Institution profile

City College of New York

Academic institutionnorthamerica · us
Official website
Research library47linked papers
Opportunities0open roles
Selected work

Representative Papers

Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages

Aug 12, 2026

This study addresses the systemic neglect of low-resource languages in current AI infrastructure across data curation, tokenization, evaluation, and deployment, which exacerbates educational and linguistic inequities. Focusing on Bengali as a case study, the work integrates multilingual corpus analysis, tokenization efficiency benchmarks, internet penetration statistics, and modeling of educational resource accessibility to expose structural barriers: extreme training data scarcity (with an English-to-Bengali data ratio of 67:1), high tokenization overhead due to syllabic orthography, limited online content, and a pronounced rural–urban digital divide. The research reframes data scarcity not merely as a technical bottleneck but as a manifestation of structural injustice and advocates for an “offline-first” infrastructure design paradigm to advance linguistic equity and foster more inclusive AI development.

0 citationsRead paper

Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage Analysis

Aug 09, 2026

This work addresses the challenges of reliable damage assessment under adverse lighting and weather conditions, where conventional vision-based methods often fail and language models are prone to hallucination due to insufficient grounding in domain-specific documentation. To overcome these limitations, the authors propose a unified multimodal AI system that integrates retrieval-augmented generation (RAG), knowledge graphs, thermal-infrared and visible-light imaging, and wireless signal sensing. A novel hybrid retrieval mechanism combining graph-structured and vector-based representations is introduced to enhance cross-document reasoning. Additionally, a vision-language model generates synthetic damage data to augment training. Experimental results demonstrate that dynamic retrieval significantly improves factual consistency, graph-based retrieval outperforms purely vector-based approaches, and multimodal fusion effectively mitigates the constraints of individual sensors, collectively enhancing damage classification accuracy.

0 citationsRead paper

Damage Classification for 3D Point Cloud Data via 3D Data Analysis and Vision Foundation Model-based 2D Projections

Aug 09, 2026

This study addresses the challenges of high computational cost and scarce labeled data in fine-grained damage classification of 3D point clouds by proposing two novel approaches. The first, termed 3PDA, leverages topological data analysis (TDA) to extract compact geometric features and integrates anomaly detection to achieve high-accuracy yet computationally intensive assessment. The second, 2PDA, projects point clouds into multi-view 2D images and employs vision foundation models (VFMs) for efficient classification. This work is the first to introduce TDA and VFMs into 3D and 2D damage analysis, respectively, and systematically evaluates their trade-offs in accuracy, efficiency, and generalization. While 3PDA achieves superior accuracy on specific structures, 2PDA offers nearly an order-of-magnitude speedup at a slight cost in precision and demonstrates stronger generalization across a broader range of damage categories.

0 citationsRead paper
Recent publications

Latest Papers

Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages

Aug 12, 2026

This study addresses the systemic neglect of low-resource languages in current AI infrastructure across data curation, tokenization, evaluation, and deployment, which exacerbates educational and linguistic inequities. Focusing on Bengali as a case study, the work integrates multilingual corpus analysis, tokenization efficiency benchmarks, internet penetration statistics, and modeling of educational resource accessibility to expose structural barriers: extreme training data scarcity (with an English-to-Bengali data ratio of 67:1), high tokenization overhead due to syllabic orthography, limited online content, and a pronounced rural–urban digital divide. The research reframes data scarcity not merely as a technical bottleneck but as a manifestation of structural injustice and advocates for an “offline-first” infrastructure design paradigm to advance linguistic equity and foster more inclusive AI development.

0 citationsRead paper

Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage Analysis

Aug 09, 2026

This work addresses the challenges of reliable damage assessment under adverse lighting and weather conditions, where conventional vision-based methods often fail and language models are prone to hallucination due to insufficient grounding in domain-specific documentation. To overcome these limitations, the authors propose a unified multimodal AI system that integrates retrieval-augmented generation (RAG), knowledge graphs, thermal-infrared and visible-light imaging, and wireless signal sensing. A novel hybrid retrieval mechanism combining graph-structured and vector-based representations is introduced to enhance cross-document reasoning. Additionally, a vision-language model generates synthetic damage data to augment training. Experimental results demonstrate that dynamic retrieval significantly improves factual consistency, graph-based retrieval outperforms purely vector-based approaches, and multimodal fusion effectively mitigates the constraints of individual sensors, collectively enhancing damage classification accuracy.

0 citationsRead paper

Damage Classification for 3D Point Cloud Data via 3D Data Analysis and Vision Foundation Model-based 2D Projections

Aug 09, 2026

This study addresses the challenges of high computational cost and scarce labeled data in fine-grained damage classification of 3D point clouds by proposing two novel approaches. The first, termed 3PDA, leverages topological data analysis (TDA) to extract compact geometric features and integrates anomaly detection to achieve high-accuracy yet computationally intensive assessment. The second, 2PDA, projects point clouds into multi-view 2D images and employs vision foundation models (VFMs) for efficient classification. This work is the first to introduce TDA and VFMs into 3D and 2D damage analysis, respectively, and systematically evaluates their trade-offs in accuracy, efficiency, and generalization. While 3PDA achieves superior accuracy on specific structures, 2PDA offers nearly an order-of-magnitude speedup at a slight cost in precision and demonstrates stronger generalization across a broader range of damage categories.

0 citationsRead paper