Selected work

Representative Papers

SignaApp a modern alternative to support signwriting notation for sign languages

Oct 25, 2025

No mobile applications currently exist that support SignWriting symbol editing and composition for Deaf users. This study employs a user-centered design (UCD) methodology to develop and implement, for the first time, an Android-specific SignWriting mobile editor tailored to Deaf individuals across multiple age groups—including children, adolescents, and adults. The application integrates core functionalities: symbol input, compositional editing, document saving, and sharing. Iterative usability testing with Deaf participants from diverse age cohorts informed continuous interface refinement. Deployed on Google Play, the application demonstrates high usability and strong community acceptance, as validated through empirical evaluation. It effectively bridges a critical gap in mobile accessibility for sign language writing and provides a scalable technical framework supporting digital inclusion and equitable communication for Deaf users.

0 citationsRead paper

Are UX evaluation methods truly accessible

Aug 11, 2025

Current user experience (UX) evaluation methods inadequately address accessibility for Deaf users, largely overlooking linguistic and perceptual diversity. Method: Through critical literature review, empirical testing, and multimodal UX assessment techniques, this study evaluates the real-world applicability of existing “deaf-friendly” evaluation protocols. Contribution/Results: Findings reveal that mainstream methods rely excessively on auditory input and linear cognitive assumptions, neglecting sign language as a primary language, visual-dominant perception, and bilingual communication patterns—leading to distorted data collection and participatory barriers. The study introduces the novel “communicative accessibility” framework, exposing systemic deficiencies across perception, comprehension, and feedback dimensions. It argues for methodological reconstruction grounded in Deaf language acquisition principles and interactional norms. This work provides both theoretical foundations and practical guidelines for developing inclusive, psychometrically sound UX evaluation paradigms for Deaf users.

0 citationsRead paper

AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models

May 25, 2025

Existing mathematical reasoning benchmarks are predominantly English-based or translation-derived, risking semantic drift and obscuring language-specific reasoning deficiencies. Method: We introduce AI4Math—the first natively authored Spanish-language university-level mathematical reasoning benchmark—comprising 105 original problems spanning seven domains (e.g., algebra, calculus, geometry) with expert-annotated step-by-step solutions. It enables robust cross-lingual analysis without translation artifacts. We conduct bilingual (Spanish/English) zero-shot and chain-of-thought evaluations on state-of-the-art models including GPT-4o, DeepSeek-R1/V3, DeepSeek-o3 mini, and LLaMA-3.3. Contribution/Results: Top-performing models achieve >70% accuracy on Spanish tasks; notably, GPT-4o attains higher zero-shot accuracy in Spanish than in English. However, performance drops sharply (<40%) on geometry, combinatorics, and probability problems—revealing persistent domain-specific weaknesses. AI4Math thus provides a linguistically grounded, domain-diverse resource for probing multilingual mathematical reasoning capabilities.

0 citationsRead paper

Recent publications

Latest Papers

SignaApp a modern alternative to support signwriting notation for sign languages

Oct 25, 2025

No mobile applications currently exist that support SignWriting symbol editing and composition for Deaf users. This study employs a user-centered design (UCD) methodology to develop and implement, for the first time, an Android-specific SignWriting mobile editor tailored to Deaf individuals across multiple age groups—including children, adolescents, and adults. The application integrates core functionalities: symbol input, compositional editing, document saving, and sharing. Iterative usability testing with Deaf participants from diverse age cohorts informed continuous interface refinement. Deployed on Google Play, the application demonstrates high usability and strong community acceptance, as validated through empirical evaluation. It effectively bridges a critical gap in mobile accessibility for sign language writing and provides a scalable technical framework supporting digital inclusion and equitable communication for Deaf users.

0 citationsRead paper

Are UX evaluation methods truly accessible

Aug 11, 2025

Current user experience (UX) evaluation methods inadequately address accessibility for Deaf users, largely overlooking linguistic and perceptual diversity. Method: Through critical literature review, empirical testing, and multimodal UX assessment techniques, this study evaluates the real-world applicability of existing “deaf-friendly” evaluation protocols. Contribution/Results: Findings reveal that mainstream methods rely excessively on auditory input and linear cognitive assumptions, neglecting sign language as a primary language, visual-dominant perception, and bilingual communication patterns—leading to distorted data collection and participatory barriers. The study introduces the novel “communicative accessibility” framework, exposing systemic deficiencies across perception, comprehension, and feedback dimensions. It argues for methodological reconstruction grounded in Deaf language acquisition principles and interactional norms. This work provides both theoretical foundations and practical guidelines for developing inclusive, psychometrically sound UX evaluation paradigms for Deaf users.

0 citationsRead paper

AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models

May 25, 2025

Existing mathematical reasoning benchmarks are predominantly English-based or translation-derived, risking semantic drift and obscuring language-specific reasoning deficiencies. Method: We introduce AI4Math—the first natively authored Spanish-language university-level mathematical reasoning benchmark—comprising 105 original problems spanning seven domains (e.g., algebra, calculus, geometry) with expert-annotated step-by-step solutions. It enables robust cross-lingual analysis without translation artifacts. We conduct bilingual (Spanish/English) zero-shot and chain-of-thought evaluations on state-of-the-art models including GPT-4o, DeepSeek-R1/V3, DeepSeek-o3 mini, and LLaMA-3.3. Contribution/Results: Top-performing models achieve >70% accuracy on Spanish tasks; notably, GPT-4o attains higher zero-shot accuracy in Spanish than in English. However, performance drops sharply (<40%) on geometry, combinatorics, and probability problems—revealing persistent domain-specific weaknesses. AI4Math thus provides a linguistically grounded, domain-diverse resource for probing multilingual mathematical reasoning capabilities.

0 citationsRead paper