SY
Siu-Ming Yiu
cs.LGcs.AIAlgorithmscs.CLSoftwarecs.CRcs.CVcs.IRcs.CEHigh-Throughput Nucleotide Sequencing
On Valency
published · living versionsW_ckcjjqbg·v1 · currentpublished
ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing
with Caiyi Sun, Yujing Sun
1 version
W_26xzgw86·v1published
Preprints & journals
166 papers in the corpus · 2003–2026Structured Latent Space Modeling over Multi-Scale Temporal Patches for Multivariate Time Series Forecasting2607.19404v2 · Xingsheng Chen, Deyu Yi, Siu-Ming Yiu2026 · 0 citationsarXiv
OptimalCap: Efficient and Robust LiDAR-Based Motion Capture in Free Environments.41790823 · Ren, Yiming, Sun, Yujing, Han, Xiao et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(7):8456-8469
SPDM: Geometry-Modulated State Space Modeling with Manifold Constraints for Time Series Forecasting2606.09917v1 · Xingsheng Chen, Siu-Ming Yiu2026 · 0 citationsarXiv
The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary2606.00376v2 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
Brain-LLM Alignment Tracks Training Data, Not Typology2605.23032v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography2605.23035v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs2605.23039v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
Model Collapse as Cultural Evolution2605.23054v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent2605.09777v2 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution2605.09781v2 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees2605.08710v1 · Dongxin Guo, Jikun Wu, Siu-Ming Yiu2026 · 0 citationsarXiv
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation2605.08716v1 · Jikun Wu, Dongxin Guo, Siu-Ming Yiu2026 · 0 citationsarXiv
The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems2606.28327v1 · Dongxin Guo, Jikun Wu, Siu-Ming Yiu2026 · 0 citationsarXiv
Efficient Prompt Learning for Traffic Forecasting2605.08273v1 · Qianru Zhang, Xinyi Gao, Alexander Zhou et al.2026 · 0 citationsThe VLDB Journal of 2026
A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era.42096352 · Li, Zongru, Chen, Xingsheng, Wen, Honggang et al.2026 · 8 citationsJournal of chemical theory and computation. 2026;22(10):4866-4887
SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters2605.00528v2 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models2604.26649v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization2604.23577v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking2604.23581v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection2604.23585v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification2604.23588v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
GeoCert: Certified Geometric AI for Reliable Forecasting2604.23474v1 · Regina Zhang, Zongru Li, Honggang Wen et al.2026 · 0 citationsarXiv
SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models2604.17691v1 · Dongxin Guo, Jikun Wu, Siu Ming Yiu2026 · 0 citationsarXiv
Capacity-Controlled Global Attention for Graph Transformers2604.17324v2 · Yang Liu, Dongxin Guo, Tom Zheng et al.2026 · 0 citationsarXiv
Coalition Formation in LLM Agent Networks: Stability Analysis and Convergence Guarantees2604.14386v1 · Dongxin Guo, Jikun Wu, Siu-Ming Yiu2026 · 0 citationsarXiv
UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer2603.19637v1 · Caiyi Sun, Yujing Sun, Xiangyu Li et al.2026 · 0 citationsarXiv
ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning2603.16112v2 · Tik Yu Yim, Wenting Tan, Sum Yee Chan et al.2026 · 0 citationsarXiv
UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration2604.16325v3 · Xingsheng Chen, Xianpei Mu, Deyu Yi et al.2026 · 0 citationsarXiv
Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving2602.18757v3 · Xiaoru Dong, Ruiqin Li, Xiao Han et al.2026 · 0 citationsarXiv
