Related papers: Enhancing Hyperspace Analogue to Language (HAL) Re…

Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominant Transformer architecture scales quadratically with the sequence length. While state-space models…

Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to induce hallucinations for contrastive decoding to mitigate…

Natural language processing (NLP) techniques have become mainstream in the recent decade. Most of these advances are attributed to the processing of a single language. More recently, with the extensive growth of social media platforms focus…

Automatically generating the descriptions of an image, i.e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing. Based on the…

Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often, performance gains and improved generalization can be…

Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to achieve a trade-off between labeling burden and performance,…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category…

Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by making multiple computational steps on the memory. However,…

Multimodal affective computing, learning to recognize and interpret human affects and subjective information from multiple data sources, is still challenging because: (i) it is hard to extract informative features to represent human affects…

Emotion plays a fundamental role in human interaction, and therefore systems capable of identifying emotions in speech are crucial in the context of human-computer interaction. Speech emotion recognition (SER) is a challenging problem,…

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic…

The internal workings of modern deep learning models stay often unclear to an external observer, although spatial attention mechanisms are involved. The idea of this work is to translate these spatial attentions into natural language to…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. In this paper, we propose a temporally…

Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on semantic image segmentation. One common way to extract multi-scale features is to feed…

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…