Get started
Author

Dongxin Guo

Observed name: Guo, Dongxin
Observed institution: University of Hong Kong
OpenAlex ID: A5133844069
SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 10
PDF
RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 3
PDF
Coalition Formation in LLM Agent Networks: Stability Analysis and Convergence Guarantees
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 3
PDF
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 2
PDF
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation
2026 · Wu, Jikun, Guo, Dongxin, et al. · arXiv (Cornell University) · 2
PDF
SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 2
PDF
When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth
2026 · Dongxin Guo, Jikun Wu, et al. · International Joint Conference on Neural Networks (IJCNN) · 1
PDF
Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 1
PDF
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University) · 1
PDF
Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection
2026 · Dongxin Guo, Jikun Wu, et al. · International Joint Conference on Neural Networks (IJCNN)
PDF
Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension
2026 · Dongxin Guo, Jikun Wu, et al. · International Joint Conference on Neural Networks (IJCNN)
PDF
Brain-LLM Alignment Tracks Training Data, Not Typology
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University)
PDF
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University)
PDF
When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University)
PDF
The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems
2026 · Guo, Dongxin, Wu, Jikun, et al. · arXiv (Cornell University)
PDF
Works count: 15
Citation count: 25
H-index: 3
I10-index: 1
Year
Topic
Type