The paper introduces SCALR, a novel framework that generates synthetic user-item interaction data from a source domain to augment a target recommendation domain, significantly improving system perform…

This paper derives deterministic limits for transfer learning performance of linear discriminant analysis in high-dimensional two-class classification under spiked covariance models.

The paper proposes a Variational Adapter (VACSR) to improve cross-modal similarity representation by treating fine-grained image-text matching as a variational inference problem, thereby mitigating th…

The paper introduces CityGen, a diffusion-based framework that enables zero-label city adaptation for autonomous driving by synthesizing city-style data conditioned on HD maps and visual prompts, sign…

The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

The paper proposes Value-order Decomposition (VOD) to address the challenge of cross-domain generalization in industrial anomaly detection by disentangling and suppressing object-category-, defect-typ…

The paper introduces Inconsistency-Aware Minimization (IAM), a novel training objective that uses a label-free measure called local inconsistency to improve model generalization, particularly in semi-…

The paper proposes FedCONST, an approach for federated learning that adaptively modulates update magnitudes to prevent overfitting and promote stronger generalization.

The paper proposes REED, a post-training representation editing method that significantly improves cross-domain linguistic steganalysis performance by deterministically editing intermediate feature re…

The paper proposes SPHERE, a novel framework that uses large language models to create semantic user personas, enabling effective cross-domain recommendation knowledge transfer between completely disj…

This paper introduces PETRA, a large-scale Petroleum Engineering Text for Retrieval Adaptation dataset and pipeline that converts noisy public web data into a curated domain corpus and synthetic super…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

This paper demonstrates that in-domain pretraining of BERT significantly improves the detection of DNS exfiltration, particularly in maintaining a low false positive rate.

The paper proposes a clustering-enhanced domain adaptation method that significantly improves cross-domain intrusion detection in industrial control systems by aligning feature distributions and enhan…

The paper proposes a multi-modal contrastive learning framework to improve the generalization of machine learning models in cybersecurity by transferring knowledge from rich textual vulnerability desc…

The paper proposes an extended version of Hypencoder, a retrieval approach that encodes queries as shallow neural networks, achieving comparable effectiveness with fewer active parameters and higher s…