{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/recognition-through-reasoning-reinforcing","title":"Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models","arxiv_id":"2506.14674","date":"2025-06-17","proceeding":null,"authors":["Ling Li","Yao Zhou","Yuxuan Liang","Fugee Tsung","Jiaheng Wei"],"abstract":"Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and constrained viewpoints. On the modeling side, current approaches predominantly rely on supervised fine-tuning, which yields only marginal improvements in reasoning capabilities. To address these challenges, we propose a novel pipeline that constructs a reasoning-oriented geo-localization dataset, MP16-Reason, using diverse social media images. We introduce GLOBE, Group-relative policy optimization for Locatability assessment and Optimized visual-clue reasoning, yielding Bi-objective geo-Enhancement for the VLM in recognition and reasoning. GLOBE incorporates task-specific rewards that jointly enhance locatability assessment, visual clue reasoning, and geolocation accuracy. Both qualitative and quantitative results demonstrate that GLOBE outperforms state-of-the-art open-source LVLMs on geo-localization tasks, particularly in diverse visual scenes, while also generating more insightful and interpretable reasoning trajectories.","url_abs":"https://arxiv.org/abs/2506.14674v1","url_pdf":"https://arxiv.org/pdf/2506.14674v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"geo-localization","task_name":"geo-localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.14674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14674"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/lingli1996/GLOBE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":4},"by_repo_kind":{"found_in_text":{"samples":6,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b40d46077f78e7de","entry":"ce_loss_func","repo":"lingli1996/GLOBE","repo_kind":"found_in_text","path":"swift/plugin/loss.py","file_url":"https://github.com/lingli1996/GLOBE/blob/HEAD/swift/plugin/loss.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b40d46077f78e7de"}},{"code_sha256_prefix":"974f5e5ea25a6532","entry":"lora_state_dict","repo":"lingli1996/GLOBE","repo_kind":"found_in_text","path":"swift/tuners/lora_layers.py","file_url":"https://github.com/lingli1996/GLOBE/blob/HEAD/swift/tuners/lora_layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"974f5e5ea25a6532"}},{"code_sha256_prefix":"91b83749f4c26936","entry":"get_model_arch","repo":"lingli1996/GLOBE","repo_kind":"found_in_text","path":"swift/llm/model/model_arch.py","file_url":"https://github.com/lingli1996/GLOBE/blob/HEAD/swift/llm/model/model_arch.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91b83749f4c26936"}},{"code_sha256_prefix":"4b35155697e70ad7","entry":"loss_scale_func","repo":"lingli1996/GLOBE","repo_kind":"found_in_text","path":"swift/plugin/loss.py","file_url":"https://github.com/lingli1996/GLOBE/blob/HEAD/swift/plugin/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b35155697e70ad7"}},{"code_sha256_prefix":"50fa7d453426dfd7","entry":"patch_output_clone","repo":"lingli1996/GLOBE","repo_kind":"found_in_text","path":"swift/llm/model/patcher.py","file_url":"https://github.com/lingli1996/GLOBE/blob/HEAD/swift/llm/model/patcher.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50fa7d453426dfd7"}},{"code_sha256_prefix":"5a3ac54293be7e23","entry":"register_loss_func","repo":"lingli1996/GLOBE","repo_kind":"found_in_text","path":"swift/plugin/loss.py","file_url":"https://github.com/lingli1996/GLOBE/blob/HEAD/swift/plugin/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a3ac54293be7e23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}