Philippines

We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages In One Network (SEA-LION) models built upon NVIDIA Nemotron 3. The family includes 30B-A3B and 120B-A12B models, with both continued-pretrained base checkpoints and post-trained variants. We adapt the models using Southeast Asian, reasoning, code, and multilingual parallel data, followed by post-training with supervised fine-tuning and online on-policy distillation. On SEA-HELM, the 30B-A3B model improves the overall SEA score from 46.06 to 51.57, while the 120B-A12B model improves from 49.30 to 63.44. Across seven Southeast Asian languages, we observe broad capability gains with the 120B-A12B model showing broader and more consistent improvements across tasks.

The rapid advancement of audio and multimodal large language models has unlocked transformative speech understanding capabilities, yet evaluation frameworks remain predominantly English-centric, leaving Southeast Asian (SEA) languages critically underrepresented. We introduce SEA-SpeechBench, to the best of our knowledge, the first large-scale multitask benchmark that evaluates speech understanding in 11 SEA languages through 97,194 samples across 99 evaluation sets and 597 hours of curated audio data. Our benchmark comprises 9 diverse tasks across 3 categories: speech processing (automatic speech recognition, speech translation, spoken question answering), paralinguistic analysis (emotion, gender, age, speaker recognition), and temporal understanding, a novel dimension featuring timestamped content queries and temporal localization within extended audio sequences up to 3 minutes. We implement multilingual prompting in both native SEA languages and English to reflect user interactions with audio-language models. Evaluation of leading open-source and proprietary systems reveals marked performance gaps. Across all models, performance remains underwhelming on temporal understanding, emotion recognition, and speech translation. Prompting in low-resource languages such as Burmese and Tamil lags behind English by up to 41 percentage points. Our findings expose critical model limitations and underscore the need for inclusive model development. The SEA-SpeechBench benchmark is available at https://zwenyu.github.io/SEA-SpeechBench/.

Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vision-language models still lack. We introduce MemeCULT-1K, a multilingual benchmark of 1,000 South Asian memes in Bengali, English, and Hindi, where each meme is paired with a cultural context note and three human-written explanations, along with a supplementary set of 54 Bengali regional dialect memes. We evaluate thirteen popular Vision Language Models (VLMs) under two settings: meme-only and context-aware. Providing minimal cultural context yields consistent gains across all models and languages: mean SBERT similarity improves from 44.6 to 56.4 (+11.8), BLEURT from 37.3 to 42.3 (+5.0), and LLM-as-a-Judge scores from 2.57 to 3.43 out of 5 (+0.86). Fine-grained error analysis reveals that closed-source models fail mainly on entity and reference misidentification, while open-source models are bottlenecked by broader cultural knowledge gaps, with linguistic and phonological failures proving the most context-resistant across both. These results highlight the difficulty of culturally grounded meme understanding and motivate future work on explicit cultural knowledge integration. Our dataset and code are publicly available at TawsifDipto17/MemeCULT-1K.

Image geolocation aims to infer the geographic origin of an image from visual content alone. However, this task remains challenging in regions where countries share similar urban, roadside, architectural, and environmental characteristics. Many existing geolocation models focus on coordinate level prediction or classification performance while providing limited insight into how visual evidence contributes to location predictions. This study presents an explainable country level image geolocation pipeline for 11 ASEAN countries. First, we collected 4,850 images from GeoGuessr style sources, Google Images, and additional street level imagery. We then evaluated three approaches on this dataset: CLIP zero shot classification, a LightGBM classifier, and an MLP classifier. The MLP achieved the best test performance, attaining an accuracy and F1 score of 85.91%. For explainability, predictions generated by the MLP classifier were analyzed post hoc using CLIP attention rollout, YOLO26 object detection on the original images, and Energy Based Pointing Game (EBPG) overlap metrics. Object level analysis indicates that frequently detected objects are not necessarily associated with the highest attention density, suggesting that object frequency and attention based visual evidence capture different aspects of a scene. These results demonstrate that the proposed model can support accurate regional image geolocation while enabling object level inspection of the visual cues underlying its predictions.

Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored, especially when the original training data is inaccessible and the use case demands multilingual, spoken-query interaction. We adapt an open-source SLM to the Singaporean Home Team context across five speech tasks in Singapore's four official languages, combining LoRA fine-tuning, a surrogate text-QA dataset that guards against catastrophic forgetting, and a multi-task objective that adapts the CoBa reweighting scheme to speech. We also build HTD-multilingual-QA, a 504,853 sample multilingual QA dataset in text and spoken form. The resulting HT-Moonstone (5B) matches or outperforms SLMs up to 7x its size on most tasks, attains the best accent and gender recognition among all models evaluated, and loses under 2% of its original speech QA ability.

Stone inscriptions are invaluable sources of historical and linguistic knowledge, yet their automated analysis remains a major challenge due to surface irregularities, erosion, and low visual contrast. Conventional document and handwriting analysis techniques fail to perform well in these scenarios. In this work, we propose character detection as a core strategy for robust inscription analysis. We introduce EpiSAM, a prompt-guided transformer framework for character segmentation in stone inscriptions. Rather than treating characters in isolation, EpiSAM employs a novel neighbor-aware strategy, explicitly predicting adjacent characters alongside the target. These contextual cues resolve boundary ambiguities, improving mask generation and enabling more accurate character segmentation. Furthermore, we expand an existing stone inscription dataset by adding dense polygonal annotations for characters, thereby enabling comprehensive research on Southeast Asian epigraphy. Experimental results show that EpiSAM achieves consistent improvements over existing baselines, while also exhibiting strong zero-shot generalization in challenging epigraphic scenarios.

Existing head pose datasets predominantly feature subjects of Western or East Asian origin, leaving South Asian populations, particularly Bengali individuals, largely underrepresented. We introduce Bengal-HP_RU, the first publicly available head pose dataset centred on Bengali subjects, comprising 12,894 labelled head images annotated with continuous yaw, pitch, and roll values. Images were collected from Wikimedia Commons under free licences and processed through an automated pipeline followed by manual label correction. The dataset is partitioned by Wikimedia uploader identity to prevent data contamination, yielding 10,494 training and 2,400 test images across 296 unique uploaders. Bengal-HP_RU exhibits substantial diversity in subject age, gender, occlusion, illumination, and background, reflecting realistic in-the-wild conditions. The dataset is publicly available at https://doi.org/10.17632/xbw9kr37jb.2.

Codecfakes (CFs) are a type of speech deepfakes generated through Audio Language Models (ALMs), with Neural Audio Codecs (NACs) forming the core mechanism for speech encoding and generation. CFs exhibit distributional characteristics that differ from vocoder-based deepfakes, causing detectors trained on vocoder data to generalize poorly to CFs detection. Although this has led to the development of CF detection benchmarks, existing resources are largely confined to English -- and to a limited extent Chinese -- leaving South-East Asian (SEA) languages unexplored. To bridge this gap, we introduce SEA-CF, the first large-scale benchmark for CF detection spanning multiple SEA languages, diverse speaker profiles, and a wide range of NAC architectures. SEA-CF is constructed by synthesizing publicly available real speech corpora. Our experiments show that state-of-the-art (SOTA) CF detectors trained on English-centric datasets fail to generalize to SEA speech due to language-specific phonetic structures, tonal variations, and rich prosodic diversity. We further conduct a comprehensive zero-shot and fine-tuned evaluation of recent SOTA ALMs on SEA-CF. Fine-tuning the ALMs improves performance, however, these are very large being impractical for real-world application due to their scale, particularly in low-resource and latency-constrained settings. To address this limitation, we propose a novel small-ALM, GARUDA tailored for CF detection, which delivers strong performance while remaining lightweight. Extensive evaluations demonstrate that the proposed Small-ALM outperforms strong end-to-end and ALM-based baselines, establishing a new, practical direction for robust CF detection in SEA languages and beyond.

