Publications

Characterizing the relationship between brain anatomical wiring and functional coordination remains a fundamental challenge in computational neuroscience. This difficulty primarily arises because structure-function coupling in the human brain is spatially heterogeneous, often localized to subnetworks, and inherently difficult to align across disparate representational modalities. To address this methodological gap, we introduce Orthogonal Sparse Subgraph Alignment (Ossa), a principled and interpretable framework designed to identify compact structural cliques that exhibit maximal concordance with functional connectivity (FC) across subjects. Within each FC-derived community, optimizes an alignment objective over an orthogonal transformation, which absorbs coordinate mismatch between the two connectivity modalities, and a sparse node-selection vector, which identifies the induced structural connectivity (SC) subgraph. Furthermore, we establish theoretical properties for the estimator, demonstrating its statistical consistency in recovering the true underlying SC clique within each functional community. Extensive empirical evaluations on simulated data, alongside analyses of the Adolescent Brain Cognitive Development (ABCD) baseline and longitudinal cohorts, demonstrate that successfully recovers aligned structural cliques under latent cross-modal rotations. Ultimately, the proposed methodology significantly improves out-of-sample SC-FC alignment over size-matched baselines and robustly identifies stable, single-core topological structures within human brain networks.

Electronic health records (EHR) pose large-scale multi-disease modeling problems in which many outcomes are rare and strongly influenced by shared risk factors. While modern approaches achieve strong predictive performance, they often treat diseases independently or rely on black-box architectures, offering limited insight into how risk factors organize disease risk and little principled uncertainty quantification. We introduce a Bayesian hypergraph inference framework that reframes multi-disease modeling around latent, risk-factor-modulated disease pathways. Risk factors act on hyperedges, latent disease subsets with shared risk patterns, allowing diseases to participate in multiple distinct pathways and enabling interpretable, higher-order structure beyond pairwise associations. A repulsion prior encourages parsimonious and identifiable structure, while posterior inference provides calibrated uncertainty over both disease groupings and risk-factor influence. To enable scalable inference on large EHR datasets, we develop a structured variational inference algorithm that preserves logical dependencies among hyperedge existence, disease membership, and pathway-level effects. Experiments on simulated data and UK Biobank demonstrate stable and interpretable disease pathway structure, well-calibrated uncertainty, improved estimation for rare diseases, and competitive predictive performance.

Sentence simplification aims to make complex text more accessible by reducing linguistic complexity while preserving the original meaning. However, progress in this area remains limited for mid-resource and low-resource languages due to the scarcity of high-quality data. To address this gap, we introduce the OasisSimp dataset, a multilingual dataset for sentence-level simplification covering five languages: English, Sinhala, Tamil, Pashto, and Thai. Among these, no prior sentence simplification datasets exist for Thai, Pashto, and Tamil, while limited data is available for Sinhala. Each language simplification dataset was created by trained annotators who followed detailed guidelines to simplify sentences while maintaining meaning, fluency, and grammatical correctness. We evaluate eight open-weight multilingual Large Language Models (LLMs) on the OasisSimp dataset and observe substantial performance disparities between high-resource and low-resource languages, highlighting the simplification challenges in multilingual settings. The OasisSimp dataset thus provides both a valuable multilingual resource and a challenging benchmark, revealing the limitations of current LLM-based simplification methods and paving the way for future research in low-resource sentence simplification.

We present a multi-way parallel corpus of Math Word Problems (MWPs) in nine languages, including six low-resource languages. To date, this is the largest multilingual MWP dataset available. We utilize this dataset and show the viability of using pre-trained multilingual sequence-sequence language models (prMSLMs) for autoregressive MWP generation in both monolingual and multilingual setups, particularly for low-resource languages. We also integrate a math constraint satisfaction module with autoregressive text generation. Our extensive evaluations identify several factors that affect autoregressive text generation on prMSLMs. These include language representation in the model, model size, existence of similar languages in the model, and language script. Overall, our results reveal that autoregressive MWP generation on top of prMSLMs is very promising, even for low-resource languages.

Despite the progress in building multilingual language models, evaluation is often limited to a few languages with available datasets which excludes a large number of low-resource languages. In this paper, we create SIB-200—a large-scale open-sourced benchmark dataset for topic classification in 205 languages and dialects to address the lack of evaluation dataset for Natural Language Understanding (NLU). For many of the languages covered in SIB-200, this is the first publicly available evaluation dataset for NLU. The dataset is based on Flores-200 machine translation corpus. We annotated the English portion of the dataset and extended the sentence-level annotation to the remaining 204 languages covered in the corpus. Despite the simplicity of this task, our evaluation in full-supervised setting, cross-lingual transfer setting and prompting of large language model setting show that there is still a large gap between the performance of high-resource and low-resource languages when multilingual evaluation is scaled to numerous world languages. We found that languages unseen during the pre-training of multilingual language models, languages from under-represented families (like Nilotic and Altantic-Congo), and languages from the regions of Africa, Americas, Oceania and South East Asia, often have the lowest performance on our topic classification dataset. We hope our dataset% will encourages a more inclusive evaluation of multilingual language models on a more diverse set of languages.

Digital technologies are being more widely used in education, allowing students all around the world to access individualized, high-quality educational resources. This paper analyzes a massive amounts of data derived from students’ interactions with these diagnostic questions can help us more accurately understand the students’ learning status and thus allow us to automate learning curriculum recommendations, as evidenced by thousands of examples of students’ answers to mathematics questions provided by The NeurlIPS 2020 Education Challenge [1, 2]. In this paper, a new generated model based on Item Response Theory (IRT) is put forward. Additionally, with discrimination parameter added and classification by groups, the model on real-world dataset is verified.