---
title: "Yann Lecun — all works — Elamur Research"
description: "All 54 works of Yann Lecun in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/yann-lecun/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yann-lecun/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Yann Lecun](https://md.research.elamur.ai/free/en/authors/yann-lecun/) / all works

# Yann Lecun — all works

54 works · [← Yann Lecun](https://md.research.elamur.ai/free/en/authors/yann-lecun/)

1. [**Character-level Convolutional Networks for Text Classification arXiv:1509.01626**Xiang Zhang, Junbo Zhao, Yann LeCun*2015 · 4,827 citations*](https://md.research.elamur.ai/free/en/papers/zhang-2015-character-level-convolutional-networks-text/)
2. **[Spectral Networks and Locally Connected Networks on Graphs ↗](https://arxiv.org/abs/1312.6203) arXiv (Cornell University) · no summary yet**Joan Bruna et al.*2013 · 2,651 citations*
3. **[What is the best multi-stage architecture for object recognition? ↗](https://doi.org/10.1109/iccv.2009.5459469) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Kevin Jarrett et al.*2009 · 2,157 citations*
4. **[Convolutional networks and applications in vision ↗](https://doi.org/10.1109/iscas.2010.5537907) no summary yet**Yann LeCun, Koray Kavukcuoglu, Clément Farabet*2010 · 2,150 citations*
5. **[OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks ↗](https://arxiv.org/abs/1312.6229) arXiv:1312.6229 · no summary yet**Pierre Sermanet et al.*2013 · 1,423 citations*
6. **[Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation ↗](https://arxiv.org/abs/1404.0736) arXiv (Cornell University) · no summary yet**Emily Denton et al.*2014 · 1,388 citations*
7. **[Efficient object localization using Convolutional Networks ↗](https://doi.org/10.1109/cvpr.2015.7298664) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jonathan Tompson et al.*2015 · 1,361 citations*
8. **[Very Deep Convolutional Networks for Text Classification](https://md.research.elamur.ai/free/en/papers/conneau-2017-very-deep-convolutional-networks-text/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Alexis Conneau, Holger Schwenk, Loïc Barrault, et al.*2017 · 1,094 citations*
9. **[MDETR - Modulated Detection for End-to-End Multi-Modal Understanding ↗](https://doi.org/10.1109/iccv48922.2021.00180) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Aishwarya Kamath et al.*2021 · 819 citations*
10. **[Computing the stereo matching cost with a convolutional neural network ↗](https://doi.org/10.1109/cvpr.2015.7298767) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jure Žbontar, Yann LeCun*2015 · 812 citations*
11. **[Pedestrian Detection with Unsupervised Multi-stage Feature Learning ↗](https://doi.org/10.1109/cvpr.2013.465) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Pierre Sermanet et al.*2013 · 759 citations*
12. **[Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture ↗](https://arxiv.org/abs/2301.08243) arXiv:2301.08243 · no summary yet**Mahmoud Assran et al.*2023 · 492 citations*
13. **[Learning Convolutional Feature Hierarchies for Visual Recognition ↗](https://openalex.org/W2169488311) no summary yet**Koray Kavukcuoglu et al.*2010 · 487 citations*
14. [**Augmented Language Models: a Survey arXiv:2302.07842**Grégoire Mialon, Roberto Dessì, Maria Lomeli, et al.*2023 · 369 citations*](https://md.research.elamur.ai/free/en/papers/mialon-2023-augmented-language-models-survey/)
15. **[Convolutional Neural Networks Applied to House Numbers Digit Classification ↗](https://arxiv.org/abs/1204.3968) arXiv (Cornell University) · no summary yet**Pierre Sermanet, Soumith Chintala, Yann LeCun*2012 · 337 citations*
