Neural networks and fuzzy systems

Oscillator associative memories for high-capacity, compositional inference

Gabriel Peyré - The Expressive Power of Large Language Models

Social NeuroAI of World Modeling: Embodied Dynamics, Collective Intelligence and Relational...

Talk by Phillip Isola

Journée du Deep Learning pour la Science – Matinée du 8 juin 2026

Deep Learning Day for Science – Morning of June 8, 2026

Journée du Deep Learning pour la Science – Après-midi du 8 juin 2026

Deep Learning Day for Science – Afternoon of June 8, 2026

How to compress neural networks | Vladimír Boža

ϕ−DeepONet: A Discontinuity Capturing Neural Operator || May 29, 2026

Generative AI L30: Quantization

Neural Emulator Superiority: A lightweight introduction

[ИАД, весна 2026] Математические методы анализа текстов. Лекция 3: Transformer

[IAD, Spring 2026] Mathematical Methods for Text Analysis. Lecture 3: Transformer

Les robots IA n'ont jamais paru aussi humains ! (Mise à jour 2026)

AI robots have never seemed so human! (2026 Update)

Generative AI L15: Professor forcing, Issues with RNNs, their solutions, intro to LSTM

Bethany Lusch - Scalable graph-based surrogate models for unstructured meshes - IPAM at UCLA

AI Robots Got Shockingly Human This Year (2026 Update)

Generative AI L14: detailed derivation of BPTT of RNNs, truncated BPTT, teacher forcing

[ИАД, весна 2026] Математические методы анализа текстов. Лекция 8: Parallelism, MoE

[IAD, Spring 2026] Mathematical Methods for Text Analysis. Lecture 8: Parallelism, MoE

Stochastic Port-Hamiltonian Neural Networks || May 15, 2026

Generative AI L12: Neural network for next-word-prediction based on 3 context words, intro to RNN

AI+Science: AI for Earth

Hanlin Zhu: Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

MLP Doubt Clearing Session

MLP End Term Revision Session 2

Des robots intelligents rejoignent la police armée du SWAT et choquent le public du monde entier

Intelligent robots join the SWAT armed police and shock the public worldwide

Vardan Papyan

Joaquín Fontbona

Itay Safran - Towards a Depth Hierarchy for Computing the Maximum in ReLU Networks (Heb)

How is Deepseek V4 so cheap (A deep dive into Sparse Attention)

Decoding Neural Networks with Sparse Autoencoders | David Chanin, FAI CDT

MLP Live session

MLP OPPE Revision Session

MLP Live session

Spotlight - Neural Networks Reveal a Cognitive Continuum Toward Human Abstraction

Claude Opus 4.7 Just Dropped... Or Did It Really?

Transformers Visually Explained

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 4: Attention Alternatives

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 3: Architectures

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 2: PyTorch (einops)

MLP Live session Week 10

The Intuitive Transformer