YL
Yann LeCun
cs.LGcs.CVcs.AIstat.MLcs.CLcs.ROcs.NEArtificial Intelligencecs.DCcs.SD
On Valency
published · living versionsW_yjkvbrxa·v1 · currentpublished
Spectral Networks and Locally Connected Networks on Graphs
with Joan Bruna, Wojciech Zaremba, Arthur Szlam
1 version
Preprints & journals
239 papers in the corpus · 1995–2026HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning2608.00491v2 · Ruichen Xu, Jingxiang Qu, Wenhan Gao et al.2026 · 0 citationsarXiv
TabPFN-3.5: Technical Report2609.17895v2 · Benjamin Jager, Nick Erickson, L'eo Grinsztajn et al.2026 · 0 citationsarXiv
To Compress or Not to Compress-Self-Supervised Learning and Information Theory: A Review.38539763 · Shwartz Ziv, Ravid, LeCun, Yann2026 · 84 citationsEntropy (Basel, Switzerland). 2024;26(3)
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning.42754575 · Moutakanni, Théo, Bojanowski, Piotr, Chassagnon, Guillaume et al.2026 · 4 citationsNature communications. 2026;17(1)
Advancing Open and Reproducible Relational Learning: RelArena-$\alpha$, TabPFN-Rel and RPI2608.16319v2 · Adrian Hayler, Klemens Floge, Alan Arazi et al.2026 · 0 citationsarXiv
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?2512.24497v4 · Basile Terver, Tsung-Yen Yang, Jean Ponce et al.2025 · 0 citationsarXiv
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics2608.27395v1 · Lukas Kuhn, Lucas Maes, Giuseppe Serra et al.2026 · 0 citationsarXiv
LpWM: A Case for Sparse Representations in World Models2608.22764v1 · Yilun Kuang, Yash Dagade, Quentin Le Lidec et al.2026 · 0 citationsarXiv
Temporal Straightening for Latent Planning2603.12231v3 · Ying Wang, Oumayma Bounou, Gaoyue Zhou et al.2026 · 0 citationsarXiv
Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability2608.02208v1 · Gil Sasson, Zachary Levine, Smadar Shilo et al.2026 · 0 citationsarXiv
Music-JEPA: Learning a World Model of Sound from Action2607.22000v1 · Ziyu Wang, Kun Fang, Yann LeCun2026 · 0 citationsarXiv
Patch Policy: Efficient Embodied Control via Dense Visual Representations2607.18236v1 · Gaoyue Zhou, Zichen Jeff Cui, Ada Langford et al.2026 · 0 citationsarXiv
Separating Representation from Reconstruction Enables Scalable Text Encoders2607.04011v1 · Megi Dervishi, Mathurin Videau, Yann LeCun2026 · 0 citationsarXiv
Multi-modal AI for comprehensive breast cancer prognostication.42161927 · Witowski, Jan, Zeng, Ken G, Cappadona, Joseph et al.2026 · 6 citationsNature communications. 2026;17(1)
AdaJEPA: An Adaptive Latent World Model2606.32026v1 · Ying Wang, Oumayma Bounou, Yann LeCun et al.2026 · 0 citationsarXiv
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors2606.23444v2 · Pratyaksh Rao, Wancong Zhang, Randall Balestriero et al.2026 · 0 citationsarXiv
S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning2606.19398v1 · Georgios Ioannides, Adrian Kieback, Judah Goldfeder et al.2026 · 0 citationsarXiv
Hierarchical Planning with Latent World Models2604.03208v2 · Wancong Zhang, Basile Terver, Artem Zholus et al.2026 · 1 citationarXiv
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences2606.15956v1 · Ninad Daithankar, Alexi Gladstone, Yann LeCun et al.2026 · 0 citationsarXiv
Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks2606.08775v1 · Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun et al.2026 · 0 citationsarXiv
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels2603.19312v3 · Lucas Maes, Quentin Le Lidec, Damien Scieur et al.2026 · 0 citationsarXiv
Universal halting times in optimization and machine learning1511.06444v3 · Levent Sagun, Thomas Trogdon, Yann LeCun2015 · 9 citationsQuart. Appl. Math. 76 (2018), 289-301
Learning Stable Group Invariant Representations with Convolutional Networks1301.3537v1 · Joan Bruna, Arthur Szlam, Yann LeCun2013 · 30 citationsarXiv
Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations2602.01456v2 · Yilun Kuang, Yash Dagade, Tim G. J. Rudner et al.2026 · 0 citationsarXiv
