Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models

• URL: http://arxiv.org/abs/2608.28082v1
• Date: Fri, 28 Aug 2026 08:51:57 GMT
• Title: Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models
• Abstract summary: We introduce Attribute Token Arithmetic (ATA), a method that enables disentangled and continuous attribute control in visual autoregressive modelling.<n>We show that ATA achieves identity-preserving, fine-grained, and multi-attribute adjustment, outperforming existing autoregressive editing baselines in controllability, generality, and computational efficiency.
• Score: 39.64892851584864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive text-to-image generation has recently achieved remarkable progress, offering high-fidelity synthesis via a unified generative framework. However, fine-grained semantic control remains challenging due to the attribute entanglement and the misalignment between textual and fine-grained visual representations. In this paper, we introduce Attribute Token Arithmetic (ATA), a method that enables disentangled and continuous attribute control in visual autoregressive modelling. Inspired by the vector arithmetic property observed in word embeddings, ATA identifies semantic directions corresponding to visual attributes (e.g., aging, fatness, emotion) directly within the pretrained autoregressive latent space. These directions are learned from a single reference image, without model retraining or large-scale supervision. During generation, attributes can be continuously adjusted and compositionally combined through simple arithmetic operations with other attribute tokens. Extensive experiments demonstrate that ATA achieves identity-preserving, fine-grained, and multi-attribute adjustment, outperforming existing autoregressive editing baselines in controllability, generality, and computational efficiency. Our code will be available at https://github.com/Madaoer/ATA.

Related papers

• ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both [55.182037225013836]
  ATLAS is a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit.<n> ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability.
  arXiv  Detail & Related papers  (2026-05-14T17:59:55Z)
• TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets [26.16152568319517]
  TokenDial is a framework for continuous, slider-style attribute control in pretrained text-to-video generation models.<n>We learn attribute-specific token offsets without retraining the backbone, using pretrained understanding signals.<n>We demonstrate TokenDials effectiveness on diverse attributes and prompts, achieving stronger controllability and higher-quality edits than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-29T05:07:41Z)
• Self-Corrected Image Generation with Explainable Latent Rewards [55.29175717238288]
  We propose xLARD, a self-correcting framework that guides generation through Explainable LAtent RewarDs.<n>xLARD introduces a lightweight corrector that refines latent representations based on structured feedback from model-generated references.<n> Experiments show that xLARD improves semantic alignment and visual fidelity while maintaining generative priors.
  arXiv  Detail & Related papers  (2026-03-26T02:59:35Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions [20.351245266660378]
  Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images.<n>Providing efficient control over individual subjects, particularly the attributes characterizing them, remains a key challenge.<n>No current approach offers both simultaneously, resulting in a gap when trying to achieve precise continuous and subject-specific attribute modulation.
  arXiv  Detail & Related papers  (2024-03-25T18:00:42Z)
• Text Attribute Control via Closed-Loop Disentanglement [72.2786244367634]
  We propose a novel approach to achieve a robust control of attributes while enhancing content preservation. In this paper, we use a semi-supervised contrastive learning method to encourage the disentanglement of attributes in latent spaces. We conducted experiments on three text datasets, including the Yelp Service review dataset, the Amazon Product review dataset, and the GoEmotions dataset.
  arXiv  Detail & Related papers  (2023-12-01T01:26:38Z)
• Exploiting Semantic Attributes for Transductive Zero-Shot Learning [97.61371730534258]
  Zero-shot learning aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. We present a novel transductive ZSL method that produces semantic attributes of the unseen data and imposes them on the generative process. Experiments on five standard benchmarks show that our method yields state-of-the-art results for zero-shot learning.
  arXiv  Detail & Related papers  (2023-03-17T09:09:48Z)
• Towards Disentangling Latent Space for Unsupervised Semantic Face Editing [21.190437168936764]
  Supervised attribute editing requires annotated training data which is difficult to obtain and limits the editable attributes to those with labels. In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing.
  arXiv  Detail & Related papers  (2020-11-05T03:29:24Z)
• Fine-grained Sentiment Controlled Text Generation [28.20006438705556]
  Controlled text generation techniques aim to regulate specific attributes while preserving the attribute independent content. We propose DE-VAE, a hierarchical framework which captures both information enriched entangled representation and attribute specific disentangled representation.
  arXiv  Detail & Related papers  (2020-06-17T14:17:58Z)

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.