Yann LeCun

SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation ACL 2026 RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training CVPR 2025 Transformers without Normalization CVPR 2025 Navigation World Models CVPR 2025 Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning ICLR 2025 URLOST: Unsupervised Representation Learning without Stationarity or Topology ICLR 2025 DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning ICML 2025 Layer by Layer: Uncovering Hidden Representations in Language Models ICML 2025 Forgotten Polygons: Multimodal Large Language Models are Shape-Blind ACL 2025 Scaling Language-Free Visual Representation Learning ICCV 2025 MetaMorph: Multimodal Understanding and Generation via Instruction Tuning ICCV 2025 Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization AISTATS 2025 Training compute-optimal transformer encoder models EMNLP 2025 Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation CVPR 2025 LiveBench: A Challenging, Contamination-Limited LLM Benchmark ICLR 2025 Hierarchical World Models as Visual Whole-Body Humanoid Controllers ICLR 2025 $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs ICLR 2025 PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos ICLR 2025 Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs CVPR 2024 Stochastic positional embeddings improve masked image modeling ICML 2024 How Learning by Reconstruction Produces Uninformative Features For Perception ICML 2024 Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning ICLR 2024 The Entropy Enigma: Success and Failure of Entropy Minimization ICML 2024 G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering NIPS 2024 EgoPet: Egomotion and Interaction Data from an Animal's Perspective ECCV 2024 Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs NIPS 2024 Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning NIPS 2024 GAIA: a benchmark for General AI Assistants ICLR 2024 On the duality between contrastive and non-contrastive self-supervised learning ICLR 2023 Self-Supervised Learning with Lie Symmetries for Partial Differential Equations NIPS 2023 An Information Theory Perspective on Variance-Invariance-Covariance Regularization NIPS 2023 Reverse Engineering Self-Supervised Learning NIPS 2023 Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture CVPR 2023 Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need ICCV 2023 Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform ICLR 2023 The SSL Interplay: Augmentations, Inductive Bias, and Generalization ICML 2023 RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank ICML 2023 Self-supervised learning of Split Invariant Equivariant representations ICML 2023 A Generalization of ViT/MLP-Mixer to Graphs ICML 2023 Compact and Optimal Deep Learning With Recurrent Parameter Generators WACV 2023 Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods NIPS 2022 Decoupled Contrastive Learning ECCV 2022 VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning ICLR 2022 Understanding Dimensional Collapse in Contrastive Self-supervised Learning ICLR 2022 projUNN: efficient method for training deep networks with unitary matrices NIPS 2022 A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training NIPS 2022 The Effects of Regularization and Data Augmentation are Class Dependent NIPS 2022 Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone NIPS 2022 Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors NIPS 2022 VICRegL: Self-Supervised Learning of Local Visual Features NIPS 2022 Barlow Twins: Self-Supervised Learning via Redundancy Reduction ICML 2021 Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors NAACL 2021 MDETR - Modulated Detection for End-to-End Multi-Modal Understanding ICCV 2021 Implicit Rank-Minimizing Autoencoder NIPS 2020 Unsupervised Image Matching and Object Discovery as Optimization CVPR 2019 The role of over-parametrization in generalization of neural networks ICLR 2019 Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic ICLR 2019 A Closer Look at Spatiotemporal Convolutions for Action Recognition CVPR 2018 Comparing Dynamics: Deep Neural Networks versus Glassy Systems ICML 2018 Adversarially Regularized Autoencoders ICML 2018 GLoMo: Unsupervised Learning of Transferable Relational Graphs NIPS 2018 Predicting Future Instance Segmentation by Forecasting Convolutional Features ECCV 2018 Very Deep Convolutional Networks for Text Classification EACL 2017 Predicting Deeper Into the Future of Semantic Segmentation ICCV 2017 Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs ICML 2017 Disentangling factors of variation in deep representation using adversarial training NIPS 2016 Recurrent Orthogonal Networks and Long-Memory Tasks ICML 2016 Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches JMLR 2016 Binary embeddings with structured hashed projections ICML 2016 Deep learning with Elastic Averaging SGD NIPS 2015 Learning to Linearize Under Uncertainty NIPS 2015 Unsupervised Learning of Spatiotemporally Coherent Metrics ICCV 2015 Computing the Stereo Matching Cost With a Convolutional Neural Network CVPR 2015 Efficient Object Localization Using Convolutional Networks CVPR 2015 Character-level Convolutional Networks for Text Classification NIPS 2015 The Loss Surfaces of Multilayer Networks AISTATS 2015 Open Problem: The landscape of the loss surfaces of multilayer networks COLT 2015 Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation NIPS 2014 Signal recovery from Pooling Representations ICML 2014 Convolutional Nets and Watershed Cuts for Real-Time Semantic Labeling of RGBD Videos JMLR 2014 Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation NIPS 2014 No more pesky learning rates ICML 2013 Pedestrian Detection with Unsupervised Multi-stage Feature Learning CVPR 2013 Deep Learning Made Easier by Linear Transformations in Perceptrons AISTATS 2012 The Need for Open Source Software in Machine Learning JMLR 2007