Causal-JEPA: Learning World Models through Object-Level Latent Masking2602.11389v2 · Heejeong Nam, Quentin Le Lidec, Lucas Maes et al.2026 · 5 citationsarXiv
TabPFN-3: Technical Report2605.13986v2 · L'eo Grinsztajn, Klemens Floge, Oscar Key et al.2026 · 3 citationsarXiv
When Does LeJEPA Learn a World Model?2605.26379v1 · David Klindt, Yann LeCun, Randall Balestriero2026 · 0 citationsarXiv
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement2605.14759v2 · Nian Liu, Nikita Kazeev, Stephen Gregory Dale et al.2026 · 0 citationsarXiv
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation2605.21800v1 · Lucas Maes, Quentin Le Lidec, Luiz Facury et al.2026 · 0 citationsarXiv
On Training in Imagination2605.06732v2 · Nadav Timor, Ravid Shwartz-Ziv, Micah Goldblum et al.2026 · 0 citationsarXiv
SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation2512.21204v2 · Mahi Luthra, Jiayi Shen, Maxime Poli et al.2025 · 0 citationsarXiv
A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures2602.03604v3 · Basile Terver, Randall Balestriero, Megi Dervishi et al.2026 · 0 citationsarXiv
World Models for Learning Dexterous Hand-Object Interactions from Human Videos2512.13644v2 · Raktim Gautam Goswami, Amir Bar, David Fan et al.2025 · 0 citationsarXiv
Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science2603.15381v1 · Emmanuel Dupoux, Yann LeCun, Jitendra Malik2026 · 1 citationarXiv
Representation Learning for Spatiotemporal Physical Systems2603.13227v1 · Helen Qu, Rudy Morel, Michael McCabe et al.2026 · 0 citationsarXiv
AI+HW 2035: Shaping the Next Decade2603.05225v1 · Deming Chen, Jason Cong, Azalia Mirhoseini et al.2026 · 0 citationsarXiv
The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks2603.05498v1 · Shangwen Sun, Alfredo Canziani, Yann LeCun et al.2026 · 0 citationsarXiv
AI Must Embrace Specialization via Superhuman Adaptable Intelligence2602.23643v1 · Judah Goldfeder, Philippe Wyder, Yann LeCun et al.2026 · 1 citationarXiv
Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA2602.22617v1 · Hai Huang, Yann LeCun, Randall Balestriero2026 · 0 citationsarXiv
stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation2602.08968v2 · Lucas Maes, Quentin Le Lidec, Dan Haramati et al.2026 · 0 citationsarXiv
Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization2602.14272v1 · Yilun Kuang, Yash Dagade, Deep Chakraborty et al.2026 · 0 citationsarXiv
Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin2510.06477v2 · Enrique Queipo-de-Llano, 'Alvaro Arroyo, Federico Barbero et al.2025 · 0 citationsarXiv
Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures2602.09040v1 · Georgios Ioannides, Adrian Kieback, Judah Goldfeder et al.2026 · 0 citationsarXiv
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language2512.10942v2 · Delong Chen, Mustafa Shukor, Theo Moutakanni et al.2025 · 1 citationarXiv
Parallel Stochastic Gradient-Based Planning for World Models2602.00475v1 · Michael Psenka, Michael Rabbat, Aditi Krishnapriyan et al.2026 · 0 citationsarXiv
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders2601.16208v1 · Shengbang Tong, Boyang Zheng, Ziteng Wang et al.2026 · 0 citationsarXiv
Learning Latent Action World Models In The Wild2601.05230v2 · Quentin Garrido, Tushar Nagarajan, Basile Terver et al.2026 · 0 citationsarXiv
Value-guided action planning with JEPA world models2601.00844v1 · Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec et al.2025 · 1 citationarXiv
OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation2505.20425v2 · Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun et al.2025 · 0 citationsarXiv
From Generated Human Videos to Physically Plausible Robot Trajectories2512.05094v2 · James Ni, Zekai Wang, Wei Lin et al.2025 · 0 citationsarXiv
Career total: 581 works. 239 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.