Voxel51’s Daniel Gural and Nebius’s Dhruv Diddi will host a series of talks on video reasoning, action-conditioned world models, and novel-view synthesis. Northeastern University’s PAIR Lab researchers will present work spanning trajectory-grounded reasoning, reflectance confocal microscopy, and learning visual reasoning from instructional video.
*** Agenda *** • Hosts — Daniel Gural at Voxel51 • Hosts — Dhruv Diddi at Nebius • GeneralistJEPA: Generalizing Action-Conditioned Latent World Models with Video Model Rewards — Haichao Zhang at Northeastern University (PAIR Lab) • CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy — Tooba Imtiaz at Northeastern University (PAIR Lab) • Motion-o: Trajectory-Grounded Video Reasoning — Shayda Moezzi at Northeastern University (PAIR Lab) • Structure Over Scale: Learning Visual Reasoning from Pedagogical Video — Bishoy Galoaa at Northeastern University (PAIR Lab)
View all events and join the community →
Sign in to see guests
Sign In