Related papers: Integrating Discrete and Neural Features via Mixed…

Large vision-language models (LVLMs) perform outstandingly across various multimodal tasks. However, their ability to evaluate generated content remains limited, and training vision-language reward models (VLRMs) with preference data is…

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…

Recent advances in large language models (LLMs) have provided new opportunities for decision-making, particularly in the task of automated feature selection. In this paper, we first comprehensively evaluate LLM-based feature selection…

Large Language Models (LLMs) have achieved remarkable success, yet recent findings reveal that their deeper layers often contribute minimally and can be pruned without affecting overall performance. While some view this as an opportunity…

In this work, we focus on the detection of depression through speech analysis. Previous research has widely explored features extracted from pre-trained models (PTMs) primarily trained for paralinguistic tasks. Although these features have…

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the…

Neural radiance field (NeRF) has shown remarkable performance in generating photo-realistic novel views. Among recent NeRF related research, the approaches that involve the utilization of explicit structures like grids to manage features…

Deep Learning (DL) algorithms have shown impressive performance in diverse domains. Among them, audio has attracted many researchers over the last couple of decades due to some interesting patterns--particularly in classification of audio…

Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for training and final-layer representations for predictions, potentially overlooking the predictive power embedded in intermediate layers. Surprisingly,…

Training automatic speech recognition (ASR) models increasingly relies on decentralized federated learning to ensure data privacy and accessibility, producing multiple local models that require effective merging. In hybrid ASR systems,…

Large language models (LLMs) acquire extensive prior knowledge through large-scale pretraining and can be further enhanced via supervised fine-tuning (SFT) or reinforcement learning (RL)-based post-training. A growing body of evidence has…

This study explores the application and performance of Transformational Machine Learning (TML) in drug discovery. TML, a meta learning algorithm, excels in exploiting common attributes across various domains, thus developing composite…

We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…

While deep learning has reduced the prevalence of manual feature extraction, transformation of data via feature engineering remains essential for improving model performance, particularly for underwater acoustic signals. The methods by…

The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to…

Large Language Models (LLMs) are composed of neurons that exhibit various behaviors and roles, which become increasingly diversified as models scale. Recent studies have revealed that not all neurons are active across different datasets,…

Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of…

Traditional deep learning methods in medical imaging often focus solely on segmentation or classification, limiting their ability to leverage shared information. Multi-task learning (MTL) addresses this by combining both tasks through…

With increasing privacy concerns on data, recent studies have made significant progress using federated learning (FL) on privacy-sensitive natural language processing (NLP) tasks. Much literature suggests fully fine-tuning pre-trained…