Related papers: COCOLA: Coherence-Oriented Contrastive Learning of…

In music source separation, a standard training data augmentation procedure is to create new training samples by randomly combining instrument stems from different songs. These random mixes have mismatched characteristics compared to real…

We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additional contrastive example of opposite label. While Mansouri et…

Vocoder models have recently achieved substantial progress in generating authentic audio comparable to human quality while significantly reducing memory requirement and inference time. However, these data-hungry generative models require…

State-of-the-art (SOTA) image and text generation models are multimodal models that have many similarities to large language models (LLMs). Despite achieving strong performances, leading foundational multimodal model architectures…

Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model. However, existing designs suffers in performance due to misalignment between training…

Existing contrastive learning methods for anomalous sound detection refine the audio representation of each audio sample by using the contrast between the samples' augmentations (e.g., with time or frequency masking). However, they might be…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details…

Concept-oriented deep learning (CODL) is a general approach to meet the future challenges for deep learning: (1) learning with little or no external supervision, (2) coping with test examples that come from a different distribution than the…

We propose Corder, a self-supervised contrastive learning framework for source code model. Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks. The pre-trained model of Corder can be used…

Video-grounded dialogue systems aim to integrate video understanding and dialogue understanding to generate responses that are relevant to both the dialogue and video context. Most existing approaches employ deep learning models and have…

Medical image classification has been widely adopted in medical image analysis. However, due to the difficulty of collecting and labeling data in the medical area, medical image datasets are usually highly-imbalanced. To address this…

We propose a new high dimensional semiparametric principal component analysis (PCA) method, named Copula Component Analysis (COCA). The semiparametric model assumes that, after unspecified marginally monotone transformations, the…

Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to various categories of…

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

Weakly supervised learning algorithms are critical for scaling audio event detection to several hundreds of sound categories. Such learning models should not only disambiguate sound events efficiently with minimal class-specific annotation…

Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial perturbations. Existing methods primarily focus on adversarial fine-tuning or prompt…

The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar…

Computational musicology enables systematic analysis of performative and structural traits in recorded music, yet existing approaches remain largely tailored to notated, score-based repertoires. This study advances a methodology for…

Unsupervised representation learning has shown remarkable achievement by reducing the performance gap with supervised feature learning, especially in the image domain. In this study, to extend the technique of unsupervised learning to the…