Ti
15 posts
Join us this afternoon at our @ICCVConference workshop on Open-Vocabulary 3D Scene Understanding✨🌺 #OpenSUN3D #iccv2025 ➡️ opensun3d.github.io @FrancisEngelman @aycatakmaz @AlexDelitzas @mapo1 @TrackingActions @sainingxie @jstraub6 @ir0armeni
Flow matching produces smooth, deterministic trajectories. In contrast, the sampling process of a diffusion model is chaotic, resembling the random motion of gas particles.
Join one of the strongest communities in AI in Europe. Call for applications for postdoc fellowships in all AI-related areas. Sellection at the first stage is based on the excellence of the candidate. Deadline 29th November. More info at: epfl.ch/research/fundi…
How does sensorimotor (S1/M1) cortex support adaptive motor control? Come find out in our latest preprint, which spans the development of a full adult forelimb model + physics simulations, neural-modeling for control, complex 🐭behavior 🕹️, large-scale imaging, and of course @DeepLabCut and @CEBRA! We hypothesized that S1 supports motor learning by computing prediction errors. To tackle this, we needed to understand what is being represented, and no studies have reported what forelimb S1 represents during learning in mice🧠🐭. Moreover, this requires modeling the body🦾: kinematics, torques, force, muscle activations, & proprioception (muscle spindles & GTOs). After our 7 year journey, we have an answer: S1 & M1 represent muscle-level features. During learning, computational motifs map to functional types (like muscle-encoding), and neural dynamics in S1 change & encode sensorimotor prediction errors! biorxiv.org/content/10.110… 🧵👇
