Year: 2026
Type: conference-paper
Abstract: Typical large vision-language models (LVLMs) apply autoregressive supervision primarily to textual responses, without fully exploiting causal learning over rich visual inputs.As a result, these models often emphasize visionto-language alignment while potentially overlooking fine-grained visual information.While prior work has explored autoregressive image generation, effectively leveraging autoregressive visual supervision to enhance image understanding remains an open challenge.In this paper, we introduce Autoregressive Semantic Visual Reconstruction (ASVR), which enables joint learning of visual and textual modalities within a unified autoregressive framework.ASVR trains models to autoregressively reconstruct the semantic content of input images, which consistently enhances multimodal comprehension.Notably, we show that even when provided with continuous image features as input, models can effectively reconstruct discrete semantic tokens, resulting in stable and consistent improvements across various multimodal understanding benchmarks.ASVR delivers significant performance gains and scalability across varying data scales, visual input, visual supervision and model architectures.In particular, ASVR generally improves baselines by 2-3% across 14 multimodal benchmarks.The code is available at https:// github.com/AlenjandroWang/ASVR.
Authors: Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei, Jiaqi Wang
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4417258192