HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
By: HyperAI Team , Yuchen Liu , Kaiyang Han and more
Potential Business Impact:
Makes smart AI work on your phone.
Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models are progressively endowed with strong general capabilities, standard Vision Transformer (ViT) encoders remain a critical bottleneck, suffering from excessive latency and memory consumption when processing high-resolution inputs.To address these challenges, we introduce HyperVL, an efficient multimodal large language model tailored for on-device inference. HyperVL adopts an image-tiling strategy to cap peak memory usage and incorporates two novel techniques: (1) a Visual Resolution Compressor (VRC) that adaptively predicts optimal encoding resolutions to eliminate redundant computation, and (2) Dual Consistency Learning (DCL), which aligns multi-scale ViT encoders within a unified framework, enabling dynamic switching between visual branches under a shared LLM. Extensive experiments demonstrate that HyperVL achieves state-of-the-art performance among models of comparable size across multiple benchmarks. Furthermore, it significantly significantly reduces latency and power consumption on real mobile devices, demonstrating its practicality for on-device multimodal inference.
Similar Papers
Vision-Enhanced Large Language Models for High-Resolution Image Synthesis and Multimodal Data Interpretation
CV and Pattern Recognition
Makes computers create clearer pictures from words.
MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning
CV and Pattern Recognition
Lets phones understand pictures and words better.
AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model
CV and Pattern Recognition
Lets phones understand pictures and text easily.