Illegal logging and timber trade continue to pose significant challenges in the Philippines, where accurate wood species identification is essential for enforcement but limited by the need for specialised equipment and expertise. This study aims to evaluate whether AI models for macroscopic wood identification can be developed and deployed by wood scientists without programming expertise using the Xylorix platform, focusing on five Philippine hardwood species: Mangium (Acacia mangium Willd.), Rain Tree [Samanea saman (Jacq.) Merr.], Banuyo (Wallaceodendron celebicum Koord.), Tindalo [Afzelia rhomboidea (Blanco) Vidal], and Ipil [Intsia bijuga (Colebr.) O. Kuntze]. Binary classifiers were trained on 10,663 verified cross-section images from 260 specimens and evaluated using specimen-level mean scoring to mirror operational field conditions. Area Under the ROC Curve (AUC) values ranged from 0.969 (Ipil) to 1.000 (Mangium), and Average Precision (AP) values ranged from 0.589 (Samanea) to 1.000 (Mangium). Four of five species achieved AA grade (AUC and AP both \geq 0.90); Rain Tree received AE (AUC \geq 0.90, AP < 0.60) due to AP compression from its small positive test set (3 specimens). All five classifiers rank their target specimens above non-target specimens with near-perfect fidelity. Specimen-level error analysis revealed 9 false negatives from Ipil, primarily stemming from localized image artifacts and 3 false positives for Rain Tree and 1 false positive for Tindalo caused by shared tribal-level anatomical traits. These findings demonstrate that Xylorix non-programmers can leverage the Xylorix platform to construct operationally reliable wood identification models suitable for field deployment at supply chain checkpoints.

Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target languages - an approach that converts surface-level linguistic form while failing to reflect the cultural context embedded in threat scenarios, social norms, and legal frameworks. We construct paired DT and culturally-adapted (CA) datasets via 1:1 seed matching for four languages - Korean (KO), Japanese (JA), Thai (TH), and Khmer (KM) - and compare Attack Success Rate (ASR) and Cultural Realism scores across four open-source LLM. CA prompts yield Delta-ASR > 0 across all 16 language x model combinations (mean +9.3 pp), and DT-based evaluation underestimates risk in 44 of 48 category x language combinations. Language-level analysis reveals that the distribution of threat forms is heterogeneous across languages. Cultural Realism analysis further shows that DT Cultural Depth (C3) scores remain consistently below 1.0 out of 3.0 across all four languages (mean 0.17), whereas CA scores reach up to 2.51, indicating that direct translation produces inputs systematically divergent from those encountered in real-world multicultural settings. These findings demonstrate that adapting benchmarks to language-specific cultural contexts - rather than relying on linguistic translation alone - is necessary for valid multilingual LLM safety evaluation.

Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks. However, existing works remain confined to Western tonal traditions, offering little insight into whether current LLMs can handle structurally distinct low-resource musical traditions. We present the first systematic evaluation of LLM competence in South Asian classical music, a tradition governed by raga, tala-based melodic constraints that impose fundamentally different structural principles from Western harmony-driven music. We ground our evaluation in Hindustani classical theory and Bengali classical forms, including Rabindra and Nazrul Sangeet -- representative low-resource traditions within South Asian classical music. For music understanding evaluation, we introduce a 504-question-answer benchmark spanning raga grammar, cultural knowledge, and symbolic notation reasoning, evaluating 33 LLMs where frontier models such as Gemini 2.5 Pro achieve 85-90% accuracy, while most open-source models remain in the 23-40% range. For music generation, we design a five-level controlled prompting framework and find that even the strongest model produces stylistically faithful outputs only 40% of the time. These results reveal that structural validity and stylistic faithfulness in music generation are distinct objectives and highlight an open challenge for culturally grounded music modeling.

