This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: NR23PmrAp9uttKMUNxOrSoKTMbkI0WLfyDnnB0biuxs
Cover

Autoregressive Vision-LLMs: A Simplified Mathematical Formulation

Written by @textgeneration | Published on 2025/9/30
TL;DR —
Explaining the role of logits and the softmax function in converting the output vector into a final probability distribution for the next token.

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

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.

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

[story continues]

Written by
@textgeneration
Text Generation
Topics and
tags
vision-language-models|vision-llms|autoregressive-models|token-generation|softmax-function|deep-learning|logits|autoregressive-vision-llms
This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: NR23PmrAp9uttKMUNxOrSoKTMbkI0WLfyDnnB0biuxs