Long Context Transfer from Language to Vision
Video sequences offer valuable temporal information, but existing large multimodal models (LMMs) fall short in understanding extremely long videos. Many works address this by reducing the number of visual tokens using visual resamplers. Alternatively, in this paper, we approach this problem from the perspective of the language model. By simply extrapolating the context length of the language backbone, we enable LMMs to comprehend orders of magnitude more visual tokens without any video training. We call this phenomenon long context transfer and carefully ablate its properties. To effectively measure LMMs' ability to generalize to long contexts in the vision modality, we develop V-NIAH (Visual Needle-In-A-Haystack), a purely synthetic long vision benchmark inspired by the language model's NIAH test. Our proposed Long Video Assistant (LongVA) can process 2000 frames or over 200K visual tokens without additional complexities. With its extended context length, LongVA achieves state-of-the-art performance on Video-MME among 7B-scale models by densely sampling more input frames. Our work is open-sourced at https://github.com/EvolvingLMMs-Lab/LongVA.
Code (2)
Tasks
Language ModelingLanguage ModellingMMEVideo MMEVideo Question AnsweringVisual Question Answering (VQA)Zero-Shot Video Question AnswerSimilar Papers 제목 키워드 기반
Towards Long-window Anchoring in Vision-Language Model Distillation
While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge dist…
Long-Context UnderstandingKnowledge DistillationHow to Train Your Long-Context Visual Document Model
We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-document visual question answering with measured transfer to long-context text. Whi…
Visual Question AnsweringMetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language Models
Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-…
In-Context LearningLanguage ModelingLanguage ModellingVisual Question Answering (VQA)TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handlin…
Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning a tiny set of context vectors. Neverthel…
Transfer Learning