VILA^2: VLM Augmented VLM with Self-Improvement
Keywords: Multimodal Large Models
Abstract: Visual language models (VLMs) have rapidly progressed, driven by the success of large language models (LLMs). While model architectures and training infrastructures advance rapidly, data curation remains under-explored. When data quantity and quality become a bottleneck, existing work either directly crawls more raw data from the Internet that does not have a guarantee of data quality or distills from black-box commercial models (e.g., GPT-4V / Gemini) causing the performance upper bounded by that model. In this work, we introduce a novel approach that includes a self-augment step and a specialist-augment step to iteratively improve data quality and model performance. In the self-augment step, a VLM recaptions its own pretraining data to enhance data quality, and then retrains from scratch using this refined dataset to improve model performance. This process can iterate for several rounds. Once self-augmentation saturates, we employ several specialist VLMs finetuned from the self-augmented VLM with domain-specific expertise, to further infuse specialist knowledge into the generalist VLM through task-oriented recaptioning and retraining. With the combined self-augmented and specialist-augmented training, we introduce VILA2 (VLM-augmented-VLM), a VLM family that consistently improves the accuracy on a wide range of tasks over prior art, including MMMU leaderboard, with a reusable pretraining dataset that is 300x more cost-efficient than human labeling.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2026
Loading