6 citations · 10 across the 31 of their papers we have counts for
33 papers
FedHUR: Learning Hierarchical Utility-Guided Client Relations for Personalized Federated Recommendation
Mingzhe Han, Jiahao Liu, Dongsheng Li +5
Federated recommendation enables collaborative model training while keeping user interaction data on local clients. A central problem in federated recommendation is how to aggregat…
ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults
Weide Zhan, Qumu Shaqu, Yuanqing Liu +6
While autonomous mobile agents hold great potential for assisting older adults with smartphone usage, existing GUI benchmarks mainly rely on explicit, goal-oriented instructions an…
StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
Guanming Liu, Yuqi Ren, Hansu Gu +5
A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent obs…
From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
Jiahao Liu, Mingzhe Han, Guanming Liu +6
Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-ba…
Drift-Aware Continual Tokenization for Generative Recommendation
Yuebo Feng, Jiahao Liu, Mingzhe Han +5
Generative recommendation commonly adopts a two-stage pipeline in which a learnable tokenizer maps items to discrete token sequences (i.e. identifiers) and an autoregressive genera…
SparkTales: Facilitating Cross-Language Collaborative Storytelling through Coordinator-AI Collaboration
Wenxin Zhao, Peng Zhang, Hansu Gu +6
Cross-language collaborative storytelling plays a vital role in children's language learning and cultural development, fostering both expressive ability and intercultural awareness…
Echoes of Norms: Investigating Counterspeech Bots' Influence on Bystanders in Online Communities
Mengyao Wang, Shuai Ma, Nuo Li +4
Counterspeech offers a non-repressive approach to moderate hate speech in online communities. Research has examined how counterspeech chatbots restrain hate speakers and support ta…
Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
Jiayun Wu, Peixu Hou, Shan Qu +4
Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior ac…
Power Echoes: Investigating Moderation Biases in Online Power-Asymmetric Conflicts
Yaqiong Li, Peng Zhang, Peixu Hou +7
Online power-asymmetric conflicts are prevalent, and most platforms rely on human moderators to conduct moderation currently. Previous studies have been continuously focusing on in…
RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction
Ziye Tong, Jiahao Liu, Weimin Zhang +7
Multimodal content is crucial for click-through rate (CTR) prediction. However, directly incorporating continuous embeddings from pre-trained models into CTR models yields suboptim…
Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
Anrui Chen, Ruijun Huang, Xin Zhang +15
Mixture-of-Experts (MoE) architectures are often considered a natural fit for continual learning because sparse routing should localize updates and reduce interference, yet MoE Tra…
SD-MoE: Spectral Decomposition for Effective Expert Specialization
Ruijun Huang, Fang Dong, Xin Zhang +16
Mixture-of-Experts (MoE) architectures scale Large Language Models via expert specialization induced by conditional computation. In practice, however, expert specialization often f…
IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference
Guanming Liu, Meng Wu, Peng Zhang +8
Large language models (LLMs) have become integral to modern Human-AI collaboration workflows, where accurately understanding user intent serves as a crucial step for generating sat…
Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction
Jiahao Liu, Hongji Ruan, Weimin Zhang +7
This paper explores effective numerical feature embedding for Click-Through Rate prediction in streaming environments. Conventional static binning methods rely on offline statistic…
SoulSeek: Exploring the Use of Social Cues in LLM-based Information Seeking
Yubo Shu, Peng Zhang, Meng Wu +8
Social cues, which convey others' presence, behaviors, or identities, play a crucial role in human information seeking by helping individuals judge relevance and trustworthiness. H…
Dynamic Feature-Embedding Communication via Codebook Distillation for Federated Recommendation
Mingzhe Han, Jiahao Liu, Dongsheng Li +6
Federated recommendation systems commonly protect user privacy by keeping user parameters on local devices, while exchanging item parameters for collaborative model training. Howev…
Metis: Training LLMs with FP4 Quantization
Hengjie Cao, Mengyi Chen, Yifeng Yang +13
This work identifies anisotropy in the singular value spectra of parameters, activations, and gradients as the fundamental barrier to low-bit training of large language models (LLM…
"Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth
Yaqiong Li, Peng Zhang, Lin Wang +4
Risk perception is subjective, and youth's understanding of toxic content differs from that of adults. Although previous research has conducted extensive studies on toxicity detect…
IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
Yuzhuo Bai, Shitong Duan, Muhua Huang +7
Trained on various human-authored corpora, Large Language Models (LLMs) have demonstrated a certain capability of reflecting specific human-like traits (e.g., personality or values…
MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions
Yanxu Zhu, Shitong Duan, Xiangxu Zhang +7
Recently Multimodal Large Language Models (MLLMs) have achieved considerable advancements in vision-language tasks, yet produce potentially harmful or untrustworthy content. Despit…
Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
Jiongran Wu, Jiahao Liu, Dongsheng Li +7
Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommenda…
LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
Shengkang Gu, Jiahao Liu, Dongsheng Li +7
Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies of…
AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
Jing Yao, Shitong Duan, Xiaoyuan Yi +6
Assessing Large Language Models'(LLMs) underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases. Nevertheless, current…
FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation
Mingzhe Han, Dongsheng Li, Jiafeng Xia +5
Recommendation algorithms rely on user historical interactions to deliver personalized suggestions, which raises significant privacy concerns. Federated recommendation algorithms t…