Dongxin Guo

CoRR, May, 2026

Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs.

[BibT_eX]

[DOI]

CoRR, May, 2026

Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography.

[BibT_eX]

[DOI]

CoRR, May, 2026

Brain-LLM Alignment Tracks Training Data, Not Typology.

[BibT_eX]

[DOI]

CoRR, May, 2026

Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution.

[BibT_eX]

[DOI]

CoRR, May, 2026

EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent.

[BibT_eX]

[DOI]

CoRR, May, 2026

Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation.

[BibT_eX]

[DOI]

Siu-Ming Yiu

CoRR, May, 2026

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees.

[BibT_eX]

[DOI]

Siu-Ming Yiu

CoRR, May, 2026

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters.

[BibT_eX]

[DOI]

CoRR, May, 2026

When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models.

[BibT_eX]

[DOI]

CoRR, April, 2026

FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification.

[BibT_eX]

[DOI]

CoRR, April, 2026

ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection.

[BibT_eX]

[DOI]

CoRR, April, 2026

AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking.

[BibT_eX]

[DOI]

CoRR, April, 2026

RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization.

[BibT_eX]

[DOI]

CoRR, April, 2026

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models.

[BibT_eX]

[DOI]

CoRR, April, 2026

SigGate-GT: Taming Over-Smoothing in Graph Transformers via Sigmoid-Gated Attention.

[BibT_eX]

[DOI]

CoRR, April, 2026

Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension.

[BibT_eX]

[DOI]

CoRR, April, 2026

When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth.

[BibT_eX]

[DOI]

CoRR, April, 2026

Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection.

[BibT_eX]

[DOI]

CoRR, April, 2026

Coalition Formation in LLM Agent Networks: Stability Analysis and Convergence Guarantees.

[BibT_eX]

[DOI]