V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

• URL: http://arxiv.org/abs/2412.09616v2
• Date: Fri, 13 Dec 2024 04:58:33 GMT
• Title: V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
• Authors: Junqi Ge, Ziyi Chen, Jintao Lin, Jinguo Zhu, Xihui Liu, Jifeng Dai, Xizhou Zhu,
• Abstract summary: Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios. We propose a novel positional encoding approach that employs variable increments for visual tokens, enabling more efficient management of long multimodal sequences. We show that the fine-tuned model achieves strong performance on both standard and long-context multimodal tasks.
• Score: 40.784423313750075
• License:
• Abstract: Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text documents. In our work, we first conduct an empirical analysis of the long-context capabilities of VLMs using our augmented long-context multimodal datasets. Our findings reveal that directly applying the positional encoding mechanism used for textual tokens to visual tokens is suboptimal, and VLM performance degrades sharply when the position encoding exceeds the model's context window. To address this, we propose Variable Visual Position Encoding (V2PE), a novel positional encoding approach that employs variable and smaller increments for visual tokens, enabling more efficient management of long multimodal sequences. Our experiments demonstrate the effectiveness of V2PE to enhances VLMs' ability to effectively understand and reason over long multimodal contexts. We further integrate V2PE with our augmented long-context multimodal datasets to fine-tune the open-source VLM, InternVL2. The fine-tuned model achieves strong performance on both standard and long-context multimodal tasks. Notably, when the sequence length of the training dataset is increased to 256K tokens, the model is capable of processing multimodal sequences up to 1M tokens, highlighting its potential for real-world long-context applications.

Related papers

• Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy [111.1291107651131]
  Long-VITA is a large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M tokens. Long-VITA is fully reproducible and supports both NPU and GPU platforms for training and testing.
  arXiv  Detail & Related papers  (2025-02-07T18:59:56Z)
• GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models [20.976319536167512]
  We aim to establish an effective solution that enhances long context performance of Visual Language Models. We propose Giraffe, which is effectively extended to 128K lengths. We will open-source the code, data, and models.
  arXiv  Detail & Related papers  (2024-12-17T09:57:21Z)
• Long Context Transfer from Language to Vision [74.78422371545716]
  Video sequences offer valuable temporal information, but existing large multimodal models (LMMs) fall short in understanding extremely long videos. In this paper, we approach this problem from the perspective of the language model. By simply extrapolating the context length of the language backbone, we enable LMMs to comprehend orders of magnitude more visual tokens without any video training.
  arXiv  Detail & Related papers  (2024-06-24T17:58:06Z)
• VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks [89.24440488456405]
  VisionLLM v2 is an end-to-end generalist multimodal large model (MLLM) It unifies visual perception, understanding, and generation within a single framework.
  arXiv  Detail & Related papers  (2024-06-12T16:44:50Z)
• From Text to Pixel: Advancing Long-Context Understanding in MLLMs [70.78454154014989]
  We introduce SEEKER, a multimodal large language model designed to tackle this issue. SEEKER aims to optimize the compact encoding of long text by compressing the text sequence into the visual pixel space via images. Our experiments on six long-context multimodal tasks demonstrate that SEEKER can leverage fewer image tokens to convey the same amount of textual information compared with the OCR-based approach.
  arXiv  Detail & Related papers  (2024-05-23T06:17:23Z)
• Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback [38.708690624594794]
  Video and text multimodal alignment remains challenging, primarily due to the deficient volume and quality of multimodal instruction-tune data. We present a novel alignment strategy that employs multimodal AI system to oversee itself called Reinforcement Learning from AI Feedback (RLAIF) In specific, we propose context-aware reward modeling by providing detailed video descriptions as context during the generation of preference feedback.
  arXiv  Detail & Related papers  (2024-02-06T06:27:40Z)
• MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning [42.68425777473114]
  Vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. We introduce vision-language Model with Multi-Modal In-Context Learning (MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently. Our experiments confirm that MMICL achieves new state-of-the-art zero-shot performance on a wide range of general vision-language tasks.
  arXiv  Detail & Related papers  (2023-09-14T17:59:17Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.