Related papers: Boosting Domain Incremental Learning: Selecting th…

Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with…

Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks. L2O paradigms achieve great outcomes, e.g., refitting optimizer, generating unseen solutions iteratively or directly. However, conventional L2O…

Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain-invariant representations is pivotal for DG as they possess…

Semi-supervised learning (SSL) has emerged as a critical paradigm for medical image segmentation, mitigating the immense cost of dense annotations. However, prevailing SSL frameworks are fundamentally "inward-looking", recycling information…

We argue that inventory management presents unique opportunities for the reliable application of deep reinforcement learning (DRL). To enable this, we emphasize and test two complementary techniques. The first is Hindsight Differentiable…

Different from fine-tuning models pre-trained on a large-scale dataset of preset classes, class-incremental learning (CIL) aims to recognize novel classes over time without forgetting pre-trained classes. However, a given model will be…

Deep neural networks perform remarkably well in close-world scenarios. However, novel classes emerged continually in real applications, making it necessary to learn incrementally. Class-incremental learning (CIL) aims to gradually recognize…

In a practical recommender system, new interactions are continuously observed. Some interactions are expected, because they largely follow users' long-term preferences. Some other interactions are indications of recent trends in user…

Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability…

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Implicit Neural Representations (INRs) provide a powerful continuous framework for modeling complex visual and geometric signals, but spectral bias remains a fundamental challenge, limiting their ability to capture high-frequency details.…

The computational requirements for training deep neural networks (DNNs) have grown to the point that it is now standard practice to parallelize training. Existing deep learning systems commonly use data or model parallelism, but…

Convolutional Dictionary Learning (CDL) has emerged as a powerful approach for signal representation by learning translation-invariant features through convolution operations. While existing CDL methods are predominantly designed and used…

Portfolio optimization is essential for balancing risk and return in financial decision-making. Deep Reinforcement Learning (DRL) has stood out as a cutting-edge tool for portfolio optimization that learns dynamic asset allocation using…

On account of its many successes in inference tasks and denoising applications, Dictionary Learning (DL) and its related sparse optimization problems have garnered a lot of research interest. While most solutions have focused on single…

Machine/deep learning models have been widely adopted for predicting the configuration performance of software systems. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration…

Unsupervised domain adaptation aims to learn a model of classifier for unlabeled samples on the target domain, given training data of labeled samples on the source domain. Impressive progress is made recently by learning invariant features…

Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity…

Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images. However, most existing methods heavily rely on strictly pre-paired drone-satellite images for…