paper-with-me

홈 › Papers

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

2026-04-09 · Zhengyang Sun, Yu Chen, Xin Zhou, Xiaofan Li, Xiwu Chen, Dingkang Liang, Xiang Bai arxiv

Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA , a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsistencies by selecting discriminative self- and cross-attention heads to derive a countable latent layout. It then refines this layout conservatively and modulates cross-attention to guide regeneration. On the introduced CountBench, NUMINA improves counting accuracy by up to 7.4% on Wan2.1-1.3B, and by 4.9% and 5.5% on 5B and 14B models, respectively. Furthermore, CLIP alignment is improved while maintaining temporal consistency. These results demonstrate that structural guidance complements seed search and prompt enhancement, offering a practical path toward count-accurate text-to-video diffusion. The code is available at https://github.com/H-EmbodVis/NUMINA.

📄 PDF Abstract BibTeX arXiv:2604.08546

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LLMs Know More About Numbers than They Can Say

2026-02-08 · Fengting Yuchi, Li Du, Jason Eisner arxiv

Although state-of-the-art LLMs can solve math problems, we find that they make errors on numerical comparisons with mixed notation: "Which is larger, $5.7 \times 10^2$ or $580$?" This raises a fundamental question: Do LL…

Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers

2018-05-21 · ACL 2018 7 · Georgios P. Spithourakis, Sebastian Riedel

Numeracy is the ability to understand and work with numbers. It is a necessary skill for composing and understanding documents in clinical, scientific, and other technical domains. In this paper, we explore different str…

Language Modelling

Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues

2025-02-13 · Ye-eun Cho, Yunho Maeng

This study investigates whether vision-language models (VLMs) can perform pragmatic inference, focusing on ignorance implicatures, utterances that imply the speaker's lack of precise knowledge. To test this, we systemati…

ImplicaturesInformativeness

NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models

2024-06-05 · Ancheng Xu, Minghuan Tan, Lei Wang, Min Yang 외

Numeral systems and units of measurement are two conjoined topics in activities of human beings and have mutual effects with the languages expressing them. Currently, the evaluation of Large Language Models (LLMs) often …

MathMathematical Reasoning

Generating Natural Language Numerals with TeX

2020-09-01 · CLIB 2020 9 · Ivan Derzhanski, Milena Veneva

Sometimes one needs to produce a text in which many numbers have to be written out in words. Writing such a text and ensuring it is error-free can be a burden, especially if the author is not fluent in the language. Such…