4 papers
Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering
Zikui Cai, Kaushal Janga, Tan Dat Dao +15
Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes. Ho…
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning
Yuanchen Ju, Yongyuan Liang, Yen-Jen Wang +7
Mobile manipulators in households must both navigate and manipulate. This requires a compact, semantically rich scene representation that captures where objects are, how they funct…
Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis
Jeffrey Yang Fan Chiang, Seungjae Lee, Jia-Bin Huang +2
Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibi…
Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models
Seungjae Lee, Daniel Ekpo, Haowen Liu +3
Exploration is essential for general-purpose robotic learning, especially in open-ended environments where dense rewards, explicit goals, or task-specific supervision are scarce. V…