Denghui Zhang

18 papers · 2021–2026 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (7) 🏃 Academic Marathon (5) 🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (38) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (7) 🧭 Keyword Pioneer 🗃️ Keyword Collector (94) ⚡ Prolific Year (10) 💎 Century Club (17) 🔥 Unstoppable (5) ❓ The Questioner

Conferences

EMNLP (6) AAAI (5) ACL (2) NAACL (2) ICML (1) IJCAI (1) NIPS (1)

Top co-authors

Zhaozhuo Xu (8) Yanzhou Pan (4) Cheng Qian (4) Heng Ji (4) Xiusi Chen (3) Yanjie Fu (3) Hao Liu (3) Hui Xiong (3) Zixuan Yuan (3) Shenglan Li (2)

Research topics

Keywords

large language model (7) ai safety (3) responsible ai (2) content generation (2) risk management (2) training datum (2) language model (2) copyright infringement (2) multi-agent system (2) graph neural network (2) self-supervised learning (1) language model alignment (1) model safety (1) working memory (1) puzzle solving (1) benchmark evaluation (1) point cloud (1) online-offline optimization (1) text generation (1) hierarchical planning (1)

Papers

Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks AAAI 2026

Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context EMNLP 2025

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic EMNLP 2025

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals EMNLP 2025

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage EMNLP 2025

Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting EMNLP 2025

Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks ICML 2025

ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation NAACL 2025

LLMs and Copyright Risks: Benchmarks and Mitigation Approaches NAACL 2025

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents ACL 2025

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation ACL 2025

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making NIPS 2024

Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification AAAI 2024

Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction IJCAI 2024

Do LLMs Know to Respect Copyright Notice? EMNLP 2024

Human-Instructed Deep Hierarchical Generative Learning for Automated Urban Planning AAAI 2023

Learning to Walk with Dual Agents for Knowledge Graph Reasoning AAAI 2022

Self-Supervised Prototype Representation Learning for Event-Based Corporate Profiling AAAI 2021