Denghui Zhang
20 papers · 2021–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (41) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🗃️
Keyword Collector
(103)
⚡
Prolific Year · Prolific
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(15)
Core AI
(15)
Machine Learning
(9)
Deep Learning
(7)
Learning Types · Machine Learning
(5)
Natural Language Processing
(4)
Learning Types · Deep Learning
(4)
Application Areas
(3)
Core Methods
(3)
Resources & Methods
(3)
Architectures
(2)
Models
(2)
Data Science & Analytics
(1)
Reinforcement Learning
(1)
Security & Privacy
(1)
Keywords
large language model
(7)
ai safety
(3)
training data
(2)
graph neural network
(2)
responsible ai
(2)
risk management
(2)
language model
(2)
content generation
(2)
copyright infringement
(2)
multi-agent system
(2)
self-supervised learning
(1)
working memory
(1)
language model alignment
(1)
model safety
(1)
cross-modal learning
(1)
puzzle solving
(1)
benchmark evaluation
(1)
point cloud
(1)
llm copyright
(1)
text generation
(1)
Papers
Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks
ACL 2026
Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks
AAAI 2026
Steganography Beyond Pixels: Reimagining Image Steganography as Cross-Modal Linguistic Communication
ACL 2026
ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation
NAACL 2025
Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
ACL 2025
DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
EMNLP 2025
EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents
ACL 2025
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
EMNLP 2025
LLMs and Copyright Risks: Benchmarks and Mitigation Approaches
NAACL 2025
Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
ICML 2025
Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting
EMNLP 2025
Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context
EMNLP 2025
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
EMNLP 2025
Do LLMs Know to Respect Copyright Notice?
EMNLP 2024
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
NeurIPS 2024
Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction
IJCAI 2024
Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification
AAAI 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