VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

• URL: http://arxiv.org/abs/2501.12327v1
• Date: Tue, 21 Jan 2025 17:50:43 GMT
• Title: VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model
• Authors: Xianwei Zhuang, Yuxin Xie, Yufan Deng, Liming Liang, Jinghan Ru, Yuguo Yin, Yuexian Zou,
• Abstract summary: We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VarGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. Notably, VARGPT naturally supports capabilities in autoregressive visual generation and instruction-to-image synthesis, showcasing its versatility in both visual understanding and generation tasks.
• Score: 38.61292051733335
• License:
• Abstract: We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VARGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. VARGPT innovatively extends the LLaVA architecture, achieving efficient scale-wise autoregressive visual generation within MLLMs while seamlessly accommodating mixed-modal input and output within a single model framework. Our VARGPT undergoes a three-stage unified training process on specially curated datasets, comprising a pre-training phase and two mixed visual instruction-tuning phases. The unified training strategy are designed to achieve alignment between visual and textual features, enhance instruction following for both understanding and generation, and improve visual generation quality, respectively. Despite its LLAVA-based architecture for multimodel understanding, VARGPT significantly outperforms LLaVA-1.5 across various vision-centric benchmarks, such as visual question-answering and reasoning tasks. Notably, VARGPT naturally supports capabilities in autoregressive visual generation and instruction-to-image synthesis, showcasing its versatility in both visual understanding and generation tasks. Project page is at: \url{https://vargpt-1.github.io/}

Related papers

• Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching [0.8611782340880084]
  This study proposes an innovative visual semantic embedding model, Multi-Headed Consensus-Aware Visual-Semantic Embedding (MH-CVSE) This model introduces a multi-head self-attention mechanism based on the consensus-aware visual semantic embedding model (CVSE) to capture information in multiple subspaces in parallel. In terms of loss function design, the MH-CVSE model adopts a dynamic weight adjustment strategy to dynamically adjust the weight according to the loss value itself.
  arXiv  Detail & Related papers  (2024-12-26T11:46:22Z)
• MetaMorph: Multimodal Understanding and Generation via Instruction Tuning [57.35160715164359]
  Visual-Predictive Instruction Tuning (VPiT) is a simple and effective extension to visual instruction tuning. VPiT teaches an LLM to predict discrete text tokens and continuous visual tokens from any input sequence of image and text data. We train our MetaMorph model and achieve competitive performance on both visual understanding and generation.
  arXiv  Detail & Related papers  (2024-12-18T18:58:50Z)
• SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding [66.74446220401296]
  We propose SynerGen-VL, a simple yet powerful encoder-free MLLM capable of both image understanding and generation. We introduce the token folding mechanism and the vision-expert-based progressive alignment pretraining strategy, which effectively support high-resolution image understanding. Our code and models shall be released.
  arXiv  Detail & Related papers  (2024-12-12T18:59:26Z)
• VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation [45.52926475981602]
  VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. VILA-U employs a single autoregressive next-token prediction framework for both tasks.
  arXiv  Detail & Related papers  (2024-09-06T17:49:56Z)
• MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model [49.931663904599205]
  MaVEn is an innovative framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. We show that MaVEn significantly enhances MLLMs' understanding in complex multi-image scenarios, while also improving performance in single-image contexts.
  arXiv  Detail & Related papers  (2024-08-22T11:57:16Z)
• VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation [79.02357561313785]
  We introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for both image and text modalities by employing a straightforward auto-regressive objective.
  arXiv  Detail & Related papers  (2023-12-14T18:59:43Z)
• VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation [33.41226268323332]
  Egocentric action anticipation is a challenging task that aims to make advanced predictions of future actions in the first-person view. Most existing methods focus on improving the model architecture and loss function based on the visual input and recurrent neural network. We propose a novel visual-semantic fusion enhanced and Transformer GRU-based action anticipation framework.
  arXiv  Detail & Related papers  (2023-07-08T06:49:54Z)
• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)

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.