Awesome Large Language Models
📄
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
Siyuan Liang — most-cited papers & profile · Large Language Models
← authors
·
overview
Siyuan Liang
18
papers ·
2
citations ·
0
h-index
Beijing Institute of Technology · Beijing Electronic Science and Technology Institute · Beijing Research Institute of Mechanical and Electrical Technology
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
2024 · 1 citations
SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
2024 · 1 citations
SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models
2025
RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
2025
Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models
2025
Explaining multimodal LLMs via intra-modal token interactions
2025
Iclshield: Exploring And Mitigating In-context Learning Backdoor Attacks
2025
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
2025
Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents
2025
Universal Camouflage Attack On Vision-language Models For Autonomous Driving
2025
Bridging The Task Gap: Multi-task Adversarial Transferability In CLIP And Its Derivatives
2025
Natural Reflection Backdoor Attack On Vision Language Model For Autonomous Driving
2025
Roboview-bias: Benchmarking Visual Bias In Embodied Agents For Robotic Manipulation
2025
No Query, No Access
2025
Poison Once, Control Anywhere: Clean-text Visual Backdoors In Vlm-based Mobile Agents
2025
Topics
Vision-Language Models
Adversarial ML
LLM Security
Video-Language
Visual QA & Reasoning
Vulnerability Detection
Embodied & Agents
Instruction Tuning
Image-Text Retrieval
Threat Intelligence