Frontier LLMs perform well in Western contexts, but remain poorly tested on underrepresented cultures such as those in Southeast Asia (SEA). Existing NLI benchmarks are largely Western-centric, translation-derived, or monolingual, limiting their ability to measure culturally grounded reasoning. We introduce SEA-NLI, a native, culturally grounded NLI benchmark covering eight SEA countries in English and native regional languages, verified by native speakers. Across 17 encoder and decoder models, we observe a low performance from all models, especially for knowledge-intensive categories such as Languages and Science and Technology. Our analysis shows that failure cases mainly stem from missing SEA cultural knowledge: SEA-adapted models and culture-aware prompting improve performance, while CoT prompting offers limited gains.

Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-LION-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-LION-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region.

Standard approaches to forecasting the weekly number of earthquakes on a spatial grid rely on the Poisson distribution with a single global dispersion assumption. We show that this assumption is systematically violated in seismic data from Central Asia (2010-2024), where a likelihood-ratio test with boundary correction strongly rejects the Poisson hypothesis (p < 10^{-179}). The main contribution of this work is the EarthquakeNet architecture, which provides an endogenous per-cell estimate of the overdispersion parameter alpha via a neural network (spatial embeddings + MLP), without explicit spatial covariance specification. In contrast to existing negative binomial regression approaches in seismological forecasting, which typically assume a single global alpha, the proposed per-cell formulation allows the model to identify spatial heterogeneity in seismic clustering and to construct probabilistic risk-aware alerts via quantiles of the predicted distribution. A walk-forward evaluation (2018-2023) over four systems shows an 8.6 percent reduction in mean pinball deviation (MPD) relative to a negative binomial GLM baseline. The strongest improvements are observed in the tail regime (Y >= 5), where the continuous ranked probability score (CRPS) of the proposed model is 12.5 percent lower than that of the baseline, indicating improved calibration in extreme-event forecasting.

Passive acoustic monitoring (PAM) enables large-scale biodiversity assessment, but continuous recording generates large amounts of non-informative audio, creating challenges for storage, power consumption, and long-term edge deployment. Bird audio detection (BAD), which identifies bird vocalizations, can reduce this burden by filtering irrelevant recordings before downstream analysis. However, most BAD systems are trained on temperate datasets despite tropical soundscapes being denser, more species-rich, and acoustically unpredictable. To address this gap, we introduce SEABAD (Southeast Asian Bird Activity Detection), a dataset of 50,000 curated three-second clips from Southeast Asian soundscapes, evenly balanced between bird-present and bird-absent samples. The dataset spans 1,677 bird species and is standardized to 16 kHz mono audio for embedded and low-power inference. We developed a dual-branch curation pipeline: a six-stage positive-label workflow applied to Xeno-Canto recordings, alongside six source-specific negative-label extractions from environmental datasets. These procedures reduced class imbalance by 13.7% (Gini coefficient: 0.601 to 0.519). A manual audit of 1,000 positive clips confirmed 97.8% +/- 0.9% labeling accuracy. Baseline experiments using MobileNetV3-Small achieved 99.57% +/- 0.25% accuracy and 0.9985 +/- 0.0002 AUC across three random seeds. SEABAD and the full curation pipeline are publicly released to support tropical BAD research and energy-efficient acoustic monitoring.

Rapid earthquake magnitude estimation is crucial for effective early warning systems that can save lives and reduce economic damage. In this paper, we present a comprehensive study of magnitude classification using only the vertical component of the initial 7-second P-wave window from a single station. We compare six machine learning approaches that range from traditional models to state-of-the-art deep learning architectures. We also curated a novel dataset of 7,318 earthquake events in South Asia. The dataset was categorized into five Richter-scale classes: slight (3.0-3.9), light (4.0-4.9), moderate (5.0-5.9), strong (6.0-6.9) and severe (>= 7.0). Our experiments show that deep learning models substantially outperform traditional approaches. Our Transformer based architecture achieved 76.23% standard accuracy and 81.56% adaptive accuracy with 4.8 ms inference latency. The adaptive-accuracy metric is introduced for the inherent uncertainty in magnitude estimation of near class boundaries. These results indicate that the attention mechanisms in Transformers combined with adaptive classification effectively capture the temporal dynamics of seismic signals. The architectural advantage facilitates promising generalization to rare high-magnitude events, despite the inherent data scarcity characteristic of seismic catalogs. The adaptive accuracy provides a more realistic assessment of model performance, and the result suggests viability for real-time deployment.

