BLISS AI Speaker Series 2025

Join our free BLISS Speaker Series Summer 2025!

We are excited to feature Timothée Darcet, PhD student at Meta AI and Inria, who will discuss "CAPI: Cluster and Predict Latent Patches for Improved Masked Image Modeling", lasting approximately 45 minutes. After the talk, seize the opportunity to connect with fellow AI enthusiasts to share ideas and questions while enjoying free drinks. Door close by 7.15pm, so please come early! Also, "attend"ing (RSVP) here on Meetup is strictly necessary to be guaranteed entry.
Please note that Meetup has recently been quite keen on promoting its Plus program. However, you are not obligated to purchase it, as both our events and the platform remain free.

Who is this event for?
This event is open to everyone interested in state-of-the-art AI research. We especially design it for students, PhD candidates, academic researchers, and industry professionals with a research focus in machine learning.

Abstract: Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this talk, we systematically analyze target representations, loss functions, and architectures, to present CAPI - a novel pure-MIM framework that relies on the prediction of latent clusterings. Our approach leverages a clustering-based loss, which is stable to train, and exhibits promising scaling properties. Our ViT-L backbone, CAPI, achieves 83.8% accuracy on ImageNet and 32.1% mIoU on ADE20K with simple linear probes, substantially outperforming previous MIM methods and approaching the performance of the current state-of-the-art, DINOv2.

Join our free BLISS Speaker Series Summer 2025!

We are excited to feature Dr. Yu Xie, Senior Research Scientist at Microsoft AI4Science, who will discuss "Scalable Emulation of Protein Equilibrium Ensembles with Generative Deep Learning", lasting approximately 45 minutes. After the talk, seize the opportunity to connect with fellow AI enthusiasts to share ideas and questions while enjoying free drinks. Door close by 7.15pm, so please come early! Also, "attend"ing (RSVP) here on Meetup is strictly necessary to be guaranteed entry.
Please note that Meetup has recently been quite keen on promoting its Plus program. However, you are not obligated to purchase it, as both our events and the platform remain free.

Who is this event for?
This event is open to everyone interested in state-of-the-art AI research. We especially design it for students, PhD candidates, academic researchers, and industry professionals with a research focus in machine learning.

Abstract: Following the sequence and structure revolutions, predicting the dynamical mechanisms of proteins that implement biological function remains an outstanding scientific challenge. Several experimental techniques and molecular dynamics (MD) simulations can, in principle, determine conformational states, binding configurations and their probabilities, but suffer from low throughput. Here we develop a Biomolecular Emulator (BioEmu), a generative deep learning system that can generate thousands of statistically independent samples from the protein structure ensemble per hour on a single graphical processing unit. By leveraging novel training methods and vast data of protein structures, over 200 milliseconds of MD simulation, and experimental protein stabilities, BioEmu’s protein ensembles represent equilibrium in a range of challenging and practically relevant metrics. Qualitatively, BioEmu samples many functionally relevant conformational changes, ranging from formation of cryptic pockets, over unfolding of specific protein regions, to large-scale domain rearrangements. Quantitatively, BioEmu samples protein conformations with relative free energy errors around 1 kcal/mol, as validated against millisecond-timescale MD simulation and experimentally-measured protein stabilities. By simultaneously emulating structural ensembles and thermodynamic properties, BioEmu reveals mechanistic insights, such as the causes for fold destabilization of mutants, and can efficiently provide experimentally-testable hypotheses.

Join our free BLISS Speaker Series Summer 2025!

We are excited to feature Dr. Pierre Fernandez, Research Scientist at Meta AI, who will discuss "Watermark Anything with Localized Messages", lasting approximately 45 minutes. After the talk, seize the opportunity to connect with fellow AI enthusiasts to share ideas and questions while enjoying free drinks. Door close by 7.15pm, so please come early! Also, "attend"ing (RSVP) here on Meetup is strictly necessary to be guaranteed entry.
Please note that Meetup has recently been quite keen on promoting its Plus program. However, you are not obligated to purchase it, as both our events and the platform remain free.

Who is this event for?
This event is open to everyone interested in state-of-the-art AI research. We especially design it for students, PhD candidates, academic researchers, and industry professionals with a research focus in machine learning.

Abstract: Invisible image watermarking embeds information into image pixels in a way that remains imperceptible to the human eye but can still be retrieved even after significant image editing. However, traditional methods struggle when dealing with small, localized watermarked areas—something that often happens in real-world scenarios where images come from different sources or undergo modifications. In this talk, after a brief introduction to image watermarking, we’ll explore an approach designed to tackle this issue. Watermark Anything (ICLR 2025) reframes image watermarking as a segmentation problem. We’ll walk through the motivation behind this idea, how we developed and trained the model, the challenges we faced, and the final results.

Bio: Pierre Fernandez is a Research Scientist at FAIR Paris (the Fundamental AI Research lab at Meta). His research focuses on content protection and safety in machine learning, with a particular interest in watermarking generative models. He completed his PhD at FAIR and Inria Rennes, under the supervision of Matthijs Douze, Hervé Jégou, and Teddy Furon. Before his PhD, he studied at École Polytechnique, majoring in computer science and mathematics for visual computing.

Join our free BLISS Speaker Series Summer 2025!

We are excited to feature Daniel Duckworth, Senior Research Software Engineer at Google DeepMind, who will discuss "Radiance Fields are Dead (and why that’s OK)", lasting approximately 45 minutes. After the talk, seize the opportunity to connect with fellow AI enthusiasts to share ideas and questions while enjoying free drinks. Door close by 7.15pm, so please come early! Also, "attend"ing (RSVP) here on Meetup is strictly necessary to be guaranteed entry.
Please note that Meetup has recently been quite keen on promoting its Plus program. However, you are not obligated to purchase it, as both our events and the platform remain free.

Who is this event for?
This event is open to everyone interested in state-of-the-art AI research. We especially design it for students, PhD candidates, academic researchers, and industry professionals with a research focus in machine learning.

Abstract: TBD