Related papers: ESANS: Effective and Semantic-Aware Negative Sampl…

Token sampling strategies critically influence text generation quality in large language models (LLMs). However, existing methods introduce additional hyperparameters, requiring extensive tuning and complicating deployment. We present…

Retrieval-Augmented Generation (RAG) systems rely on retrieving relevant evidence from a corpus to support downstream generation. The common practice of splitting a long document into multiple shorter passages enables finer-grained and…

This research aims to develop a dynamic and scalable framework to facilitate harmonization of Common Data Elements (CDEs) across heterogeneous biomedical datasets by addressing challenges such as semantic heterogeneity, structural…

Recommenders built upon implicit collaborative filtering are typically trained to distinguish between users' positive and negative preferences. When direct observations of the latter are unavailable, negative training data are constructed…

Retrieval-Augmented Generation (RAG) systems often rely on fixed top-k document selection mechanisms that ignore downstream generation quality and impose computational overheads. We propose SRAS (Sparse Reward-Aware Selector), a lightweight…

In fashion recommender systems, each product usually consists of multiple semantic attributes (e.g., sleeves, collar, etc). When making cloth decisions, people usually show preferences for different semantic attributes (e.g., the clothes…

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improves the model accuracy. Nevertheless, the reasons for the…

Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism. This approach significantly improves model…

Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity of translation errors. While fine-tuning models on human-annotated data improves ESD performance, acquiring…

A lack of generalizability is one key limitation of deep learning based segmentation. Typically, one manually labels new training images when segmenting organs in different imaging modalities or segmenting abnormal organs from distinct…

Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-texture, occlusions and reflections. Concurrently, deep…

Generative recommendation is emerging as a powerful paradigm that directly generates item predictions, moving beyond traditional matching-based approaches. However, current methods face two key challenges: token-item misalignment, where…

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage…

Despite the superiority of convolutional neural networks demonstrated in time series modeling and forecasting, it has not been fully explored on the design of the neural network architecture and the tuning of the hyper-parameters. Inspired…

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…

While the semi-blind source separation-based acoustic echo cancellation (SBSS-AEC) has received much research attention due to its promising performance during double-talk compared to the traditional adaptive algorithms, it suffers from…

Contrastive learning has been attracting much attention for learning unsupervised sentence embeddings. The current state-of-the-art unsupervised method is the unsupervised SimCSE (unsup-SimCSE). Unsup-SimCSE takes dropout as a minimal data…

Learning from implicit feedback is challenging because of the difficult nature of the one-class problem: we can observe only positive examples. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the…

Due to their ease of use and high accuracy, Word2Vec (W2V) word embeddings enjoy great success in the semantic representation of words, sentences, and whole documents as well as for semantic similarity estimation. However, they have the…