Want to see more on our recent work and how you can connect with Meta AI? You can see more on our ICLR 2023 page https://
ai.facebook.com/events/iclr-20
23/
… 6/6
@aiatmeta
-
Meta AI showcases recent work at ICLR 2023 conference
By
–
-
Ensemble, Knowledge Distillation and Self-Distillation Theory
By
–
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning. A theory to explain why ensemble and knowledge distillation work for Deep Learning. Paper https://
openreview.net/forum?id=Uuf2q
9TfXGA
… 4/6 -
Duality Between Contrastive and Non-Contrastive Self-Supervised Learning Methods
By
–
On the duality between contrastive and non-contrastive self-supervised learning This work shows how contrastive & non-contrastive self-supervised methods can be shown to be closely related + how implementation details impact performance. Paper https://
openreview.net/forum?id=kDEL9
1Dufpa
… 3/6 -
Maps Emergence in Blind Navigation Agents Memories
By
–
Emergence of Maps in the Memories of Blind Navigation Agents One of four #ICLR2023 Outstanding Papers. More on this work in Dhruv’s thread. 2/6
-
Meta AI Notable Papers at ICLR 2023 Conference
By
–
Notable papers to know about from Meta AI at #ICLR2023 this week and where you can learn more — even if you’re not attending. /6
-
Meta’s Efficient AI Development Ecosystems for Production
By
–
AI development ecosystems are increasingly complex and challenging to maintain. Companies like Meta need to develop highly efficient systems to build, serve and improve AI models for production uses. Here's how we make this work effective + efficient
-
Meta Announces AtScale AI Virtual Event for May 18th
By
–
Just announced! Join live us on May 18th for #AtScaleMetaAI, a one-day virtual event sharing a look at the next generation of AI infrastructure and innovations powering Meta’s products and services today and in the future. RSVP
-
SSL Cookbook: Collaborative Research for Democratizing Self-Supervised Learning
By
–
The SSL cookbook features insights from more than a dozen authors from @NYUTandon
, @umiacs
, @UCDavis
, @UMontreal + Meta AI researchers, such as @ylecun We’re excited to share this with the community as part of our effort to lower barriers + democratize access to SSL research. -
SSL Cookbook: Practical Guide to Self-Supervised Learning
By
–
Self-supervised learning underpins today’s cutting-edge work across natural language, computer vision & more — but it’s an intricate art with high barriers to entry. Today we're releasing the SSL Cookbook, a practical guide for navigating SSL + contributing to this space
-
DINOv2: Meta’s Self-Supervised Vision Model Breakthrough
By
–
DINOv2 by Meta AI is the first method for training computer vision models that uses self-supervised learning to achieve results matching or exceeding industry standards. More details and a demo