4 papers
RoboChrono: A Real Robot Benchmark for Streaming Task Understanding
Yuzhou Wu, Longteng Fan, Zimeng Li +22
Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We introduce RoboChrono, a benchmark…
RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning
Kewei Hu, Wanchan Yu, Fangwen Chen +6
Despite rapid progress, embodied reasoning under real-world variability remains challenging. Existing approaches rely on demonstration-driven sequential biases, limiting flexibilit…
GSR: Learning Structured Reasoning for Embodied Manipulation
Kewei Hu, Michael Zhang, Wei Ying +7
Despite rapid progress, embodied agents still struggle with long-horizon manipulation that requires maintaining spatial consistency, causal dependencies, and goal constraints. A ke…
Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI
Ching-Chun Chang, Fan-Yun Chen, Shih-Hong Gu +3
As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial attacks manifest in two primary f…