Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Tianhang Zheng — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Tianhang Zheng
13
papers ·
122
citations ·
18
h-index
Northeast Agricultural University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Distributionally Adversarial Attack
2018 · 117 citations
HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
2025 · 5 citations
RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
2026
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
2026
Unveiling The Backdoor Mechanism Hidden Behind Catastrophic Overfitting In Fast Adversarial Training
2026
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
2026
Dynamic Target Attack
2025
NonTextual Target Attack
2025
Untargeted Jailbreak Attack
2025
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
2025
DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization
2025
Contextual Bandits for Unbounded Context Distributions
2024
Topics
Adversarial ML
LLM Security
Vulnerability Detection
cs.AI
cs.CL
Model Architecture
Safety & Alignment
Evaluation
Network Security
cs.LG