Geometric Bias

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 23

All topics

T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block Models
Sep 30, 2026Serena Grazia De Benedictis, Andersen Ang, Nicoletta Del Buono +2Topology Geometric Bias
Department of Mathematics, University of Bari Aldo Moro, Italy
Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning
Sep 30, 2026Joan PerezGeometric Bias Faithfulness
Urban Geo Analytics
Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection
Sep 7, 2026Manwen Yang, Leqian Ding, Yu Guo +1Abnormality Zero-Shot
School of Software Engineering, Xi’an Jiaotong University · State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
S $^2$ Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models
Sep 1, 2026Yuanyuan Jia, Shunpu Tang, Qianqian YangVisual Token Pruning Multimodal Large Language Models
College of Information Science and Electronic Engineering, Zhejiang University Hangzhou, China
Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models
Aug 12, 2026Shukrullo Nazirjonov, Sai Prasanna, Anna Manasyan +1Object-Centric Representations World Models
University of Tuebingen · Max Planck Institute for Intelligent Systems
Evaluating Regional Bias in LLMs From Abstract Stereotype to Concrete Social Decision-Making
Jul 29, 2026Jiayuan Di, Haoyi Yang, Yufei Luo +2Stereotype Mitigation Geometric Bias
East China University of Science and Technology · Mohamed bin Zayed University of Artificial Intelligence · Beijing University of Posts and Telecommunications +2
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Jul 8, 2026Weicheng Ma, John Guerrerio, Soroush VosoughiStereotype Mitigation Multilingual Benchmark
College of Computing, Georgia Institute of Technology · Computer Science Department, Dartmouth College
Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation
Jul 8, 2026Veronika Shilova, Emmanuel Malherbe, Giovanni Palma +3Blind Face Restoration Humanml3D
Artefact Research Center, Paris, France · Institut de Mathématique de Toulouse, CNRS, Toulouse, France · L’Oréal Recherche et Innovation, Paris, France +2
Do Location Encoders Capture Spatial Effects? A GeoShapley Benchmark Across Scales
Jun 22, 2026Daniel Kiv, Shaowen WangGeometric Bias Encoders
Siebel School of Computing & Data Science, University of Illinois Urbana-Champaign Urbana, IL, USA · Department of Geography & GIS and Siebel School of Computing & Data Science, University of Illinois Urbana-Champaign Urbana, IL, USA
Unintended Effects of Geographic Conditioning in Large Language Models
Jun 16, 2026Naz Col, David M. ChanGeometric Bias Large Language Model Bias
University of California, Berkeley
Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivoting
Jun 13, 2026Xinze ZhangUrban Environments Geometric Bias
University of Southern California, Los Angeles, CA 90007, USA
Geometric bias in eigenspace perturbation under random heterogeneous noise
Jun 9, 2026Fengkai Liu, Ke Wang, Wanjie WangSpectral Decomposition Low-Rank Structure
Department of Mathematics, Hong Kong University of Science and Technology · Department of Statistics and Data Science, National University of Singapore
Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
Jun 1, 2026Chuang Ma, Qianying Liu, Tomoyuki Obuchi +6Multimodal Large Language Models Large Language Models Fail
Kyoto University · NII LLMC · RIKEN AIP +4
Assessing socio-economic climate impacts from text data
May 20, 2026Mariana Madruga de Brito, Brielen Madureira, Taís Maria Nunes Carvalho +15Disaster Response Text-Driven
Helmholtz Centre for Environmental Research, Germany · Leipzig University, Germany · UCLouvain Brussels, Belgium +12
How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence
May 19, 2026Yue Chen, Yihao Wang, Ziyi Tang +2Document Parsing Model Auditing
Sun Yat-sen University · Chaotic Pendulum Lab · Nanyang Technological University
How Loud Rumbles Hit Newsstands: A Data Analysis of Coverage and Spatial Bias in German News about Landslides Around the World
May 18, 2026Brielen Madureira, Andreas Niekler, Marc Keuschnigg +1Landslides Headlines
LeipzigLab – Climate Discourse, Leipzig University, Germany · Helmholtz Centre for Environmental Research, Germany · Computational Humanities, Leipzig University, Germany +2
Understanding and Accelerating the Training of Masked Diffusion Language Models
May 13, 2026Chunsan Hong, Sanghyun Lee, Chieh-Hsin Lai +5Masked Diffusion Language Models Language Modeling
1KAIST · 2Sony AI · University of Tokyo +1
Geolocating News about Extreme Climate Events: A Comparative Analysis of Off-the-Shelf Tools for Toponym Identification in German
May 5, 2026Brielen Madureira, Mariana Madruga de Brito, Andreas NieklerGerman Named-Entity Recognition
LeipzigLab - Climate Discourse, Leipzig University, Leipzig, Germany · Helmholtz Centre for Environmental Research - UFZ, Leipzig, Germany · Leipzig University, Leipzig, Germany +1
Geospatial foundation-model embeddings improve population estimation unevenly across space and scale
May 3, 2026Wenbin Zhang, Eimear Cleary, Francisco Rowe +4Geospatial Foundation Models Populations
WorldPop, School of Geography and Environmental Sciences, University of Southampton, United Kingdom · Geographic Data Science Lab, Department of Geography and Planning, School of Environmental Sciences, University of Liverpool, United Kingdom
Geographic Bias and Diversity in AI Evaluation
Apr 28, 2026Zilong Liu, Krzysztof Janowicz, Gengchen Mai +2Geometric Bias Large Language Model Bias
University of Vienna, Austria · University of Texas at Austin, USA · University of Wisconsin-Madison, USA +1
Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
Apr 23, 2026Joseba Fernandez de Landa, Carla Perez-Almendros, Jose Camacho-ColladosLarge Language Model Bias Natural Language Datasets
HiTZ Center - Ixa, University of the Basque Country EHU · Cardiff University
CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
Feb 10, 2026Zhenyu Yu, Chunlei Meng, Yangchen Zeng +3Recommendation Quality Location
College of Computer Science and Artificial Intelligence Fudan University Shanghai, China · College of Intelligent Robotics and Advanced Manufacturing Fudan University Shanghai, China · School of Cyber Science and Engineering Southeast University Nanjing, China +2
GeoGR^2:Zero-Shot Geospatial Inference via Geostatistically-Guided Iterative Refinement with LLMs
Aug 6, 2025Jinfan Tang, Kunming Wu, Xieruifeng Gong +4Geospatial Reasoning Geogs-Slam
College of Computer Science, Sichuan University · National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University · College of Life Science, Sichuan University