A hybrid unsupervised methodology on artificial intelligence filtering for automatically processing cellular DNA-encoded library (DEL) datasets.41502004 · Huang, Yiran, Tan, Xiao, Li, Xiaoyu et al.2026 · 0 citationsBioinformatics (Oxford, England). 2026;42(1)
MODE: Efficient Time Series Prediction with Mamba Enhanced by Low-Rank Neural ODEs2601.00920v2 · Xingsheng Chen, Regina Zhang, Bo Gao et al.2026 · 0 citationsarXiv
LIMA: Towards building a non-invasive and stealthy real-world adversarial attack model for traffic sign recognition systems.41505933 · Fang, Junbin, Shen, Yixuan, Sun, Yujing et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;197:108497
ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions2511.14342v2 · Xingwei He, Qianru Zhang, Pengfei Chen et al.2025 · 0 citationsarXiv
A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System2510.09721v3 · Jiale Guo, Suizhi Huang, Mei Li et al.2025 · 2 citationsarXiv
FLDmamba: Integrating Fourier and Laplace Transform Decomposition with Mamba for Enhanced Time Series Prediction2507.12803v1 · Qianru Zhang, Chenglei Yu, Haixin Wang et al.2025 · 0 citationsarXiv
AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Prediction2506.16001v2 · Qianru Zhang, Honggang Wen, Ming Li et al.2025 · 0 citationsICDE'2026
HUMOF: Human Motion Forecasting in Interactive Social Scenes2506.03753v3 · Caiyi Sun, Yujing Sun, Xiao Han et al.2025 · 0 citationsarXiv
HMamba: Hyperbolic Mamba for Sequential Recommendation2505.09205v1 · Qianru Zhang, Honggang Wen, Wei Yuan et al.2025 · 2 citationsarXiv
M2Rec: Multi-scale Mamba for Efficient Sequential Recommendation2505.04445v1 · Qianru Zhang, Liang Qu, Honggang Wen et al.2025 · 0 citationsarXiv
SeqNovo: De Novo Peptide Sequencing Prediction in IoMT via Seq2Seq.37792659 · Wang, Ke, Zhu, Mingjia, Boulila, Wadii et al.2025 · 6 citationsIEEE journal of biomedical and health informatics. 2025;29(4):2377-2387
Time Series Analysis in Frequency Domain: A Survey of Open Challenges, Opportunities and Benchmarks2504.07099v5 · Qianru Zhang, Yuting Sun, Honggang Wen et al.2025 · 0 citationsarXiv
UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis2502.06324v1 · Zemin Yang, Yujing Sun, Xidong Peng et al.2025 · 5 citationsarXiv
An Attack-Driven Incident Response and Defense System (ADIRDS)2502.02230v1 · Anthony Cheuk Tung Lai, Siu Ming Yiu, Ping Fan Ke et al.2025 · 0 citationsarXiv
A Statistical Physics Perspective: Understanding the Causality Behind Convolutional Neural Network Adversarial Vulnerability.38324429 · Wang, Ke, Zhu, Mingjia, Chen, Zicong et al.2025 · 1 citationIEEE transactions on neural networks and learning systems. 2025;36(2):2118-2132
Efficient Traffic Prediction Through Spatio-Temporal Distillation2501.10459v2 · Qianru Zhang, Xinyi Gao, Haixin Wang et al.2025 · 25 citationsAAAI'2025
Automatic identification of clinically important Aspergillus species by artificial intelligence-based image recognition: proof-of-concept study.39585232 · Tsang, Chi-Ching, Zhao, Chenyang, Liu, Yueh et al.2024 · 10 citationsEmerging microbes & infections. 2025;14(1):2434573
Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching2411.15860v1 · Yujing Sun, Caiyi Sun, Yuan Liu et al.2024 · 2 citationsarXiv
Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning2411.14937v2 · Junjie Shan, Ziqi Zhao, Jialin Lu et al.2024 · 2 citationsarXiv
HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning2410.10915v2 · Qianru Zhang, Xinyi Gao, Haixin Wang et al.2024 · 2 citationsCIKM 2025
TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions2410.04107v1 · Xingwei He, Qianru Zhang, A-Long Jin et al.2024 · 1 citationarXiv
Career total: at least 791 works. 166 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.