FTibSuite provides human-verified multimodal corpora, Tibetan-adapted benchmarks with quality controls, and a baseline VLM showing gains on tasks like MMBench while preserving Chinese capabilities.
arXiv preprint arXiv:2506.02041 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
InduceKV is a retrieval-based continual adaptation method that uses bilevel selection to build a compact set of inducing KV memories for fixed-footprint updates to multimodal LLMs.
citing papers explorer
-
FTibSuite: A Comprehensive Resource Suite for Tibetan Vision-Language Modeling
FTibSuite provides human-verified multimodal corpora, Tibetan-adapted benchmarks with quality controls, and a baseline VLM showing gains on tasks like MMBench while preserving Chinese capabilities.