paper-with-me

홈 › Papers

AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description

2024-07-22 · Junyu Xie, Tengda Han, Max Bain, Arsha Nagrani, Gül Varol, Weidi Xie, Andrew Zisserman

Our objective is to generate Audio Descriptions (ADs) for both movies and TV series in a training-free manner. We use the power of off-the-shelf Visual-Language Models (VLMs) and Large Language Models (LLMs), and develop visual and text prompting strategies for this task. Our contributions are three-fold: (i) We demonstrate that a VLM can successfully name and refer to characters if directly prompted with character information through visual indications without requiring any fine-tuning; (ii) A two-stage process is developed to generate ADs, with the first stage asking the VLM to comprehensively describe the video, followed by a second stage utilising a LLM to summarise dense textual information into one succinct AD sentence; (iii) A new dataset for TV audio description is formulated. Our approach, named AutoAD-Zero, demonstrates outstanding performance (even competitive with some models fine-tuned on ground truth ADs) in AD generation for both movies and TV series, achieving state-of-the-art CRITIC scores.

📄 PDF Abstract BibTeX arXiv:2407.15850

Code (1)

Jyxarthur/AutoAD-Zero 공식 구현 pytorch

Tasks

Sentence

Similar Papers 제목 키워드 기반

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models

2025-11-04 · Aashray Reddy, Andrew Zagula, Nicholas Saban arxiv

Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions while real-world attacks unfold through adap…

AutoAdapt: An Automated Domain Adaptation Framework for LLMs

2026-03-09 · Sidharth Sinha, Anson Bastos, Xuchao Zhang, Akshay Nambi 외 arxiv

Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, inc…

Domain Adaptation

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

2023-12-14 · Zimian Wei, Lujun Li, Peijie Dong, Zheng Hui 외

The substantial success of Vision Transformer (ViT) in computer vision tasks is largely attributed to the architecture design. This underscores the necessity of efficient architecture search for designing better ViTs aut…

Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis

2021-06-22 · Miao Zhang, Wei Huang, Li Wang

The recently proposed training-free NAS methods abandon the training phase and design various zero-cost proxies as scores to identify excellent architectures, arousing extreme computational efficiency for neural architec…

Computational EfficiencyNetwork PruningNeural Architecture SearchSensitivity

LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data

2025-08-12 · Peng Wang, Dongsheng Wang, He Zhao, Hangting Ye 외 arxiv

Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing advanced LLMs in few-shot and even zero-shot…