9 citations · 33 across the 21 of their papers we have counts for
24 papers
SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation
Zhenrui Yue, Huimin Zeng, Yueqi Wang +8
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for improving large language models (LLMs) on various tasks, yet its sparse outcome rewards lac…
Retrieval Augmented Conversational Recommendation with Reinforcement Learning
Zhenrui Yue, Honglei Zhuang, Zhen Qin +4
Large language models (LLMs) exhibit enhanced capabilities in language understanding and generation. By utilizing their embedded knowledge, LLMs are increasingly used as conversati…
FASA: Frequency-aware Sparse Attention
Yifei Wang, Yueqi Wang, Zhenrui Yue +6
The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address th…
Hybrid Latent Reasoning via Reinforcement Learning
Zhenrui Yue, Bowen Jin, Huimin Zeng +6
Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hid…
Transferable Sequential Recommendation via Vector Quantized Meta Learning
Zhenrui Yue, Huimin Zeng, Yang Zhang +2
While sequential recommendation achieves significant progress on capturing user-item transition patterns, transferring such large-scale recommender systems remains challenging due…
Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation
Yueqi Wang, Zhenrui Yue, Huimin Zeng +2
Despite recent advancements in language and vision modeling, integrating rich multimodal knowledge into recommender systems continues to pose significant challenges. This is primar…
Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments
Zhenrui Yue, Huimin Zeng, Lanyu Shang +3
The rapid propagation of misinformation poses substantial risks to public interest. To combat misinformation, large language models (LLMs) are adapted to automatically verify claim…
Open-Vocabulary Federated Learning with Multimodal Prototyping
Huimin Zeng, Zhenrui Yue, Dong Wang
Existing federated learning (FL) studies usually assume the training label space and test label space are identical. However, in real-world applications, this assumption is too ide…
Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation
Zhenrui Yue, Huimin Zeng, Yimeng Lu +3
The proliferation of online misinformation has posed significant threats to public interest. While numerous online users actively participate in the combat against misinformation,…
Federated Recommendation via Hybrid Retrieval Augmented Generation
Huimin Zeng, Zhenrui Yue, Qian Jiang +1
Federated Recommendation (FR) emerges as a novel paradigm that enables privacy-preserving recommendations. However, traditional FR systems usually represent users/items with discre…
Linear Recurrent Units for Sequential Recommendation
Zhenrui Yue, Yueqi Wang, Zhankui He +3
State-of-the-art sequential recommendation relies heavily on self-attention-based recommender models. Yet such models are computationally expensive and often too slow for real-time…
Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning
Zhenrui Yue, Huimin Zeng, Mengfei Lan +2
With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only…
MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning
Zhenrui Yue, Huimin Zeng, Yang Zhang +2
With emerging topics (e.g., COVID-19) on social media as a source for the spreading misinformation, overcoming the distributional shifts between the original training domain (i.e.,…
Region-Aware Portrait Retouching with Sparse Interactive Guidance
Huimin Zeng, Jie Huang, Jiacheng Li +1
Portrait retouching aims to improve the aesthetic quality of input portrait photos and especially requires human-region priority. The deep learning-based methods largely elevate th…
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
Zhenrui Yue, Huimin Zeng, Bernhard Kratzwald +2
Question answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target dom…
On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks
Huimin Zeng, Zhenrui Yue, Yang Zhang +3
In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems. Targeting at the go…
Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup
Huimin Zeng, Zhenrui Yue, Ziyi Kou +3
In the real-world application of COVID-19 misinformation detection, a fundamental challenge is the lack of the labeled COVID data to enable supervised end-to-end training of the mo…
Domain Adaptation for Question Answering via Question Classification
Zhenrui Yue, Huimin Zeng, Ziyi Kou +2
Question answering (QA) has demonstrated impressive progress in answering questions from customized domains. Nevertheless, domain adaptation remains one of the most elusive challen…
Contrastive Domain Adaptation for Early Misinformation Detection: A Case Study on COVID-19
Zhenrui Yue, Huimin Zeng, Ziyi Kou +2
Despite recent progress in improving the performance of misinformation detection systems, classifying misinformation in an unseen domain remains an elusive challenge. To address th…
Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders
Zhenrui Yue, Huimin Zeng, Ziyi Kou +2
While sequential recommender systems achieve significant improvements on capturing user dynamics, we argue that sequential recommenders are vulnerable against substitution-based pr…
Efficient Localness Transformer for Smart Sensor-Based Energy Disaggregation
Zhenrui Yue, Huimin Zeng, Ziyi Kou +2
Modern smart sensor-based energy management systems leverage non-intrusive load monitoring (NILM) to predict and optimize appliance load distribution in real-time. NILM, or energy…
Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
Zhenrui Yue, Zhankui He, Huimin Zeng +1
We investigate whether model extraction can be used to "steal" the weights of sequential recommender systems, and the potential threats posed to victims of such attacks. This type…
Certified Defense via Latent Space Randomized Smoothing with Orthogonal Encoders
Huimin Zeng, Jiahao Su, Furong Huang
Randomized Smoothing (RS), being one of few provable defenses, has been showing great effectiveness and scalability in terms of defending against -norm adversarial perturba…
Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks
Huimin Zeng, Chen Zhu, Tom Goldstein +1
Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional d…