Yann LeCun

Courant Institute of Mathematical Sciences — United States

Computer Science · Physical Sciences

118h-index244.3kcitations481works10.72yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Neural Networks and Applications(75), Domain Adaptation and Few-Shot Learning(72), Advanced Image and Video Retrieval Techniques(62), Advanced Neural Network Applications(45), Generative Adversarial Networks and Image Synthesis(42)

Publications481 total

What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
ArXiv.org·2025Open Access
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
arXiv (Cornell University)·2025Open Access
World Models Can Leverage Human Videos for Dexterous Manipulation
arXiv (Cornell University)·2025Open Access
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
arXiv (Cornell University)·2025Open Access
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
arXiv (Cornell University)·2025Open Access
Cambrian-S: Towards Spatial Supersensing in Video
arXiv (Cornell University)·2025Open Access
Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
arXiv (Cornell University)·2025Open Access
Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
arXiv (Cornell University)·2025Open Access
LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
arXiv (Cornell University)·2025Open Access
Whole-Body Conditioned Egocentric Video Prediction
arXiv (Cornell University)·2025Open Access
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
arXiv (Cornell University)·2025Open Access
RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training
2025
Transformers without Normalization
2025· 64 cited
Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
2025
Navigation World Models
2025· 8 cited
OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
arXiv (Cornell University)·2025Open Access
Scaling Language-Free Visual Representation Learning
arXiv (Cornell University)·2025Open Access
Transformers without Normalization
arXiv (Cornell University)·2025Open Access
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
arXiv (Cornell University)·2025· 2 citedOpen Access
Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
arXiv (Cornell University)·2025· 1 citedOpen Access
page 1 of 25Next →

Frequent Co-authors

Léon Bottou(10), Yoshua Bengio(6), Joan Bruna(5), Sumit Chopra(4), Eduard Säckinger(4), Rob Fergus(4), J. S. Denker(3), L. D. Jackel(3), Raia Hadsell(3), Wojciech Zaremba(3), Koray Kavukcuoglu(3), Isabelle Guyon(3), Genevieve Orr(3), Jonathan Tompson(3), Christoph Bregler(3), Fu Jie Huang(3), Pierre Sermanet(3), Michaël Mathieu(3), Y-Lan Boureau(3), Jure Žbontar(3)