Related papers: Hearing is Believing? Evaluating and Analyzing Aud…
Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.g., mood, location, or social setting). In this paper, we introduce a Large Language Model…
Audio deepfakes pose a significant security threat, yet current state-of-the-art (SOTA) detection systems do not generalize well to realistic in-the-wild deepfakes. We introduce a novel \textbf{I}n-\textbf{C}ontext \textbf{L}earning…
Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that…
Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities.…
Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous,…
Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL…
In recent years, we have observed a rapid advancement in speech language models (SpeechLLMs), catching up with humans' listening and reasoning abilities. SpeechLLMs have demonstrated impressive spoken dialog question-answering (SQA)…
Advances in large language models (LLMs) have enabled significant capabilities in audio processing, resulting in state-of-the-art models now known as Large Audio Language Models (LALMs). However, minimal work has been done to measure audio…
Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this pattern arises from training objectives that reward user satisfaction over accuracy, it may become…
Large language models are often described as sycophantic, in the sense that they appear to flatter users or mirror their beliefs. We argue that this label is conceptually misleading: sycophancy implies motives and strategic intent, which…
An ideal multimodal agent should be aware of the quality of its input modalities. Recent advances have enabled large language models (LLMs) to incorporate auditory systems for handling various speech-related tasks. However, most audio LLMs…
Large audio language models (LALMs) can answer questions about speech, music, and environmental sounds, yet their internal reasoning is largely opaque and difficult to validate. We describe TalTech's solution to the Agent Track of the…
Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications.…
Audio-Visual Large Language Models (AVLLMs) are emerging as unified interfaces to multimodal perception. We present the first mechanistic interpretability study of AVLLMs, analyzing how audio and visual features evolve and fuse through…
Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in…
Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if…
Voice-based AI development faces unique challenges in processing both linguistic and paralinguistic information. This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech…
Large audio language models (LALMs) leverage multimodal representations to generate open-ended answers to natural language queries about audio. In this paper, we (1) provide empirical evidence that assessment of LALMs using the popular…
Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behavior in general contexts, its impact on…
Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter many audio-centric…