Activity
-
We are starting the #RSS2024 tutorial on Supervised Policy Learning in approximately 30 minutes! The zoom link is here if you are joining remotely:…
We are starting the #RSS2024 tutorial on Supervised Policy Learning in approximately 30 minutes! The zoom link is here if you are joining remotely:…
Liked by Yann LeCun
-
Nice to see HISS win a best paper award at the Next Gen Sequence Models workshop #ICML2024! HISS is a SSM-based model that is focused on modeling…
Nice to see HISS win a best paper award at the Next Gen Sequence Models workshop #ICML2024! HISS is a SSM-based model that is focused on modeling…
Liked by Yann LeCun
-
OctoAI is proud to introduce the full Llama 3.1 herd to our customers, featuring 8B, 70B, and 405B models! These cutting-edge models unlock new…
OctoAI is proud to introduce the full Llama 3.1 herd to our customers, featuring 8B, 70B, and 405B models! These cutting-edge models unlock new…
Liked by Yann LeCun
Experience & Education
Publications
-
Feature Learning and Deep Architectures: New Directions for Music Informatics
Journal of Intelligent Information Systems / Springer
-
Moving Beyond Feature Design: Deep Architectures and Automatic Feature Learning in Music Informatics
Proc. of the International Society of Music Information Retrieval (ISMIR) 2012
Projects
-
LAGR
-
LAGR was a DARPA competition in autonomous vision-based off-road robot navigation. Nine labs competed in many races through complex off-road terrain over the course of 3 years. In the first year, our team achieved the competition's 3-year goal of improving the baseline run-time by a factor of 2, forcing the government to up the goal to a factor of 3.
Using visual input for navigation is essential in unstructured outdoor environments, which can cause simpler sensors such as GPS…LAGR was a DARPA competition in autonomous vision-based off-road robot navigation. Nine labs competed in many races through complex off-road terrain over the course of 3 years. In the first year, our team achieved the competition's 3-year goal of improving the baseline run-time by a factor of 2, forcing the government to up the goal to a factor of 3.
Using visual input for navigation is essential in unstructured outdoor environments, which can cause simpler sensors such as GPS, odometry, and laser scanners to drift severely or become unusably noisy. As an alternative to such sensors, I contributed a novel, fast form of visual odometry. Our efficient “hybrid visual odometry” method used 5% of the CPU time, in contrast to full VO methods which require an entire CPU. Despite this, it maintained comparable accuracy to full VO over diverse terrain types. This makes it particularly suitable for consumer robots, extraterrestrial rovers, and other platforms with limited computing power.
This contribution was described in the ICRA 2009 paper Efficient Off-Road Localization Using Visually Corrected Odometry, and contributed to our JFR 2009 paper, A Multi-Range Architecture for Collision-Free Off-Road Robot Navigation.Other creatorsSee project -
DjVu
-
DjVu (pronounced "déjà vu") is a digital document format with advanced compression technology.
I initiated and directed the project.Other creatorsSee project -
Check Recognition with Deep Learning
-
The first practical system for reading the amount on bank checks.
It was deployed by NCR first in ATM machines in 1995, then in high-speed check reading machines in 1996. At some point in the late 90's these systems read an estimated 10 to 20% of all the checks in the US.
It used a convolutional neural net, combined with a so-called graph-transformer network, a form of non conditional random field in which the solution space can be represented by a treillis.
Other creatorsSee project
More activity by Yann
-
I’ve been leading a secret project for months … and the word is finally out! 🛠️ I'm proud to announce the Llama 3 Groq Tool Use 8B and 70B models…
I’ve been leading a secret project for months … and the word is finally out! 🛠️ I'm proud to announce the Llama 3 Groq Tool Use 8B and 70B models…
Liked by Yann LeCun
-
The Global AI Frontier Lab was officially launched on May 30, 2024, marking a significant collaboration between Korea and NYU. Spearheaded by AI…
The Global AI Frontier Lab was officially launched on May 30, 2024, marking a significant collaboration between Korea and NYU. Spearheaded by AI…
Liked by Yann LeCun
-
Create, summarize, write code and so much more — Meta AI just got even better at helping your work day run smoother and…
Create, summarize, write code and so much more — Meta AI just got even better at helping your work day run smoother and…
Liked by Yann LeCun
-
We’re excited to bring customers AI at Meta’s most advanced models today—its Llama 3.1 collection—to Amazon Bedrock and Amazon…
We’re excited to bring customers AI at Meta’s most advanced models today—its Llama 3.1 collection—to Amazon Bedrock and Amazon…
Liked by Yann LeCun
-
The largest openly available foundation model to date, #Llama 3.1 405B by Meta is now available on Groq, alongside the other 3.1 models released…
The largest openly available foundation model to date, #Llama 3.1 405B by Meta is now available on Groq, alongside the other 3.1 models released…
Liked by Yann LeCun
-
Llama 3.1 is here - this time with 405B! 🚀 We at Meta are doubling down on our commitment to open and accessible AI - innovating not just at the…
Llama 3.1 is here - this time with 405B! 🚀 We at Meta are doubling down on our commitment to open and accessible AI - innovating not just at the…
Liked by Yann LeCun
-
We trained a model and we wrote a paper about it. Have fun y’all! https://lnkd.in/g-8fqmVh https://lnkd.in/gahr7Cfn
We trained a model and we wrote a paper about it. Have fun y’all! https://lnkd.in/g-8fqmVh https://lnkd.in/gahr7Cfn
Liked by Yann LeCun
-
We’re excited to announce the just-released Llama 3.1 models from Meta are running on Groq! Our 300K+ developer community can access via GroqCloud…
We’re excited to announce the just-released Llama 3.1 models from Meta are running on Groq! Our 300K+ developer community can access via GroqCloud…
Liked by Yann LeCun
-
Happy to announce that in September 2025, I will open my research laboratory at NYU Courant Institute of Mathematical Sciences 🏢🔬. As an assistant…
Happy to announce that in September 2025, I will open my research laboratory at NYU Courant Institute of Mathematical Sciences 🏢🔬. As an assistant…
Liked by Yann LeCun
-
It has been a crazy day and I wanted to share a click down on the various Llama repos we have so it’s clear where to go to get what. In short…
It has been a crazy day and I wanted to share a click down on the various Llama repos we have so it’s clear where to go to get what. In short…
Liked by Yann LeCun
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Yann LeCun
2 others named Yann LeCun are on LinkedIn
See others named Yann LeCun