paper-with-me

홈 › Papers

SFTok: Bridging the Performance Gap in Discrete Tokenizers

2025-12-18 · Qihang Rao, Borui Zhang, Wenzhao Zheng, Jie Zhou, Jiwen Lu arxiv

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in lower-dimensional spaces, thereby improving computational efficiency and reducing complexity. Discrete tokenizers naturally align with the autoregressive paradigm but still lag behind continuous ones, limiting their adoption in multimodal systems. To address this, we propose \textbf{SFTok}, a discrete tokenizer that incorporates a multi-step iterative mechanism for precise reconstruction. By integrating \textbf{self-forcing guided visual reconstruction} and \textbf{debias-and-fitting training strategy}, SFTok resolves the training-inference inconsistency in multi-step process, significantly enhancing image reconstruction quality. At a high compression rate of only 64 tokens per image, SFTok achieves state-of-the-art reconstruction quality on ImageNet (rFID = 1.21) and demonstrates exceptional performance in class-to-image generation tasks (gFID = 2.29).

📄 PDF Abstract BibTeX arXiv:2512.16910

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyImage ReconstructionImage Generation

Similar Papers 제목 키워드 기반

From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval

2025-02-18 · Jian Jia, Jingtong Gao, Ben Xue, Junhao Wang 외

Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs). These tokenizers serve as the …

Information Retrievalmultimodal generationRecommendation SystemsSurvey

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

2025-03-20 · Yuqing Wang, Zhijie Lin, Yao Teng, Yuanzhi Zhu 외

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straigh…

Quantization

CODA: Repurposing Continuous VAEs for Discrete Tokenization

2025-03-22 · Zeyu Liu, Zanlin Ni, Yeguo Hua, Xin Deng 외

Discrete visual tokenizers transform images into a sequence of tokens, enabling token-based visual generation akin to language models. However, this process is inherently challenging, as it requires both compressing visu…

Semantic-Aware Prefix Learning for Token-Efficient Image Generation

2026-03-26 · Qingfeng Li, Haoxian Zhang, Xu He, Songlin Tang 외 arxiv

Visual tokenizers play a central role in latent image generation by bridging high-dimensional images and tractable generative modeling. However, most existing tokenizers are still trained with reconstruction-dominated ob…

Representation LearningImage Generation

On the Adversarial Robustness of Discrete Image Tokenizers

2026-02-20 · Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion, Francesco Croce arxiv

Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, …

Adversarial Robustness