Siu Ming Yiu
Identifiers
- name variant Siu Ming Yiu 0.60 · backfill
Papers (19)
- The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary cs.AI · 2026 · author #3
- Model Collapse as Cultural Evolution cs.CL · 2026 · author #3
- Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs cs.CL · 2026 · author #3
- Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography cs.CL · 2026 · author #3
- Brain-LLM Alignment Tracks Training Data, Not Typology cs.CL · 2026 · author #3
- Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution cs.NE · 2026 · author #3
- EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent cs.NE · 2026 · author #3
- SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters cs.DC · 2026 · author #3
- When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models cs.IR · 2026 · author #3
- FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification cs.AI · 2026 · author #3
- ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection cs.CL · 2026 · author #3
- AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking cs.SE · 2026 · author #3
- RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization cs.CL · 2026 · author #3
- SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models cs.LG · 2026 · author #3
- SigGate-GT: Taming Over-Smoothing in Graph Transformers via Sigmoid-Gated Attention cs.LG · 2026 · author #3
- Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension cs.LG · 2026 · author #3
- When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth cs.LG · 2026 · author #3
- Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection cs.AI · 2026 · author #3
- A multi-task learning model for malware classification with useful file access pattern from API call sequence cs.SD · 2016 · author #2
Mentions
- 2606.00376 #3 · arxiv_oai · confidence 0.70 Siu Ming Yiu
- 2605.23054 #3 · arxiv_oai · confidence 0.70 Siu Ming Yiu
- 2605.23039 #3 · arxiv_oai · confidence 0.70 Siu Ming Yiu
- 2605.23035 #3 · arxiv_oai · confidence 0.70 Siu Ming Yiu
- 2605.23032 #3 · arxiv_oai · confidence 0.70 Siu Ming Yiu
Frequent Coauthors
- Dongxin Guo 18 shared papers
- Jikun Wu 18 shared papers
- Xin Wang 1 shared papers