paper-with-me

Papers

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

2025-01-12 · Michael Toker, Ido Galil, Hadas Orgad, Rinon Gal, Yoad Tewel, Gal Chechik, Yonatan Belinkov

Text-to-image (T2I) diffusion models rely on encoded prompts to guide the image generation process. Typically, these prompts are extended to a fixed length by adding padding tokens before text encoding. Despite being a default practice, the influence of padding tokens on the image generation process has not been investigated. In this work, we conduct the first in-depth analysis of the role padding tokens play in T2I models. We develop two causal techniques to analyze how information is encoded in the representation of tokens across different components of the T2I pipeline. Using these techniques, we investigate when and how padding tokens impact the image generation process. Our findings reveal three distinct scenarios: padding tokens may affect the model's output during text encoding, during the diffusion process, or be effectively ignored. Moreover, we identify key relationships between these scenarios and the model's architecture (cross or self-attention) and its training process (frozen or trained text encoder). These insights contribute to a deeper understanding of the mechanisms of padding tokens, potentially informing future model design and training practices in T2I systems.

📄 PDF Abstract BibTeX arXiv:2501.06751

Code (1)

tokeron/lens pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Exact Expressive Power of Transformers with Padding

2025-05-25 · William Merrill, Ashish Sabharwal

Chain of thought is a natural inference-time method for increasing the computational power of transformer-based large language models (LLMs), but comes at the cost of sequential decoding. Are there more efficient alterna…

Hard Attention

Silent Tokens, Loud Effects: Padding in LLMs

2025-09-23 · Rom Himelstein, Amit LeVi, Yonatan Belinkov, Avi Mendelson arxiv

Padding tokens are widely used in large language models (LLMs) to equalize sequence lengths during batched inference. While they should be fully masked, implementation errors can cause them to influence computation, and …

Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs

2025-10-04 · Bumjun Kim, Dongjae Jeon, Dueun Kim, Wonje Jeung 외 arxiv

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive models, offering flexible generation orders and strong performance on complex reasoning tasks. However, instruction-tuned …

VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination

2026-06-16 · Chunyu Liu, Zhengyang Fan, Kaisen Yang, Alex Lamb arxiv

MDLMs generate text by denoising a preallocated masked response canvas, making response-length modeling central to instruction tuning. Existing MDLMs often inherit the autoregressive convention of using repeated \texttt{…

Mathematical ReasoningCode Generation

Turn Waste into Worth: Rectifying Top-$k$ Router of MoE

2024-02-17 · Zhiyuan Zeng, Qipeng Guo, Zhaoye Fei, Zhangyue Yin 외

Sparse Mixture of Experts (MoE) models are popular for training large language models due to their computational efficiency. However, the commonly used top-$k$ routing mechanism suffers from redundancy computation and me…

Computational EfficiencyGPUMixture-of-Experts