Large language models (LLMs) have demonstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource African languages remains poorly understood and largely unevaluated. This paper presents Nsanku, a systematic benchmark that evaluates the zero-shot machine translation performance of 19 open-weight and proprietary LLMs across 43 Ghanaian languages paired with English. Evaluation sentences were sourced from the YouVersion Bible platform, providing 300 sentence pairs per language. Two complementary automatic metrics are employed: Bilingual Evaluation Understudy (BLEU) and Character n-gram F-Score (chrF), alongside an average accuracy score and a cross-language consistency dimension. Nsanku represents the most comprehensive LLM translation evaluation for Ghanaian languages conducted to date. Results show that gemini-2.5-flash achieves the highest overall average score of 26.88 (BLEU: 24.60, chrF: 29.16), followed by claude-sonnet-4-5 at 24.87 (BLEU: 22.46, chrF: 27.28) and gpt-4.1 at 23.20 (BLEU: 21.15, chrF: 25.24). Among open-weight models, kimi-k2-instruct-0905 leads at an average score of 20.87. A critical finding from the consistency analysis is that no model and no language reached the Leaders quadrant of high performance and high consistency simultaneously, indicating that current LLMs are not yet reliably usable for Ghanaian language translation at scale. Siwu achieved the highest per-language average score at 25.73 while Nkonya scored lowest at 11.65. Nsanku establishes a publicly available, community-extensible evaluation infrastructure for African language NLP research.

This study examines the factors influencing pre-service teachers' behavioral intention to use AI-enabled educational tools during their practicum, using the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) as the theoretical framework. The model includes the core UTAUT2 constructs such as performance expectancy, effort expectancy, hedonic motivation, social influence, facilitating conditions, price value, and habit. It also incorporates additional predictors including computer self-efficacy, computer anxiety, and computer playfulness. Data were collected from 563 pre-service teachers using a structured questionnaire and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results indicate that performance expectancy and hedonic motivation are the strongest predictors of behavioral intention. Computer self-efficacy, computer anxiety, and computer playfulness significantly influenced effort expectancy, although effort expectancy did not directly predict behavioral intention. Performance expectancy was significantly predicted by extrinsic motivation, job fit, relative advantage, and outcome expectations. Constructs such as social influence and facilitating conditions showed limited or inverse effects. These findings suggest that internal motivational, cognitive, and emotional factors are more influential than external or institutional factors in shaping the adoption of AI-enabled tools. The study highlights the importance of promoting personal relevance, confidence, and enjoyment in teacher preparation programs to encourage technology integration.

Pakistan experienced an unusually severe flood season between June and December 2025, with cascading impacts on population, infrastructure, and agriculture. Existing operational flood products (e.g., UNOSAT) provide valuable episode-level snapshots but rarely deliver spatially and temporally continuous inundation maps at near-real-time latency within the country. We present a multi-sensor, ensemble-based remote-sensing framework for continuous flood nowcasting in Pakistan that integrates Sentinel-1 SAR, Harmonized Landsat-Sentinel (HLS L30 and S30), MODIS, and VIIRS observations on a harmonized grid in Google Earth Engine. The framework employs a tiered nowcasting ensemble that prioritizes higher-resolution sensors (Sentinel-1 and HLS) and falls back to MODIS and VIIRS when necessary, preserving daily continuity of flood extent at each sensor's native resolution. Applied to the 2025 monsoon period, the system generates near-real-time, spatially consistent inundation maps across Pakistan. As a nowcasting case study, we track the super-flood of 26 August-7 September 2025 day by day, demonstrating the framework's ability to capture the evolving flood footprint in near real time and extend beyond the temporal limits of episodic mapping products. Validation against GloFAS discharge anomalies and precipitation datasets (CHIRPS v3.0, MSWEP) shows strong agreement with observed hydrometeorological conditions. By integrating nowcast outputs with exposure layers (WorldPop, ESA WorldCover, Giga-HOTOSM), the framework enables rapid estimation of affected populations, cropland, and critical infrastructure, supporting timely disaster response and resilience planning in South Asia.

