vlgiitr (@vlgiitr) 's Twitter Profile
vlgiitr

@vlgiitr

Deep Learning and AI discussion group at IIT Roorkee

ID: 1192093915022647297

linkhttps://vlgiitr.github.io/ calendar_today06-11-2019 14:58:40

34 Tweet

164 Followers

231 Following

vlgiitr (@vlgiitr) 's Twitter Profile Photo

The fifth article in our ELI5 series is on Metric Learning by Keerat Kaur Guliani medium.com/vlgiitr/metric… Hope you enjoy the animations and explanation! #DeepLearning #MachineLearning #Mathematics

vlgiitr (@vlgiitr) 's Twitter Profile Photo

Join us for a discussion on Sunday(21/05/23), where we'll be discussing an introduction to generative AI Date:21st May Time:6:30pm Venue:ACM Room 109,SAC Topic: An Introduction to Generative AI No prerequisites required. See you All!!

Join us for a discussion on Sunday(21/05/23), where we'll be discussing an introduction to generative AI
Date:21st May
Time:6:30pm
Venue:ACM Room 109,SAC
Topic: An Introduction to Generative AI
No prerequisites required.
See you All!!
vlgiitr (@vlgiitr) 's Twitter Profile Photo

We are releasing Open Projects in various AI domains. Submission Deadline: 22 June For the link to the google form and for more information regarding each project, visit our website or check the link in instagram bio. instagram.com/p/CseSBkOPhM3/…

We are releasing Open Projects in various AI domains.
Submission Deadline: 22 June
For the link to the google form and for more information regarding each project, visit our website or check the link in instagram bio.
instagram.com/p/CseSBkOPhM3/…
vlgiitr (@vlgiitr) 's Twitter Profile Photo

Join us for a discussion, where we'll be discussing an introduction to reinforcement learning. Date: 24th May Time: 6:30pm Venue: ACM Room 109,SAC Topic: Reinforcement Learning No prerequisites required.

Join us for a discussion, where we'll be discussing an introduction to reinforcement learning.

Date: 24th May
Time: 6:30pm
Venue: ACM Room 109,SAC
Topic: Reinforcement Learning

No prerequisites required.
vlgiitr (@vlgiitr) 's Twitter Profile Photo

Join us as we explore the advanced ML/DL techniques and the mathematical background behind Recommender Systems. Date: 31st May Time: 6:30 pm Venue: ACM Room 109, SAC Topic: Recommender Systems No prerequisites required. See you all! instagram.com/p/Cs4SHnihqrA/…

Aayan Yadav (@ionydv) 's Twitter Profile Photo

📢 Introducing our #ECCV2024 work, COCO-ReM (COCO Refined Masks), for more reliable benchmarking of object detectors, crucial for the future of object detection research. Paper: arxiv.org/abs/2403.18819 Code: arxiv.org/abs/2403.18819 Website: cocorem.xyz

📢 Introducing our #ECCV2024 work, COCO-ReM (COCO Refined Masks), for more reliable benchmarking of object detectors, crucial for the future of object detection research.

Paper: arxiv.org/abs/2403.18819
Code: arxiv.org/abs/2403.18819
Website: cocorem.xyz
Paras Chopra (@paraschopra) 's Twitter Profile Photo

LLM post-training requires a reward model for preference alignment. But is it necessary? In our new preprint, we show that the language model is itself a preference classifier & reward model isn't needed. We can self-improve a model by using its own feedback!

LLM post-training requires a reward model for preference alignment.

But is it necessary?  

In our new preprint, we show that the language model is itself a preference classifier & reward model isn't needed.

We can self-improve a model by using its own feedback!
Ofir Press (@ofirpress) 's Twitter Profile Photo

New ICLR 2025 blogpost shows that a vision transformer with 2D ALiBi achieves the best performance extrapolating to larger image sizes on Imagenet100. Cool! iclr-blogposts.github.io/2025/blog/posi…

New ICLR 2025 blogpost shows that a vision transformer with 2D ALiBi achieves the best performance extrapolating to larger image sizes on Imagenet100. Cool!

iclr-blogposts.github.io/2025/blog/posi…
Paras Chopra (@paraschopra) 's Twitter Profile Photo

Excited to announce that my paper has been accepted in ACL main conference! The first one from Lossfunk - many more to come! 🧵 on the paper

Excited to announce that my paper has been accepted in ACL main conference!

The first one from <a href="/lossfunk/">Lossfunk</a> - many more to come!

🧵 on the paper