Awesome Multimodal
📄
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 Ma — most-cited papers & profile · Multimodal
← authors
·
overview
Siyuan Ma
11
papers ·
5
citations ·
0
h-index
Chinese Academy of Sciences · China University of Geosciences · Guangdong Polytechnic Normal University · Institute of Semiconductors · University of Chinese Academy of Sciences
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
2024 · 5 citations
Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent
2025
BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
2025
Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent
2025
BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
2025
Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement
2018
Learning the joint distribution of two sequences using little or no paired data
2022
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
2024
Topics
LLM Security
Vulnerability Detection
Evaluation
Agentic
Adversarial ML
Threat Intelligence
Malware Detection
Perception
Navigation
Manipulation