This study examined the barriers and enablers of online instruction in hospitality education. A sequential exploratory design was implemented with hospitality teachers from both public and private higher educational institutions in the Philippines. Thematic analysis of interviews identified four key themes: technological barriers, pedagogical challenges, institutional and personal support, and integration of artificial intelligence (AI). These themes were transformed into survey constructs and tested for reliability. Pedagogical challenges, including difficulties in teaching hands-on subjects and sustaining student engagement, emerged as the most critical concerns. Technological barriers such as unstable internet and limited devices were moderately rated, while institutional and personal support received mixed evaluations. Teachers viewed AI integration as helpful but also expressed caution and emphasized the need for training. Reliability analysis showed acceptable to good internal consistency across constructs. The findings highlight the importance of strengthening pedagogical training, providing clear institutional support, and fostering responsible competence in AI use. Future studies should validate these results with larger and more diverse samples.

Bangla-English code-mixing is widespread across South Asian social media, yet resources for implicit meaning identification in this setting remain scarce. Existing sentiment and sarcasm models largely focus on monolingual English or high-resource languages and struggle with transliteration variation, cultural references, and intra-sentential language switching. To address this gap, we introduce MixSarc, the first publicly available Bangla-English code-mixed corpus for implicit meaning identification. The dataset contains 9,087 manually annotated sentences labeled for humor, sarcasm, offensiveness, and vulgarity. We construct the corpus through targeted social media collection, systematic filtering, and multi-annotator validation. We benchmark transformer-based models and evaluate zero-shot large language models under structured prompting. Results show strong performance on humor detection but substantial degradation on sarcasm, offense, and vulgarity due to class imbalance and pragmatic complexity. Zero-shot models achieve competitive micro-F1 scores but low exact match accuracy. Further analysis reveals that over 42% of negative sentiment instances in an external dataset exhibit sarcastic characteristics. MixSarc provides a foundational resource for culturally aware NLP and supports more reliable multi-label modeling in code-mixed environments.

Peer support plays a vital role in expanding access to mental health care by providing empathetic, community-based support outside formal clinical systems. As digital platforms increasingly mediate such support, the design and impact of these technologies remain under-examined, particularly in Asian contexts. This paper presents findings from an interview study with 20 peer supporters in Singapore, who operate across diverse online, offline, and hybrid environments. Through a thematic analysis, we unpack how participants start, conduct, and sustain peer support, highlighting their motivations, emotional labour, and the sociocultural dimensions shaping their practices. Building on this grounded understanding, we surface design directions for culturally responsive digital tools that scaffold rather than supplant relational care. Drawing insights from qualitative accounts, we offer a situated perspective on how AI might responsibly augment peer support. This research contributes to human-centred computing by articulating the lived realities of peer supporters and proposing design implications for trustworthy and context-sensitive AI in mental health.

Natural Language Processing (NLP) for Ghana's 73 living indigenous languages remains deeply fragmented, under-resourced, and heavily skewed toward a single language. We present the first systematic review of the Ghanaian NLP landscape, screening 17,000+ publications across four academic databases to critically synthesize 36 core studies spanning datasets, model architectures, and evaluation paradigms. Our analysis exposes a severe resource imbalance: Twi-centric NLP has grown modestly, driven largely by religious-text alignment and crowdsourcing, while the remaining 70+ languages remain almost entirely unaddressed, and dataset releases, model checkpoints, and evaluation practices remain inconsistent and rarely shared across the field. We translate these findings into a prioritized roadmap targeting Ghana's acute regional constraints, dialectal variation, non-standardized orthographies, and the absence of shared infrastructure, offering a replicable template for systematic review and research prioritization in other low-resource language settings.