A dedicated collaborative platform indexing natural language processing capstone internships, corpus engineering tools, and foundation model benchmarks at Kathmandu University. Jointly steered by the Department of Artificial Intelligence (DoAI) and the Information and Language Processing Research Lab (ILPRL).
Guiding student researchers to solve low-resource NLP challenges through principled engineering and linguistic rigor.
Lecturer & Bachelor Program Coordinator at the Department of Artificial Intelligence, School of Engineering, Kathmandu University. Guides capstone cohorts on curriculum integration, machine learning pipelines, and modern AI engineering standards.
Professor of Computer Engineering, Dean of the School of Engineering, and Founding Lead of ILPRL. Pioneered computational linguistics, Devanagari OCR, and Nepali corpus archival for over two decades.
Dedicated exclusively to solving foundational NLP bottlenecks for Nepali and Nepal-based languages.
Scraping, deduplicating, and gating clean Nepali corpora while maintaining full parentage to original sources and licenses.
Ergonomic web-based annotation queues for native speakers covering NER, POS tagging, spelling correction, and instruction pairs.
Standardized empirical test suites (BalEval) to evaluate LLM reasoning, multimodal retrieval, and instruction fidelity.
Acoustic speech models (ASR), dialect archiving, and Devanagari layout analysis with legacy Preeti font restoration.
Active and milestone research initiatives in the lab.
A unified, audit-first data operating system built on Datasette and SQLite. Ingests raw web crawls and archive dumps, normalizes legacy fonts (Preeti/Kantipur), filters Hindi leakage, clusters MinHash duplicates, and runs native-speaker annotation queues with complete provenance tracing.
A rigorous empirical evaluation benchmark and baseline suite testing generative reasoning, instruction-following, and natively multimodal retrieval across 22 years of Nepali computational linguistics assets, pairing Gemma 4 E4B with EmbeddingGemma 2.
