8 papers
MANIGUARD: A Benchmark and Data Suite for Specification-Grounded Safety Evaluation and Improvement of Robotic Manipulation
Yiyan Peng, Philip Wang, Simon Sinong Zhan +11
Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce Mani…
CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
Zhenyang Ni, Yijiang Li, Ruochen Jiao +7
Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied man…
LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
Jiacheng Lin, Kun Qian, Arvind Srinivasan +15
Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete pi…
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
Simon Sinong Zhan, Qingyuan Wu, Philip Wang +4
Offline-to-online deployment of reinforcement-learning (RL) agents must bridge two gaps: (1) the sim-to-real gap, where real systems add latency and other imperfections not present…
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
Simon Sinong Zhan, Philip Wang, Qingyuan Wu +4
In this paper, we aim to tackle the limitation of the Adversarial Inverse Reinforcement Learning (AIRL) method in stochastic environments where theoretical results cannot hold and…
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
Simon Sinong Zhan, Yao Liu, Philip Wang +13
We present SENTINEL, a framework for formally evaluating the physical safety of foundation model (FM)-based embodied agents. SENTINEL is the first to provide multi-level safety eva…