Lina Yao

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing

Rui Wang, Junjie Wu, Yu Xia, Tong Yu et autres

Rui Wang, Junda Wu, Yu Xia, Tong Yu, Ruiyi Zhang, Ryan A. Rossi, Subrata Mitra, Lina Yao, Julian McAuley. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

us, au (code pays fourni par la source)

From Small to Large: In-Context Learning as a New Paradigm for Domain Generalization

Guanglin Zhou, Z. Y. Han, Shaoan Xie, Shiming Chen et autres

au, cn, us, ae, sa (code pays fourni par la source)

Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning

Xiaocong Chen, Siyu Wang, Tong Yu, Lina Yao

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize …

au, us (code pays fourni par la source)

Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration

Xingmei Wang, Cheng-Kai Huang, Guohao Nie, Quan Z. Sheng et autres

Bridging 2D and 3D sensor modalities is critical for robust perception in autonomous systems. However, image-to-point cloud (I2P) registration remains challenging due to the semantic-geometric gap between texture-rich but depth-ambiguous images and sparse yet metrically precise point clouds, as well as the …

Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition

Matthew Nolan, Lina Yao, Robert M. Davidson

Human Activity Recognition (HAR) has seen significant advancements with the adoption of deep learning techniques, yet challenges remain in terms of data requirements, reliability and robustness. This paper explores a novel application of Ensemble Distribution Distillation (EDD) within a self-supervised learning framework …

Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning

Huiyi Wang, Haodong Lu, Lina Yao, Dong Gong

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable representation in pre-trained models (PTMs), PTM-based CL methods perform effective continual adaptation …

au (code pays fourni par la source)

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

Ruhan Wang, Zhiyong Wang, Chengkai Huang, Rui Wang et autres

For question-answering (QA) tasks, in-context learning (ICL) enables language models to generate responses without modifying their parameters by leveraging examples provided in the input. However, the effectiveness of ICL heavily depends on the availability of high-quality examples, which are often scarce due …

Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems

Le Pan, Yuanjiang Cao, Chengkai Huang, Wenjie Zhang et autres

Recommender Systems (RSs) aim to provide personalized recommendations for users. A newly discovered bias, known as sentiment bias, uncovers a common phenomenon within Review-based RSs (RRSs): the recommendation accuracy of users or items with negative reviews deteriorates compared with users or items …

A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms

Chengkai Huang, Hongtao Huang, Tong Yu, Kaige Xie et autres

Recommender systems (RS) have become essential in filtering information and personalizing content for users. RS techniques have traditionally relied on modeling interactions between users and items as well as the features of content using models specific to each task. The emergence of …

Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition

Matthew Nolan, Lina Yao

au (code pays fourni par la source)

Towards Robust Cross-Domain Recommendation with Joint Identifiability of User Preference

Jing Du, Zesheng Ye, Bin Guo, Zhiwen Yu et autres

Recent cross-domain recommendation (CDR) studies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect disentanglement is challenging in practice, because user behaviors in CDR are highly complex, and the true underlying …

Dual Contrastive Transformer for Hierarchical Preference Modeling in Sequential Recommendation

Chengkai Huang, Shoujin Wang, Xianzhi Wang, Lina Yao

Sequential recommender systems (SRSs) aim to predict the subsequent items which may interest users via comprehensively modeling users' complex preference embedded in the sequence of user-item interactions. However, most of existing SRSs often model users' single low-level preference based on item ID …