16. **[Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://md.research.elamur.ai/free/en/papers/tong-2024-eyes-wide-shut-exploring-visual/) [IEEE Computer Society Conference on Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/)**Shengbang Tong, Zhuang Liu, Yuexiang Zhai, et al.*2024 · 321 citations*
17. **[Learning long‐range vision for autonomous off‐road driving ↗](https://doi.org/10.1002/rob.20276) Journal of Field Robotics · no summary yet**Raia T. Hadsell et al.*2009 · 320 citations*
18. **[Learning invariant features through topographic filter maps ↗](https://doi.org/10.1109/cvpr.2009.5206545) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Koray Kavukcuoglu et al.*2009 · 281 citations*
19. **[Fast Convolutional Nets With fbfft: A GPU Performance Evaluation ↗](https://arxiv.org/abs/1412.7580) arXiv (Cornell University) · no summary yet**Nicolas Vasilache et al.*2014 · 271 citations*
20. **[Very Deep Convolutional Networks for Natural Language Processing. ↗](https://128.84.21.199/abs/1606.01781) arXiv (Cornell University) · no summary yet**Alexis Conneau et al.*2016 · 263 citations*
21. **[G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://md.research.elamur.ai/free/en/papers/he-2024-g-retriever-retrieval-augmented-generation/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Xiaoxin He, Yijun Tian, Yifei Sun, et al.*2024 · 236 citations*
22. [**GAIA: a benchmark for General AI Assistants arXiv:2311.12983**Gregoire Mialon, Clementine Fourrier, Craig Swift, et al.*2023 · 232 citations*](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/)
23. **[Tracking the World State with Recurrent Entity Networks ↗](https://arxiv.org/abs/1612.03969) arXiv:1612.03969 · ICLR 2017 · no summary yet**Mikael Henaff et al.*2016 · 228 citations*
24. **[Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition ↗](https://arxiv.org/abs/1010.3467) arXiv (Cornell University) · no summary yet**Koray Kavukcuoglu, Marc’Aurelio Ranzato, Yann LeCun*2010 · 190 citations*
25. **[Transformers without Normalization ↗](https://doi.org/10.1109/cvpr52734.2025.01388) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jiachen Zhu et al.*2025 · 179 citations*
26. **[Large-Scale FPGA-Based Convolutional Networks ↗](https://doi.org/10.1017/cbo9781139042918.020) Cambridge University Press eBooks · no summary yet**Clément Farabet et al.*2011 · 128 citations*
27. **[Unsupervised Learning Of Sparse Features For Scalable Audio Classification. ↗](https://doi.org/10.5281/zenodo.1416085) no summary yet**Mikael Henaff et al.*2011 · 111 citations*
28. **[A Mathematical Motivation for Complex-Valued Convolutional Networks ↗](https://doi.org/10.1162/neco_a_00824) Neural Computation · no summary yet**Mark Tygert et al.*2016 · 87 citations*
29. **[Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning ↗](https://arxiv.org/abs/2305.19523) arXiv:2305.19523 · no summary yet**Xiaoxin He et al.*2023 · 75 citations*
30. **[Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning ↗](https://doi.org/10.52202/079017-3522) neural information processing systems · no summary yet**Yuexiang Zhai et al.*2024 · 65 citations*
31. **[Layer by Layer: Uncovering Hidden Representations in Language Models ↗](https://arxiv.org/abs/2502.02013) arXiv:2502.02013 · no summary yet**Oscar Skean et al.*2025 · 64 citations*
32. **[Navigation World Models ↗](https://doi.org/10.1109/cvpr52734.2025.01472) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Amir Bar et al.*2025 · 61 citations*
33. **[Adversarially Regularized Autoencoders for Generating Discrete Structures. ↗](https://arxiv.org/abs/1706.04223) arXiv (Cornell University) · no summary yet**Junbo Zhao et al.*2017 · 52 citations*
34. **[MetaMorph: Multimodal Understanding and Generation via Instruction Tuning ↗](https://doi.org/10.1109/iccv51701.2025.01579) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Shengbang Tong et al.*2025 · 47 citations*
