Related papers: \emph{FoQuS}: A Forgetting-Quality Coreset Selecti…

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite…

Foundation models such as the recently introduced Segment Anything Model (SAM) have achieved remarkable results in image segmentation tasks. However, these models typically require user interaction through handcrafted prompts such as…

Network quantization has gained increasing attention with the rapid growth of large pre-trained language models~(PLMs). However, most existing quantization methods for PLMs follow quantization-aware training~(QAT) that requires end-to-end…

Large Transformer models have achieved impressive performance in many natural language tasks. In particular, Transformer based language models have been shown to have great capabilities in encoding factual knowledge in their vast amount of…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…

MOOC recommendation systems have received increasing attention to help learners navigate and select preferred learning content. Traditional methods such as collaborative filtering and content-based filtering suffer from data sparsity and…

Deep Feedback Models (DFMs) are a new class of stateful neural networks that combine bottom up input with high level representations over time. This feedback mechanism introduces dynamics into otherwise static architectures, enabling DFMs…

Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has…

Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing…

Automated emotion recognition in speech is a long-standing problem. While early work on emotion recognition relied on hand-crafted features and simple classifiers, the field has now embraced end-to-end feature learning and classification…

Micro-expressions recognition (MER) has essential application value in many fields, but the short duration and low intensity of micro-expressions (MEs) bring considerable challenges to MER. The current MER methods in deep learning mainly…

Explainable Multimodal Emotion Recognition (EMER) is an emerging task that aims to achieve reliable and accurate emotion recognition. However, due to the high annotation cost, the existing dataset (denoted as EMER-Fine) is small, making it…

Predicting materials properties from composition or structure is of great interest to the materials science community. Deep learning has recently garnered considerable interest in materials predictive tasks with low model errors when…

Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neuron sparsity reduces high-dimensional computations, both…

Test-time adaptation enables models to adapt to evolving domains. However, balancing the tradeoff between preserving knowledge and adapting to domain shifts remains challenging for model adaptation methods, since adapting to domain shifts…

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…

The field of face anti-spoofing (FAS) has witnessed great progress with the surge of deep learning. Due to its data-driven nature, existing FAS methods are sensitive to the noise in the dataset, which will hurdle the learning process.…

Content-based recommendation systems (CRSs) utilize content features to predict user-item interactions, serving as essential tools for helping users navigate information-rich web services. However, ensuring the effectiveness of CRSs…

Leveraging multimodal information from Magnetic Resonance Imaging (MRI) plays a vital role in lesion segmentation, especially for brain tumors. However, in clinical practice, multimodal MRI data are often incomplete, making it challenging…