Yecheng Zhang

Rong Zhao, Wanqi Liu, Zhizhou Sha et al.

Large language models (LLMs) are increasingly used to describe, evaluate and interpret places, yet it remains unclear whether they do so from a culturally neutral standpoint. Here we test urban perception in frontier LLMs using a balanced global street-view sample and prompts that either remain neutral or invoke different regional cultural standpoints. Across open-ended descriptions and structured place judgments, the neutral condition proved not to be neutral in practice. Prompts associated with Europe and Northern America remained systematically closer to the baseline than many non-Western prompts, indicating that model perception is organized around a culturally uneven reference frame rather than a universal one. Cultural prompting also shifted affective evaluation, producing sentiment-based ingroup preference for some prompted identities. Comparisons with regional human text-image benchmarks showed that culturally proximate prompting could improve alignment with human descriptions, but it did not recover human levels of semantic diversity and often preserved an affectively elevated style. The same asymmetry reappeared in structured judgments of safety, beauty, wealth, liveliness, boredom and depression, where model outputs were interpretable but only partly reproduced human group differences. These findings suggest that LLMs do not simply perceive cities from nowhere: they do so through a culturally uneven baseline that shapes what appears ordinary, familiar and positively valued.

Yecheng Zhang, Rong Zhao, Zhizhou Sha et al.

Aligning vision-language model (VLM) outputs with human preferences in domain-specific tasks typically requires fine-tuning or reinforcement learning, both of which demand labelled data and GPU compute. We show that for subjective perception tasks, this alignment can be achieved without any model training: VLMs are already strong concept extractors but poor decision calibrators, and the gap can be closed externally. We propose a training-free post-hoc concept-bottleneck pipeline consisting of three tightly coupled stages: concept mining, multi-agent structured scoring, and geometric calibration, unified by an end-to-end dimension optimization loop. Interpretable evaluation dimensions are mined from a handful of human annotations; an Observer-Debater-Judge chain extracts robust continuous concept scores from a frozen VLM; and locally-weighted ridge regression on a hybrid visual-semantic manifold calibrates these scores against human ratings. Applied to urban perception as UrbanAlign, the framework achieves 72.2% accuracy ($κ=0.45$) on Place Pulse 2.0 across six categories, outperforming the best supervised baseline by +15.1 pp and uncalibrated VLM scoring by +16.3 pp, with full dimension-level interpretability and zero model-weight modification.

Yecheng Zhang, Huimin Zhao, Ying Long

Rapidly acquiring three-dimensional (3D) building data, including geometric attributes like rooftop, height and orientations, as well as indicative attributes like function, quality, and age, is essential for accurate urban analysis, simulations, and policy updates. Current building datasets suffer from incomplete coverage of building multi-attributes. This paper introduces a geospatial artificial intelligence (GeoAI) framework for large-scale building modeling, presenting the first national-scale Multi-Attribute Building dataset (CMAB), covering 3,667 spatial cities, 29 million buildings, and 21.3 billion square meters of rooftops with an F1-Score of 89.93% in OCRNet-based extraction, totaling 337.7 billion cubic meters of building stock. We trained bootstrap aggregated XGBoost models with city administrative classifications, incorporating features such as morphology, location, and function. Using multi-source data, including billions of high-resolution Google Earth images and 60 million street view images (SVIs), we generated rooftop, height, function, age, and quality attributes for each building. Accuracy was validated through model benchmarks, existing similar products, and manual SVI validation, mostly above 80%. Our dataset and results are crucial for global SDGs and urban planning.

Junhao Xia, Chaoyang Zhang, Yecheng Zhang et al.

Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and training-free methods. While training-based methods incur high computational costs, training-free alternatives often yield suboptimal performance. To address these limitations, we propose DAPE, a high-quality yet cost-effective two-stage parameter-efficient fine-tuning (PEFT) framework for video editing. In the first stage, we design an efficient norm-tuning method to enhance temporal consistency in generated videos. The second stage introduces a vision-friendly adapter to improve visual quality. Additionally, we identify critical shortcomings in existing benchmarks, including limited category diversity, imbalanced object distribution, and inconsistent frame counts. To mitigate these issues, we curate a large dataset benchmark comprising 232 videos with rich annotations and 6 editing prompts, enabling objective and comprehensive evaluation of advanced methods. Extensive experiments on existing datasets (BalanceCC, LOVEU-TGVE, RAVE) and our proposed benchmark demonstrate that DAPE significantly improves temporal coherence and text-video alignment while outperforming previous state-of-the-art approaches.