Related papers: AIBA: Attention-based Instrument Band Alignment fo…
Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Previous studies have shown a strong fit between surprisal…
With new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform the state-of-the-art in single-channel speech enhancement and audio representation learning. However, prior research has…
Modeling long sequences is crucial for various large-scale models; however, extending existing architectures to handle longer sequences presents significant technical and resource challenges. In this paper, we propose an efficient and…
The current scenario of IoT is witnessing a constant increase on the volume of data, which is generated in constant stream, calling for novel architectural and logical solutions for processing it. Moving the data handling towards the edge…
Flow-Matching (FM)-based zero-shot text-to-speech (TTS) systems exhibit high-quality speech synthesis and robust generalization capabilities. However, the speaker representation ability of such systems remains underexplored, primarily due…
Given a sequence of tokens generated by a language model, we may want to identify the preceding tokens that influence the model to generate this sequence. Performing such token attribution is expensive; a common approach is to ablate…
The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes feature extraction and fusion processes more challenging.…
Auditory attention decoding (AAD) identifies the attended speech stream in multi-speaker environments by decoding brain signals such as electroencephalography (EEG). This technology is essential for realizing smart hearing aids that address…
Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds often yield large variations in image quality and prompt-image alignment. We revisit…
We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (LALMs). As audio encodes non-semantic information, it induces severe train and test distribution shifts and can lead to spurious…
Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or…
Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…
Thanks to a Multiple Scattering Theory algorithm, we present a way to focus energy at the deep subwavelength scale, from the far-field, inside a cubic disordered bubble cloud by using broadband Time Reversal (TR). We show that the…
Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility…
Moonbeam is a transformer-based foundation model for symbolic music, pretrained on a large and diverse collection of MIDI data totaling 81.6K hours of music and 18 billion tokens. Moonbeam incorporates music-domain inductive biases by…
Communication in high frequencies such as millimeter wave and terahertz suffer from high path-loss and intense shadowing which necessitates beamforming for reliable data transmission. On the other hand, at high frequencies the channels are…
Text-to-audio (TTA) generation with fine-grained control signals, e.g., precise timing control or intelligible speech content, has been explored in recent works. However, constrained by data scarcity, their generation performance at scale…
Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a…
Large Language Models (LLMs), already shown to ace various unstructured text comprehension tasks, have also remarkably been shown to tackle table (structured) comprehension tasks without specific training. Building on earlier studies of…
Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model…