2025/05/27 by Bozhou Li, Wentao Zhang, Li, Bozhou +1 · 1 citation
Arts and Humanities · Computer Science · #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Multimodal Machine Learning Applications #Subtitles and Audiovisual Media
paper · pdf · doi:10.48550/arxiv.2505.21465
openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbnail of an image simultaneously. While effective, this method generates a large number of image tokens. When combined with the widely used Rotary Position Embedding (RoPE), its long-term decay property hinders the interaction between high-resolution tokens and thumbnail tokens, as well as between text and image. To address these issues, we propose ID-Align, which alleviates these problems by reordering position IDs. In this method, high-resolution tokens inherit IDs from their corresponding thumbnail token while constraining the overexpansion of positional indices. Our experiments conducted within the LLaVA-Next framework demonstrate that ID-Align achieves significant improvements, including a 6.09% enhancement on MMBench's relation reasoning tasks and notable gains across multiple benchmarks. Our code is available at the following link: https://github.com/zooblastlbz/ID-Align.