paper-with-me

Papers

FTibSuite: A Comprehensive Resource Suite for Tibetan Vision-Language Modeling

2026-05-26 · Guixian Xu, Yide Liang, Zeli Su, Xuexian Song, Ziyin Zhang, Yushuang Dong, Ting Zhang, Xu Han arxiv

Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible training and evaluation infrastructure. To fill this gap, we introduce FTibSuite, a comprehensive resource suite for Tibetan vision-language research, consisting of FTibData (human-verified multimodal training corpora spanning continual pretraining, image-text alignment, and instruction tuning data), FTibBench (Tibetan adaptations of five mainstream multimodal benchmarks with a hierarchical quality-control workflow to reduce translation noise), and FTibVLM, a reproducible baseline built on Qwen3-VL-8B-Instruct via a three-stage adaptation pipeline. Experiments on FTibBench show FTibVLM delivers consistent performance gains across all tasks, such as improving MMBench accuracy from 42.97 to 67.78 and POPE-random accuracy from 47.53 to 80.56, while retaining the backbone's original Chinese capabilities with minimal degradation, providing the first standardized foundation for Tibetan multimodal research.

📄 PDF Abstract BibTeX arXiv:2605.26601

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Pretraining

Similar Papers 제목 키워드 기반

Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challenges

2025-10-22 · Cheng Huang, Nyima Tashi, Fan Gao, Yutong Liu 외 arxiv

Tibetan, one of the major low-resource languages in Asia, presents unique linguistic and sociocultural characteristics that pose both challenges and opportunities for AI research. Despite increasing interest in developin…

Cross-Lingual TransferMachine TranslationSpeech Recognition

TLUE: A Tibetan Language Understanding Evaluation Benchmark

2025-03-15 · Fan Gao, Cheng Huang, Nyima Tashi, Xiangxiang Wang 외

Large language models (LLMs) have made tremendous progress in recent years, but low-resource languages, such as Tibetan, remain significantly underrepresented in their evaluation. Despite Tibetan being spoken by over sev…

Sun-Shine: A Large Language Model for Tibetan Culture

2025-03-24 · Cheng Huang, Fan Gao, Nyima Tashi, Yutong Liu 외

Tibetan, a minority language in China, features a highly intricate grammatical structure, characterized by four verb tenses and a tense system with frequent irregularities, contributing to its extensive inflectional dive…

Language ModelingLanguage ModellingLarge Language ModelMachine Translation+2

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan

2025-07-12 · Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin 외 arxiv

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, yet their performance remains heavily biased toward high-resource languages. Tibetan, despite its cu…

A Aelf-supervised Tibetan-chinese Vocabulary Alignment Method Based On Adversarial Learning

2021-10-04 · Enshuai Hou, Jie Zhu

Tibetan is a low-resource language. In order to alleviate the shortage of parallel corpus between Tibetan and Chinese, this paper uses two monolingual corpora and a small number of seed dictionaries to learn the semi-sup…