SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.10477 · 2026

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

Yu Wang, Xiangxiang Chu, Rui Dai, Yi Wang, Yujie Wang, Kaikui Liu, Yansheng Li, Soccer Field, Socio Reasoner

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
AMAP-ML/SocioReasoner canonical 1 of 7
FunctionStatusWhere it lives
filter_forward_args Ran AMAP-ML/SocioReasoner/roll/models/func_providers.py
code served (permissive licence) · get_code("a063873313ec0a07")
distributed_concat Not yet run AMAP-ML/SocioReasoner/mcore_adapter/src/mcore_adapter/utils.py
code served (permissive licence) · get_code("a940969bae605850")
distributed_reduce Not yet run AMAP-ML/SocioReasoner/mcore_adapter/src/mcore_adapter/utils.py
code served (permissive licence) · get_code("9b40061bc20d82e3")
get_checkpoint_tracker_filename Not yet run AMAP-ML/SocioReasoner/mcore_adapter/src/mcore_adapter/checkpointing.py
code served (permissive licence) · get_code("92a8337ca2e3095a")
get_logger Not yet run AMAP-ML/SocioReasoner/mcore_adapter/src/mcore_adapter/utils.py
code served (permissive licence) · get_code("0ca242314116dc9c")
no_set_device_hook_post_init Not yet run AMAP-ML/SocioReasoner/roll/models/trl_patches.py
code served (permissive licence) · get_code("414bb5321e52ac1b")
read_metadata Not yet run AMAP-ML/SocioReasoner/mcore_adapter/src/mcore_adapter/checkpointing.py
code served (permissive licence) · get_code("ba3f7804e93d016e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. The dataset and code are open-sourced under the Apache License 2.0 at github.com/AMAP-ML/SocioReasoner.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.10477")
get_code_for_paper("2601.10477")
have("2601.10477")

Connect an agent — have() is free.