, a sequential Bayesian updating framework that reduces confirmation bias in MLLM-based image geo-localization by probabilistically combining visual clues into location inference.

Problem

MLLMs for image geo-localization suffer from confirmation bias, committing early to possibly incorrect location guesses driven by visual clues with varied geographic likelihoods.

Approach

Treats geo-localization as sequential Bayesian updating over candidate locations, so that evidence from successive visual clues updates a posterior rather than locking in an early guess; described in the abstract as a no-training (training-free) approach.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace CoT with GeoBayes sequential Bayesian updatingQwen2.5-VL-7B · Im2GPS3Kaccuracy within 25km (%): 31.0 -> 34.7Improved
add visual objects (MCoT) to CoT (ablation)Qwen2.5-VL-7B · Im2GPS3Kaccuracy within 25km (%): 750km 70.4 -> 71.7; 25km 31.0 -> 26.3Mixed
add image-search RAG to MCoT (ablation)Qwen2.5-VL-7B · Im2GPS3Kaccuracy within 25km (%): 26.3 -> 25.8Hurt
calibrate likelihood with discrete support rating and confidence (ablation)GeoBayes · Im2GPS3Kaccuracy within 25km (%): 31.5 -> 31.9Improved
add centering term ln2(c-3) to likelihood (ablation)GeoBayes · Im2GPS3Kaccuracy within 25km (%): 31.9 -> 34.7Improved
add hierarchical transition (ablation)GeoBayes · Im2GPS3Kaccuracy within 25km (%): 31.5 -> 34.7Improved
add Enhance web search retrieval (ablation)GeoBayes · Im2GPS3Kaccuracy within 25km (%): 31.3 -> 34.7Improved
add Replace strategy (ablation)GeoBayes · Im2GPS3Kaccuracy within 25km (%): 33.2 -> 34.7Improved
add Backtrack strategy (ablation)GeoBayes · Im2GPS3Kaccuracy within 25km (%): 33.7 -> 34.7Improved
apply GeoBayes to Qwen2-VL-7BQwen2-VL-7B · Im2GPS3Kaccuracy within 25km (%): 29.9 -> 31.7Improved
apply GeoBayes to Qwen2.5-VL-7BQwen2.5-VL-7B · YFCC4Kaccuracy within 1km (%): 2.1 -> 4.9Improved
GeoBayes (training-free MLLM) versus classification/retrieval methods at street levelQwen2.5-VL-7B · Im2GPS3Kaccuracy within 1km (%): 14.1 (GeoCLIP) vs 6.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy