Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 2
background 1
citation-polarity summary
years
2026 4representative citing papers
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
MV-VDP jointly predicts multi-view RGB and heatmap videos via diffusion to achieve data-efficient, robust robotic manipulation policies.
citing papers explorer
-
Why Does Agentic Safety Fail to Generalize Across Tasks?
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
-
dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
-
Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model
MV-VDP jointly predicts multi-view RGB and heatmap videos via diffusion to achieve data-efficient, robust robotic manipulation policies.
- Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control