Dmitry Krotov

CDS Silver Professor Julia Kempe (@kempelab.bsky.social) is co-organizing this year's ICLR 2026 Workshop on New Frontiers in Associative Memory.

The workshop is accepting submissions related to associative memory until Feb 14.

nfam2026.amemory.net

Now that ICML papers are submitted, what could be a better time to prepare a cool paper for the New Frontiers in Associative Memory workshop @iclr-conf.bsky.social?

Deadline: February 14, 2026.

Call for papers: nfam2026.amemory.net

Submissions are open via Open Review.

Workshop website: nfam2026.amemory.net

The lineup of invites speakers is amazing: Jay McClelland, Xueyan Niu, Paul Liang, Meisam Razaviyayn, Natalia Berloff, David Clark, and others. There will also be exciting panel discussions.

The call for contributed papers is now open via Open Review. Please consider submitting your best work!

Official #ICLR2026 workshop on Associative Memory! The scope covers algorithms, architectures, hardware design, agentic workflows, and other ideas where memory plays a crucial computational role.

I will also present our paper Dense Associative Memory with Epanechnikov Energy on Wednesday. Stop by and say hi!

I have just landed in San Diego and I will be at #NeurIPS2025 for the week. DM or send me an email if you want to chat about interesting papers and potential projects related to associative memory, energy-based models, new architectures, or other cool ideas.

The overlaid network illustrates a mathematical model, which represents the astrocyte as a network of processes that enables multi-synaptic communication and supports associative memory function.

Data credit: Leyka Nagendren, Cagla Eroglu.
Artist Credit: Annette Hui, IBM Research

The raw image was captured in October 2023 using an Olympus FV 3000 confocal microscope with a 60x objective lens and a z-step size of 0.5 μm across a 50–60 μm z-stack for high magnification and resolution.

A custom Imaris extension, 3D Sholl Analysis, was used to quantify the number of process intersections at 5 μm intervals from the cell soma, marked by the sphere, thereby visualizing the highly complex network of processes of the astrocyte.

The image summarizes the main message of our paper: astrocyte = network of processes that engage in information exchange and computation. The image shows a 3D reconstruction of an astrocyte from the visual cortex using Imaris Bitplane 9.9.

Key takeaways:
🔷 Astrocytes compute.
🔷 Dense Associative Memories can be built using astrocytes.
🔷 From the computational perspective astrocyte is a network of processes.
🔷 Memories can be stored, at least partially, in the biochemical machinery inside the astrocyte, as opposed to just synapses.

I am very excited about our new paper just published in PNAS.

www.pnas.org/doi/abs/10.1...

It was a pleasure to work on this idea together with @leokoz8.bsky.social and Jean-Jacques Slotine.

Big week for astrocyte research: 3 new Science papers link astrocytes to behavior. We're excited to add to the momentum with our new PNAS paper: a theory, grounded in biology, proposing astrocytes as key players in memory storage and recall. w/ JJ Slotine and @krotov.bsky.social
(1/6)

YouTube video by Nobel Prize John J. Hopfield, Nobel Prize in Physics 2024: Official interview

John Hopfield on pursuing interesting things: “Doesn’t matter what they are - interesting is the important one”. www.youtube.com/watch?v=iYgs...

Workshop on Associative Memory @ICLR 2025 New Frontiers in Associative Memories Workshop @ICLR 2025. Discuss the latest multidisciplinary developments in Associative Memory. Explore synergies between Associative Memories and LLMs.

More info here: nfam.vizhub.ai

I am heading to #ICLR2025 in Singapore. If you want to chat about associative memories, energy-based models, and related topics let’s connect! The highlight for me this year is the New Frontiers in Associative Memories workshop on Sunday April 27. Here is the schedule ⬇️

Convergence of efficient and predictive coding in multimodal sensory processing The existence of pathways connecting different sensory modalities in the brain challenges the traditional view of sensory systems as operating independently. However, the reasons and mechanisms underl...

New ms! www.biorxiv.org/content/10.1...
I developed a normative coding theory for feedback-modulated canonical networks, providing a unified view of (1) efficient & predictive coding, (2) computational & algorithmic principles, (3) unimodal & multimodal sensory processing.

Workshop on Associative Memory @ICLR 2025 New Frontiers in Associative Memories Workshop @ICLR 2025. Discuss the latest multidisciplinary developments in Associative Memory. Explore synergies between Associative Memories and LLMs.

Website: nfam.vizhub.ai

Submissions on Open Review: openreview.net/group?id=ICL...

Associative memory is a prominent emerging paradigm in the landscape of mainstream AI and I expect exciting developments in this area in the next few years. Please take a look at the call for papers and submit by the deadline: February 14. It will be interesting! 😀

Now that ICML papers are submitted and we are in the midst of discussions on whether scaling is enough or new architectural/algorithmic ideas are needed, what can be a better time to submit your best work to our workshop on New Frontiers in Associative Memory @iclr-conf.bsky.social?

I am very honored to return to my alma mater to give a distinguished lecture on AI for Science at Rice University's Ken Kennedy Institute.
events.rice.edu/event/spring...

I am excited to announce the call for papers for the New Frontiers in Associative Memories workshop at ICLR 2025. New architectures and algorithms, memory-augmented LLMs, energy-based models, Hopfield nets, AM and diffusion, and many other topics.

Website: nfam.vizhub.ai

@iclr-conf.bsky.social

Wow, what a night! A heartfelt congratulations to my dear friend and collaborator John Hopfield and all the 2024 Laureates. #NobelPrize

What a wonderful day of Nobel lectures and inspiring conversations at the beautiful Aula Magna, Stockholm University! #NobelPrize

Physics is a point of view. Wise words from John Hopfield’s Nobel lecture. #NobelPrize

Please check out the post in the first quote and join us at the Scientific Methods for Understanding Deep Learning workshop at #NeurIPS2024 on December 15 to learn more.

We demonstrate empirically that spurious states exist in conventional DMs. Their existence is a distinct prediction of DenseAM theory, yet these states have been overlooked in the DM literature. Spurious states mark the onset of the memorization-generalization transition in DMs.

In our latest work, we leverage the correspondence between DenseAMs and Diffusion Models (DMs) to make a theoretical prediction: a similar phenomenon must occur during the memorization-to-generalization transition in DMs.

DenseAM theory predicts a distinct phenomenon when the amount of data surpasses the critical memory capacity: spurious states emerge. Spurious states are local minima of the energy function that fail to store each pattern in a unique basin of attraction (two or more patterns sharing the same basin).