Related papers: DASH: Dynamic Audio-Driven Semantic Chunking for E…

Large language models (LLMs) have advanced in text and vision, but their reasoning on audio remains limited. Most existing methods rely on dense audio embeddings, which are difficult to interpret and often fail on structured reasoning…

Evaluating AI generated dubbed content is inherently multi-dimensional, shaped by synchronization, intelligibility, speaker consistency, emotional alignment, and semantic context. Human Mean Opinion Scores (MOS) remain the gold standard but…

In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…

Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks do not fully isolate audio visual association in noisy user generated videos. We…

In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on…

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…

Recent Large Audio-Language Models (LALMs) have shown strong performance on various audio understanding tasks such as speech translation and Audio Q\&A. However, they exhibit significant limitations on challenging audio reasoning tasks in…

Audio tagging aims to perform multi-label classification on audio chunks and it is a newly proposed task in the Detection and Classification of Acoustic Scenes and Events 2016 (DCASE 2016) challenge. This task encourages research efforts to…

Speech codecs are traditionally optimized for waveform fidelity, allocating bits to preserve acoustic detail even when much of it can be inferred from linguistic structure. This leads to inefficient compression and suboptimal performance on…

Cross-modal hashing is a promising approach for efficient data retrieval and storage optimization. However, contemporary methods exhibit significant limitations in semantic preservation, contextual integrity, and information redundancy,…

Point cloud semantic segmentation plays an essential role in autonomous driving, providing vital information about drivable surfaces and nearby objects that can aid higher level tasks such as path planning and collision avoidance. While…

Guided wave-based structural health monitoring (SHM) remains a powerful strategy for identifying early-stage defects and safeguarding vital aerospace structures. Yet, its practical use is often hindered by the enormous, high-dimensional…

Document chunking is a critical preprocessing step in dense retrieval systems, yet the design space of chunking strategies remains poorly understood. Recent research has proposed several concurrent approaches, including LLM-guided methods…

Unsupervised Semantic Segmentation (USS) involves segmenting images without relying on predefined labels, aiming to alleviate the burden of extensive human labeling. Existing methods utilize features generated by self-supervised models and…

Early detection of cognitive disorders such as Alzheimer's disease is critical for enabling timely clinical intervention and improving patient outcomes. In this work, we introduce CogniAlign, a multimodal architecture for Alzheimer's…

Domain adaptive segmentation (DAS) of numerous organelle instances from large-scale electron microscopy (EM) is a promising way to enable annotation-efficient learning. Inspired by SAM, we propose a promptable multitask framework, namely…

We present CoSense-LLM, an edge-first framework that turns continuous multimodal sensor streams (for example Wi-Fi CSI, IMU, audio, RFID, and lightweight vision) into compact, verifiable semantic tokens and coordinates with large language…

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Modern Large Language Models (LLMs) rely on Transformer self-attention, which scales quadratically with sequence length. Recent linear-time alternatives, like State Space Models (SSMs), often suffer from signal degradation over extended…

Distributed Acoustic Sensing (DAS) is an emerging technology for earthquake monitoring and subsurface imaging. The recorded seismic signals by DAS have several distinct characteristics, such as unknown coupling effects, strong anthropogenic…