Awesome Computer Vision
📄
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
Xingjun Ma — most-cited papers & profile · Computer Vision
← authors
·
overview
Xingjun Ma
17
papers ·
3
citations ·
33
h-index
The University of Melbourne · Fudan University · Shanghai Institute of Planned Parenthood Research · Shanghai Key Laboratory of Trustworthy Computing
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Toward Evaluating Robustness Of Reinforcement Learning With Adversarial Policy
2023 · 3 citations
Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation
2026
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
2026
Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
2026
DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
2025
StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
2025
Fedapt: Federated Adversarial Prompt Tuning For Vision-language Models
2025
Defense-to-attack: Bypassing Weak Defenses Enables Stronger Jailbreaks In Vision-language Models
2025
Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models
2024
Towards Fair and Privacy-Preserving Federated Deep Models
2019
Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models
2023
Topics
Vision-Language Models
Multi-Agent
Adversarial ML
Vulnerability Detection
Threat Intelligence
Video-Language
Federated Learning
Safety
Planning
Visual QA & Reasoning