iiinova — where your digital self keeps evolving

Jorge FdCD

@jorgefdcd.bsky.social

820 followers 1.5K following 46 posts

CNRS researcher working at the Institut de Physique Théorique (IPhT) in Paris-Saclay. Interested in statistical physics, machine learning, and biological data modeling. Website: sites.google.com/view/jorgefdcd

Posts Replies Media

Jorge FdCD @jorgefdcd.bsky.social · 5h

Our paper on Spherical Boltzmann machines is accepted at #NeurIPS2026. A solvable energy-based model where training-time phase transitions explain sampling temperature tuning, double descent, tempered posteriors, and more.

120

Jorge FdCD @jorgefdcd.bsky.social · 01/07/2026

@cnrs.fr published a popular summary of our recent work: Using recordings of whole-brain activity in zebrafish larvae, a French team has shown that it is possible to translate spontaneous neural activity between individuals without matching neurons one-to-one.

150

Jorge FdCD @jorgefdcd.bsky.social · 16/06/2026

New preprint: Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models with Thomas Tulinski, Simona Cocco, Rémi Monasson 🧵

121

Jorge FdCD @jorgefdcd.bsky.social · 23/05/2026

How can we steer protein language models toward specific traits, without losing sequence diversity? In our new preprint, we introduce Iterative Lookback Monte Carlo (ILMC)—a training-free sampling strategy that balances generation quality, steering constraints, and diversity.

131