How does the brain extract relevant visual features from the rich, dynamic visual input that typifies active exploration, and how does the neural representation of these features support visual navigation?
Jing Peng is a former MS student, now lab volunteer working on the “Mouse vs. AI” NeurIPS competition.
M.S. in Computer Science, 2025
University of California, Santa Barbara
How does the brain extract relevant visual features from the rich, dynamic visual input that typifies active exploration, and how does the neural representation of these features support visual navigation?
We propose the Mouse vs. AI: Robust Foraging Competition at NeurIPS ‘25, a novel bioinspired visual robustness benchmark to test generalization in reinforcement learning (RL) agents trained to navigate a virtual environment toward a visually cued target.
Marius Schneider, Joe Canzano, Jing Peng, Yuchen Hou, Spencer LaVere Smith, Michael Beyeler arXiv:2509.14446