activity
20242026
collaborators
Showing 2024Show all

7 papers · 1 filter

cs.CL2024

Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR

Minghan Wang, Yuxia Wang, Thuy-Trang Vu +2

Recent advancements in multimodal large language models (MLLMs) have made significant progress in integrating information across various modalities, yet real-world applications in…

cs.CL2024

Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models

Hao Yang, Lizhen Qu, Ehsan Shareghi +1

Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to…

cs.CL2024

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

Hao Yang, Lizhen Qu, Ehsan Shareghi +1

Large language models (LLMs) have exhibited outstanding performance in engaging with humans and addressing complex questions by leveraging their vast implicit knowledge and robust…

cs.SD2024

Human Brain Exhibits Distinct Patterns When Listening to Fake Versus Real Audio: Preliminary Evidence

Mahsa Salehi, Kalin Stefanov, Ehsan Shareghi

In this paper we study the variations in human brain activity when listening to real and fake audio. Our preliminary results suggest that the representations learned by a state-of-…

cs.CL2024

Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights

Hao Yang, Lizhen Qu, Ehsan Shareghi +1

Large Multimodal Models (LMMs) have achieved great success recently, demonstrating a strong capability to understand multimodal information and to interact with human users. Despit…

cs.CL2024

Towards Uncertainty-Aware Language Agent

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

While Language Agents have achieved promising success by placing Large Language Models at the core of a more versatile design that dynamically interacts with the external world, th…