< Publications />

Workshop CL4FMAgents @ NeurIPS

When Rank Rises as LLMs Degrade

Zhaohui Geoffrey Wang

Workshop on Continual Learning for Foundation Models and Agents (CL4FMAgents) at the Conference on Neural Information Processing Systems (NeurIPS), non-archival, 2026

PDF arXiv Details

Workshop NExT-Game @ ICML

From Risk Scoring to Risk Allocation: A Density-Driven Framework for Diverse Monitoring in Multi-Agent Systems

Zhaohui Wang

NExT-Game Workshop on New Frontiers in Game-Theoretic Learning at the International Conference on Machine Learning (ICML), Seoul, South Korea (non-archival), 2026

PDF Project Details

Workshop VerifAI @ ICLR

Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference

Zhaohui Wang

VerifAI Workshop at the International Conference on Learning Representations (ICLR), 2026

PDF arXiv Details

Workshop C3NLP @ ACL

TabletCraft: Bridging a 4,000-Year Cultural Gap with Bidirectional Akkadian NMT and Cuneiform Rendering

Zhaohui Wang

4th Workshop on Cross-Cultural Considerations in NLP (C3NLP), co-located with ACL, San Diego, 2026

Code Project Details

Workshop RLxF @ ICML

Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL

Zhaohui Wang

RLxF Workshop at the International Conference on Machine Learning (ICML), 2026

Details

Workshop WSS @ ICML

Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM Families

Zhaohui Wang

Workshop on Weight-Space Symmetries (WSS) at the International Conference on Machine Learning (ICML), 2026

Details

Conference NLPCC

When Retrieval Systems Encode Wrong Entity-Context Bindings

Zhaohui Wang

CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2026

Code Details

Conference NLPCC

IntegriRef: A Five-Layer Bayesian Framework for Cross-Domain Reference Integrity Verification

Zhaohui Wang

CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2026

Code Details

Conference CIKM Featured

The Recall Ceiling: Why LLM Recommendation Reranking Fails in Practice

Zhaohui Wang

Proceedings of the 35th ACM International Conference on Information and Knowledge Management (CIKM), Rome, Italy, 2026

DOI Details

Preprint Preprint

Who Audits the Auditor? Tamper-Proof Fraud Detection with Blockchain-Anchored Explainable ML

Zhaohui Wang

arXiv preprint — accepted at IEEE COMPSAC 2026 (withdrawn; seeking resubmission), 2026

PDF arXiv Details

Workshop ProbML

When Individually Calibrated Models Become Collectively Miscalibrated

Zhaohui Wang

Symposium of Probabilistic Machine Learning (ProbML), 2026

PDF arXiv Details

Workshop AAMAS-SE Workshop

Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detection

Zhaohui Wang

Software Engineering Workshop at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2026

PDF Code arXiv Details

Conference ECML PKDD Featured

Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems

Zhaohui Wang

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2026

PDF Code arXiv Details

Conference ICML Featured

Persistent Semantic Entities in Tool-Augmented LLM Systems

Zhaohui Wang

International Conference on Machine Learning (ICML), 2026

PDF Code Project Details

Conference ICICS Featured

NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference

Zhaohui Geoffrey Wang

International Conference on Information and Communications Security (ICICS), 2026

PDF Code arXiv Details

Workshop LLA @ ICLR

Universe Routing: Why Self-Evolving Agents Need Epistemic Control

Zhaohui Wang

LLA Workshop at the International Conference on Learning Representations (ICLR), 2026

PDF Code arXiv Details

Workshop AIWILD @ ICLR

AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems

Zhaohui Wang

Workshop on Agents in the Wild: Safety, Security, and Beyond at the International Conference on Learning Representations (ICLR), 2026

PDF Code arXiv Details