Devanagari
PulseAugur coverage of Devanagari — every cluster mentioning Devanagari across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Familiar scripts, not related languages, unlock AI understanding of unseen languages
Researchers have demonstrated that the familiarity of a script, rather than linguistic relatedness, is key to enabling AI models to understand unseen languages. In experiments with a model called GlyphMind, which proces…
-
Multilingual LLMs Fail Cross-Script Entity Matching, Study Finds
A new research paper published on arXiv details how multilingual language models struggle with entity matching when names are presented in different scripts. The study found that models like Qwen2.5-7B exhibit significa…
-
New TITAN framework enhances low-resource multilingual translation in LLMs
Researchers have developed a new framework called TITAN to understand and improve translation capabilities in multilingual large language models, particularly for low-resource languages. This framework uses causal inter…
-
New Nepali Sentiment Benchmark NEPSEE Released
Researchers have developed NEPSEE, a new benchmark for Nepali sentiment analysis, which utilizes double annotation to ensure label consistency. The benchmark consists of 3,189 sentences from Nepali public figures' tweet…
-
New test reveals LLMs struggle with mixed-language prompts
A new evaluation protocol called Multilingual Distractor Interference (MDI) has been developed to assess how large language models handle prompts containing irrelevant foreign-language sentences. When tested on Llama-3.…
-
Pretraining boosts Devanagari OCR efficiency, slashing transcription needs
A new study published on arXiv investigates the efficiency of annotation for handwritten Devanagari recognition systems. Researchers found that supervised synthetic pretraining significantly reduces the number of transc…
-
Srijika system generates OpenType fonts for nine Indic scripts
Researchers have developed Srijika, a novel system designed to create installable OpenType fonts for nine Indic scripts, including Devanagari, Tamil, and Bengali. Instead of generating fonts from scratch, Srijika restyl…
-
Whisper fine-tuned for Nepali financial voice commands, improving accessibility
Researchers have developed SpeakPay, a voice-first digital wallet designed to assist visually impaired users in Nepal. The core technical contribution is a domain-adaptive fine-tuning approach using LoRA on the Whisper …
-
New NAS Framework Generates Devanagari Digits for AI Training
Researchers have developed NepScript Genesis, a Neural Architecture Search (NAS) framework designed to automate the discovery of Generative Adversarial Networks (GANs) for synthesizing handwritten Devanagari digits. Thi…
-
New Arkios language model trained on English-Nepali text
Researchers have introduced Arkios, a 1.04 billion parameter language model trained on 150 billion tokens of English and Nepali text. The model utilizes a custom training stack and a Devanagari-aware tokenizer. Evaluati…
-
Nepali Meme Classification System Achieves Top Ranks at CHiPSAL 2026
Researchers have developed a novel system for classifying Nepali memes, achieving second place in the CHiPSAL 2026 shared task for hate speech detection and fourth place for sentiment analysis. Their approach utilizes t…
-
Compact AI model achieves benchmark saturation for Devanagari recognition
Researchers have developed a highly efficient convolutional neural network, named Barnamala, for recognizing handwritten Devanagari script. This compact model, with only 1.11 million parameters, achieves a benchmark sat…
-
Nepali Number Plate Recognition System Achieves 93% Accuracy
Researchers have developed a new Automatic Number Plate Recognition (ANPR) system specifically designed for Nepali license plates, which use the Devanagari script. The system employs a pipeline that first uses YOLO-base…
-
AI models struggle with Devanagari script OCR, new benchmark reveals
A new benchmark study has evaluated the performance of ten OCR systems, including specialized OCR-VLMs and frontier multimodal LLMs, on Devanagari script. The research found that while many systems perform well on clean…
-
New benchmark measures stereotypical bias in Goan identity groups
Researchers have introduced AmchiBias, a novel benchmark designed to measure stereotypical bias within Goan identity groups, utilizing a dataset of minimal pairs in both English and Konkani. The benchmark evaluates five…