Papers

Filtered to safety frameworks · clear filter

Browse by term

continual learning 33reinforcement learning 21large language models 9vision-language models 8language models 6benchmarking 5autoregressive models 4diffusion transformers 4generative models 4multimodal learning 4robotics 4video generation 4benchmarks 3computer vision 3policy optimization 3self-distillation 3vision-language-action models 3world modeling 3agent-based systems 2autonomous agents 2calibration 2coding agents 2diffusion models 2foundation models 2image synthesis 2in-context learning 2knowledge graphs 2LLMs 2multimodal evaluation 2multimodal large language models 2

Matching papers

SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction

24 upvotes · 17 JUL 2026 · Xue Yu, Bo Yuan, Pengshuai Yang et al.

This paper introduces SeerGuard, a safety framework that helps mobile GUI agents make safe decisions by predicting potential outcomes of their actions before they are executed. Practitioners caring about the safety of autonomous mobile agents might be interested in this research.

mobile GUI agentssafety frameworksworld model predictionmulti-task learningsemantic next-state prediction