You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<ahref="/publications/2025-09-mouse-vs-ai-neurips-challenge/" itemprop="url">Mouse vs. AI: A neuroethological benchmark for visual robustness and neural alignment</a>
1261
+
<ahref="/publications/2025-09-neural-activity-shaping/" itemprop="url">Deep learning-based control of electrically evoked activity in human visual cortex</a>
1262
1262
</h3>
1263
1263
1264
1264
1265
1265
<divitemprop="articleBody">
1266
-
<pclass="m-0">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.</p>
1266
+
<pclass="m-0">We developed a data-driven neural control framework for a visual cortical prosthesis in a blind human, showing that deep learning can synthesize efficient, stable stimulation patterns that reliably evoke percepts and outperform conventional calibration methods.</p>
<ahref="/publications/2025-07-checkerboard-raster/" itemprop="url">Simulated prosthetic vision confirms checkerboard as an effective raster pattern for epiretinal implants</a>
1394
+
<ahref="/publications/2025-09-mouse-vs-ai-neurips-challenge/" itemprop="url">Mouse vs. AI: A neuroethological benchmark for visual robustness and neural alignment</a>
1397
1395
</h3>
1398
1396
1399
1397
1400
1398
<divitemprop="articleBody">
1401
-
<pclass="m-0">Using an immersive VR system, we systematically evaluated two behavioral tasks under four raster patterns (horizontal, vertical, checkerboard, and random) and found checkerboard raster to be the most effective.</p>
1399
+
<pclass="m-0">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.</p>
0 commit comments