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block Models

Serena Grazia De Benedictis, Andersen Ang, Nicoletta Del Buono, Flavia Esposito+1

Department of Mathematics, University of Bari Aldo Moro, Italy

Topology Geometric Bias

Open paper AskPDF arXiv

In this work, we introduce a new clustering method, namely T-ARC (Topology-Aware Randomized Clustering), that corrects the geometric bias of K-means by embedding topological information directly into the optimization objective. Building on the assumption that the data admits an underlying hidden structure modeled via a latent graph, the idea is to uncover this information through the interplay between the standard K-means data-fidelity term and a graph-cut penalty, which discourages cluster assignments inconsistent with the connectivity structure of the data. To render this coupling tractable, the latent graph is modeled as a random realization from a Stochastic Block Model (SBM), whose scalar parameter is optimized within a Distributionally Robust Optimization (DRO) framework, yielding a closed-form proximal update. Both SBM and DRO are informed by a persistence-based similarity matrix derived from zero-dimensional persistent homology (

H_0

), which translates the multiscale connectivity structure of the data into a pairwise topological prior. The overall optimization proceeds via Block Coordinate Descent; convergence is established through a global Lyapunov functional: the deterministic blocks satisfy monotonic descent, while the stochastic graph update satisfies descent in expectation, so that the expected energy converges. Experiments on synthetic datasets with non-convex geometries and on random subsets of Fashion-MNIST show that T-ARC recovers latent topological structures where K-means fails, achieving the highest accuracy on curved and interleaved clusters while remaining competitive, and markedly more stable than K-means, on real data.

Momentum

Related topics

Latest papers 23