2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- City University of Hong Kong, Shenzhen Research InstituteCN108 papers
- University of Hong KongHK94 papers
- Chinese Academy of SciencesCN88 papers
- Chinese University of Hong KongHK72 papers
- Hong Kong University of Science and TechnologyHK64 papers
- Southern University of Science and TechnologyCN63 papers
- Nanyang Technological UniversitySG59 papers
- Tsinghua UniversityCN56 papers
- University of Chinese Academy of SciencesCN53 papers
- Hong Kong Polytechnic UniversityHK52 papers
- Institut National de la Recherche ScientifiqueCA52 papers
- Shanghai Jiao Tong UniversityCN51 papers
1,953 papers
Delay-Aware Reinforcement Learning for O-RAN Control under Stochastic Reward Feedback
Xingqi Wu, Junaid Farooq, Tao Li +2
Reinforcement learning (RL) is increasingly employed for real-time control in Open Radio Access Networks (O-RANs). However, the asynchronous nature of O-RAN feedback introduces sto…
CRISP: Co-designing Pruning and Scheduling for Efficient MoE Inference on Edge Servers
Congwei Zhang, Youming Tao, Yifei Zou +6
Mixture-of-Experts (MoE) inference on memory-constrained edge platforms is often dominated by expert-weight movement rather than computation. Although each token activates only a s…
Thermal Responses of Spin Density and Spin Current Induced by Bogoliubov Fermi Surfaces in Proximity Superconductors
Yingwen Zhang, Cong Xiao, Xiao Li
The emergence of Bogoliubov Fermi surfaces in s-wave proximity superconducting systems provides a unique platform for generating nontrivial spin responses in the presence of spin-o…
De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift
Mengyuan Liu, Yuhang Wen, Yi Zhang +4
Skeleton sequences can represent both individual actions and multi-entity interactions, encompassing human bodies, hands, objects, and robots. Existing approaches to recognize skel…
SIMS: Scale-Invariant Merit-Function-Based Scalarization for Multi-Task Learning
Zebin Chen, Fei Xing, Yang Chen +4
Multi-task learning (MTL) requires navigating unavoidable trade-offs among competing objectives. This paradigm is frequently formulated as multi-objective optimization (MOO), where…
Reconfigurable microwave photonic Fano filters based on optical Kerr microcombs
Qi Zou, Jiayang Wu, Yang Sun +9
Microwave photonic (MWP) Fano filters, featuring asymmetric filter shapes that enable steep spectral transitions, are attractive for high bandwidth microwave signal processing such…
Robotic Fabric Alignment System for Sewing Using Global Local Weighted ICP
Wenbo Dong, Dipankar Bhattacharya Member, Kai Tang +5
Accurate fabric alignment is a critical step that must be performed before sewing. This paper presents a novel automated fabric alignment system. The system estimates the poses of…
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
Zhaoqi Wang, Daqing He, Zijian Zhang +13
While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption att…
Large Models for Battery Prognostics and Health Management: A Review and Future Roadmap
Jiale Liu, Huan Wang, Weicheng Wang +3
Battery Prognostics and Health Management (BPHM) is critical for ensuring the safe, reliable, and cost-effective operation of batteries across electric vehicles, grid storage, and…
RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning
Kwunhang Wong, Jichang Yang, Karl M. H. Lai +7
Edge Artificial Intelligence of Things (AIoT) systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory (RRAM) is an…
Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis
Jiachen Qian, Junyu Li
Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains unclear how much jailbreak capabili…
CRAFT: Exploring Wearable Creative AI on Smart Glasses for Fiction Writing in Real-World Contexts
Runze Cai, Yuxuan Huang, Lin-Ping Yuan +5
Creative writing increasingly integrates AI assistance, yet current tools miss in-situ moments when writers draw inspiration from real-world experiences. We envision Context-aware…
Neural Network-Based Impedance Identification and Stability Analysis for Double-Sided Feeding Railway Systems
Xiangyu Meng, Guiyang Hu, Zhigang Liu +4
The double-sided power supply railway system increases the simultaneous operation of vehicles on the grid, potentially causing system instability and oscillation overvoltage issues…
Orbital-Selective Mott and Antiferromagnetic Phases in Diagonally Compressed Kagome Lattice
Jiewei Ding, Ho-Kin Tang, Wing Chi Yu
We perform determinant quantum Monte Carlo simulations of the half-filled Hubbard model on a diagonally compressed kagome lattice, introducing exponential decay long-range hopping…
BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing
Feifei Wang, Shiyuan Yang, Xiaoyu Li +1
As instruction-based editing models and multimodal large language models advance, diverse image editing tasks have become feasible. However, achieving precise and consistent geomet…
LLM-as-a-Judge for Reliable and Explainable Offline Evaluation in Top-K Recommendation
Yue Que, Junyi Zhou, Xiaokun Zhang +3
Recommendation evaluation plays a crucial role in guiding the refinement and deployment of recommender systems. Most existing trials rely on offline evaluation using Top-K metrics…
BIM-Loc: BIM-Integrated Discrepancy-Aware LiDAR-based Indoor Localization
Yinqiang Zhang, Liang Lu, Yipeng Pan +5
Accurate and robust localization is a fundamental requirement for service and inspection robots, particularly in feature-sparse indoor environments where traditional systems strugg…
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9
Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriev…
A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback
Yunian Pan, Tao Li, Quanyan Zhu
Mirror descent provides a geometric framework for learning in games, but its last-iterate behavior can fail in weakly stable regimes, where the dynamics may exhibit rotational or r…
Training-free image inversion for one-step diffusion models
Tao Wu, Senmao Li, Yaxing Wang +3
In this work, we introduce a novel training-free inversion (TFinv) framework for one-step diffusion models,addressing key challenges in real image inversion and editing. We first i…
SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
Jiachen Qian
Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning…
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Peiyang Liu, Ziqiang Cui, Xi Wang +2
Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external…
Recasting AI Data Centers as Engines for Carbon Removal
Zhicong Fang, Boyu Zhang, Jin Shang +1
AI data centers (AIDCs) are rapidly increasing electricity demand and associated CO2 emissions, yet they also generate continuous low-grade waste heat. Here, we assess whether this…
ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval
Ke Chen, Shengyuan Han, Yongfeng Huang +4
This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries. Prevailing single-round retrieval paradigms face a performance…