Autoregressive Vision-LLMs: A Simplified Mathematical Formulation

Explaining the role of logits and the softmax function in converting the output vector into a final probability distribution for the next token.


This content originally appeared on HackerNoon and was authored by Text Generation

Abstract and 1. Introduction

  1. Related Work

    2.1 Vision-LLMs

    2.2 Transferable Adversarial Attacks

  2. Preliminaries

    3.1 Revisiting Auto-Regressive Vision-LLMs

    3.2 Typographic Attacks in Vision-LLMs-based AD Systems

  3. Methodology

    4.1 Auto-Generation of Typographic Attack

    4.2 Augmentations of Typographic Attack

    4.3 Realizations of Typographic Attacks

  4. Experiments

  5. Conclusion and References

3 Preliminaries

3.1 Revisiting Auto-Regressive Vision-LLMs

\

\

:::info Authors:

(1) Nhat Chung, CFAR and IHPC, A*STAR, Singapore and VNU-HCM, Vietnam;

(2) Sensen Gao, CFAR and IHPC, A*STAR, Singapore and Nankai University, China;

(3) Tuan-Anh Vu, CFAR and IHPC, A*STAR, Singapore and HKUST, HKSAR;

(4) Jie Zhang, Nanyang Technological University, Singapore;

(5) Aishan Liu, Beihang University, China;

(6) Yun Lin, Shanghai Jiao Tong University, China;

(7) Jin Song Dong, National University of Singapore, Singapore;

(8) Qing Guo, CFAR and IHPC, A*STAR, Singapore and National University of Singapore, Singapore.

:::

:::info This paper is available on arxiv under CC BY 4.0 DEED license.

:::

\


This content originally appeared on HackerNoon and was authored by Text Generation


Print Share Comment Cite Upload Translate Updates
APA

Text Generation | Sciencx (2025-09-30T01:27:56+00:00) Autoregressive Vision-LLMs: A Simplified Mathematical Formulation. Retrieved from https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/

MLA
" » Autoregressive Vision-LLMs: A Simplified Mathematical Formulation." Text Generation | Sciencx - Tuesday September 30, 2025, https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/
HARVARD
Text Generation | Sciencx Tuesday September 30, 2025 » Autoregressive Vision-LLMs: A Simplified Mathematical Formulation., viewed ,<https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/>
VANCOUVER
Text Generation | Sciencx - » Autoregressive Vision-LLMs: A Simplified Mathematical Formulation. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/
CHICAGO
" » Autoregressive Vision-LLMs: A Simplified Mathematical Formulation." Text Generation | Sciencx - Accessed . https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/
IEEE
" » Autoregressive Vision-LLMs: A Simplified Mathematical Formulation." Text Generation | Sciencx [Online]. Available: https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/. [Accessed: ]
rf:citation
» Autoregressive Vision-LLMs: A Simplified Mathematical Formulation | Text Generation | Sciencx | https://www.scien.cx/2025/09/30/autoregressive-vision-llms-a-simplified-mathematical-formulation/ |

Please log in to upload a file.



There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.

Related Posts