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

arXiv: https://arxiv.org/abs/2605.26601 · HTML: https://mlsanity.com/paper/2605.26601/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding](https://mlsanity.com/paper/1711.06475/) (2017)
- [Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning](https://mlsanity.com/paper/2402.11690/) (2024)
- [Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale](https://mlsanity.com/paper/2407.02118/) (2024)
- [Enhancing Multimodal Continual Instruction Tuning with BranchLoRA](https://mlsanity.com/paper/2506.02041/) (2025)
- [Adapting Large Language Models to Low-Resource Tibetan: A Two-Stage Continual and Supervised Fine-Tuning Study](https://mlsanity.com/paper/2512.03976/) (2025)
- [BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models](https://mlsanity.com/paper/2301.12032/) (2023)
- [COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark](https://mlsanity.com/paper/2507.13405/) (2025)

## Built on by (most cited first, 2 of 2)

- [Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation](https://mlsanity.com/paper/2605.29502/) (2026)
- [Towards the Roof of the World: NLP Progress in Tibetan Languages](https://mlsanity.com/paper/2610.13398/) (2026)

## Abstract (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.