5 papers
Search-Augmented Masked Diffusion Models for Constrained Generation
Huu Binh Ta, Michael Cardei, Alvaro Velasquez +1
Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for struc…
Criticality and Safety Margins for Reinforcement Learning
Alexander Grushin, Walt Woods, Alvaro Velasquez +1
State of the art reinforcement learning methods sometimes encounter unsafe situations. Identifying when these situations occur is of interest both for post-hoc analysis and during…
From Abstraction to Reality: DARPA's Vision for Robust Sim-to-Real Autonomy
Erfaun Noorani, Zachary Serlin, Ben Price +1
The DARPA Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) program aims to address rapid and robust transfer of autonomy technologies across dynamic…
A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models
Longchao Da, Justin Turnau, Thirulogasankar Pranav Kutralingam +3
Deep Reinforcement Learning (RL) has been explored and verified to be effective in solving decision-making tasks in various domains, such as robotics, transportation, recommender s…
Imperceptible Adversarial Examples in the Physical World
Weilin Xu, Sebastian Szyller, Cory Cornelius +5
Adversarial examples in the digital domain against deep learning-based computer vision models allow for perturbations that are imperceptible to human eyes. However, producing simil…