Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become inefficient at high resolutions due to the large number of tokens and high encoding latency. At different operational resolutions, the vision encoder of a VLM can be optimized along two axes: reducing encoding latency and minimizing the number of visual tokens passed to the LLM, thereby lowering overall latency. Based on a comprehensive efficiency analysis of the interplay between image resolution, vision latency, token count, and LLM size, we introduce FastVLM—a model that achieves an optimized trade-off between resolution, latency, and accuracy. FastVLM incorporates FastViTHD, a novel hybrid vision encoder designed to output fewer tokens and significantly reduce encoding time for high-resolution images. Unlike previous methods, FastVLM achieves the optimal balance between visual token count and image resolution solely by scaling the input image, eliminating the need for additional token pruning and simplifying the model design. In the LLaVA-1.5 setup, FastVLM achieves 3.2x improvement in time-to-first-token (TTFT) while maintaining similar performance on VLM benchmarks compared to prior works. Compared to LLaVa-OneVision at the highest resolution (1152x1152), FastVLM achieves comparable performance on key benchmarks like SeedBench and MMMU, using the same 0.5B LLM, but with 85x faster TTFT and a vision encoder that is 3.4x smaller.

Related readings and updates.

Vision Language Models (VLMs) enable visual understanding alongside textual inputs. They are typically built by passing visual tokens from a pretrained vision encoder to a pretrained Large Language Model (LLM) through a projection layer. By leveraging the rich visual representations of the vision encoder and the world knowledge and reasoning capabilities of the LLM, VLMs can be useful for a wide range of applications, including accessibility…
Read more
Apple researchers are advancing AI and ML through fundamental research, and to support the broader research community and help accelerate progress in this field, we share much of our research through publications and engagement at conferences. This week, the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), will take place in Nashville, Tennessee. Apple is proud to once again participate in this important event for the…
Read more