Phantom of Latent for Large Language and Vision Models
Keywords: Large Language and Vision Models
Abstract: The success of visual instruction tuning has accelerated the development of large language and vision models (LLVMs). Following the scaling laws of instruction-tuned large language models (LLMs), LLVMs have also further increased in size, with examples including 26B, 34B, and even 80B parameters. While this increase in model size has yielded significant performance gains, it demands substantially more hardware resources for both training and inference. Consequently, there naturally exists a strong need for efficient LLVMs that achieve the performance of larger models while being smaller in size. To achieve this need, we present a new efficient LLVM family with model sizes of 0.5B, 1.8B, 3.8B, and 7B parameters, Phantom, which significantly enhances learning capabilities within limited structures. By temporarily increasing the latent hidden dimension during multi-head self-attention (MHSA), we make LLVMs understand much more vision-language knowledge on the latent, without substantially increasing physical model sizes. To maximize its advantage, we introduce Phantom Optimization (PO) using both autoregressive supervised fine-tuning (SFT) and direct preference optimization (DPO)-like concept, which effectively follows correct answers while eliminating incorrect and ambiguous ones. Phantom outperforms numerous larger open- and closed-source LLVMs, positioning itself as a leading solution in the landscape of efficient LLVMs.
Primary Area: other topics in machine learning (i.e., none of the above)
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.
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: 2520
Loading