35. **[GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations ↗](https://arxiv.org/abs/1806.05662) arXiv (Cornell University) · no summary yet**Zhilin Yang et al.*2018 · 34 citations*
36. **[Convolutional Matching Pursuit and Dictionary Training ↗](https://arxiv.org/abs/1010.0422) arXiv (Cornell University) · no summary yet**Arthur D. Szlam, Koray Kavukcuoglu, Yann LeCun*2010 · 27 citations*
37. **[EBLearn: Open-Source Energy-Based Learning in C++ ↗](https://doi.org/10.1109/ictai.2009.28) Proceedings - International Conference on Tools with Artificial Intelligence, TAI · no summary yet**Pierre Serman, Koray Kavukcuoglu, Yann LeCun*2009 · 27 citations*
38. **[GLoMo: Unsupervised Learning of Transferable Relational Graphs ↗](https://openalex.org/W2902164678) neural information processing systems · no summary yet**Zhilin Yang et al.*2018 · 21 citations*
39. **[A multi-range vision strategy for autonomous offroad navigation ↗](https://openalex.org/W178742210) Robotics and Applications · no summary yet**Raia T. Hadsell et al.*2007 · 13 citations*
40. **[Cambrian-S: Towards Spatial Supersensing in Video ↗](https://arxiv.org/abs/2511.04670) arXiv (Cornell University) · no summary yet**Shusheng Yang et al.*2025 · 11 citations*
41. **[Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders ↗](https://arxiv.org/abs/2601.16208) arXiv (Cornell University) · no summary yet**Shengbang Tong et al.*2026 · 9 citations*
42. **[Whole-Body Conditioned Egocentric Video Prediction ↗](https://doi.org/10.52202/085713-5482) neural information processing systems · no summary yet**Yutong Bai et al.*2025 · 8 citations*
43. **[Beyond Language Modeling: An Exploration of Multimodal Pretraining ↗](https://arxiv.org/abs/2603.03276) arXiv (Cornell University) · no summary yet**Shengbang Tong et al.*2026 · 6 citations*
44. **[Learning with Reflective Likelihoods ↗](https://openalex.org/W2909379646) no summary yet**Adji Bousso Dieng et al.*2018 · 6 citations*
45. **[Joint Embedding Predictive Architectures Focus on Slow Features ↗](https://arxiv.org/abs/2211.10831) arXiv (Cornell University) · no summary yet**Vlad Sobal et al.*2022 · 5 citations*
46. **[Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models ↗](https://arxiv.org/abs/2502.14819) arXiv (Cornell University) · no summary yet**Vlad Sobal et al.*2025 · 3 citations*
47. **[EgoPet: Egomotion and Interaction Data from an Animal’s Perspective ↗](https://doi.org/10.1007/978-3-031-72913-3_21) Lecture notes in computer science · no summary yet**Amir Bar et al.*2024 · 3 citations*
48. **[A theoretical argument for complex-valued convolutional networks ↗](http://dblp.uni-trier.de/db/journals/corr/corr1503.html#BrunaCLPST15) arXiv (Cornell University) · no summary yet**Joan Bruna et al.*2015 · 3 citations*
49. **[Separating the World and Ego Models for Self-Driving ↗](https://arxiv.org/abs/2204.07184) arXiv (Cornell University) · no summary yet**Vlad Sobal et al.*2022 · 2 citations*
50. **[Learning feature hierarchies for object recognition ↗](https://openalex.org/W2301105015) no summary yet**Yann LeCun, Koray Kavukcuoglu*2010 · 2 citations*
51. **[AI+HW 2035: Shaping the Next Decade ↗](https://arxiv.org/abs/2603.05225) arXiv (Cornell University) · no summary yet**Deming Chen et al.*2026 · 1 citation*
52. **[From Generated Human Videos to Physically Plausible Robot Trajectories ↗](https://arxiv.org/abs/2512.05094) arXiv (Cornell University) · no summary yet**Ni, James et al.*2025 · 1 citation*
53. **[X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs ↗](https://arxiv.org/abs/2407.18134) arXiv (Cornell University) · no summary yet**Vlad Sobal et al.*2024*
54. **[Stochastic positional embeddings improve masked image modeling ↗](https://arxiv.org/abs/2308.00566) arXiv (Cornell University) · no summary yet**Amir Bar et al.*2023*