Vision and Language Group, part of the IIT Roorkee ACM Student Chapter.
28/10/2022
Hello Everyone!
We will be holding a fundamental discussion on Saturday (29/10/22) where we shall discuss Vision and Language Models.
Date: 29th October
Time: 6:30 PM
Venue: ACM Room 109, SAC
Topic: Vision and Language Models
No prerequisites required
Resources:
https://theaisummer.com/vision-language-models/
https://lilianweng.github.io/posts/2022-06-09-vlm/
https://www.youtube.com/watch?v=jReaoJWdO78
19/10/2022
Hello Everyone!
We will be holding a project discussion on Wednesday (19/10/22) where we shall discuss Whisper - The Automatic Speech Recognition System developed by OpenAI
Date: 19th October
Time: 6:30 PM
Venue: ACM Room 109, SAC
Topic: OpenAI Whisper
No prerequisites required.
Resources:
https://openai.com/blog/whisper/
11/10/2022
Hello Everyone!
We will be holding a project discussion on Wednesday (12/10/22) where we shall discuss the basics of Neural Radiance Fields
Date: 12th October
Time: 6:30 PM
Venue: ACM Room 109, SAC
Topic: Introduction to NeRF
Prerequisites:
Basic knowledge of Neural Networks
Resources:
https://arxiv.org/abs/2003.08934
https://nerfmm.active.vision/
https://lingjie0206.github.io/papers/NeuS/
https://arxiv.org/abs/2210.01548
https://youtu.be/CRlN-cYFxTk
07/10/2022
Hello Everyone!
We will be holding a fundamental discussion on Saturday (8/10/22) where we shall discuss the basics of Generative Modeling
Date: 8th October
Time: 6:30 PM
Venue: ACM Room 109, SAC
Topic: Generative Modelling
Prerequisites:
None
To view a demo, check out:
http://imaginaire.cc/gaugan2/
03/10/2022
Hello Everyone!
We would be holding our next discussion on Wednesday (5/10/2022) where we shall discuss a paper based on Image Restoration
Date: 5th October 2022
Time: 6:30 PM
Venue: ACM Room 109, SAC
Topic: Image Restoration
Resources:
https://arxiv.org/abs/2111.09881
Prerequisites:
Basic knowledge of the working of Transformers.
Restormer: Efficient Transformer for High-Resolution Image Restoration Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural architectures, Transformers, have shown significant performance g...
01/10/2022
Hello Everyone!
We will be holding a fundamental discussion on Saturday (1/10/22) where we shall discuss the basics of Computer Vision
Date: 1st October
Time: 6:30 PM
Venue: ACM Room 109, SAC
Topic: Introduction to Computer Vision
Prerequisites:
Basic knowledge of neural networks
17/06/2022
Inspired by progress in large-scale language modeling, we apply a similar approach toward building a single generalist agent beyond the realm of text outputs. Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm, and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens.
Know more about Gato by visiting DeepMind's article: https://www.deepmind.com/publications/a-generalist-agent
04/06/2022
When one hears the term "Password Cracking", many think it must be to guess someone's password or similar. But the reality is not so satisfying.
Read this amazingly written blog by Rohan, as he explores various Deep Learning models and their algorithms, which can crack passwords efficiently.
Link:
Password Cracking On hearing the term "password-cracking," many will think this post will be about how to guess someone's password or somewhat similar, but…
16/05/2022
Hello everyone!
VLG is happy to announce its set of open projects for this summer. These projects are open for all, and we encourage all to take up a project.
The two projects are:
• Image Colorization using Conditional GAN's
• Super Mario RL Agent
The links for project descriptions are given below:
•Image Colorization: https://hackmd.io/-DI5UxSv-1jDGVwxqvFA/SyPf1_AI5
•Super Mario RL Agent: https://hackmd.io//HkCMOPALq
Website link: https://vlgiitr.github.io/open_projects/
Register yourself through the registration form link to be a part of these projects. The deadline for filling out the form is 20th May 2022.
The projects will tentatively start on 25th May and will end by 14th June. The projects will be certified by VLG upon completion.
For any doubts, feel free to reach out to us!
Greetings everyone!
We would be holding a discussion on Latest Advancements in Deep Learning, today at 5PM.
Students from all years are welcome to join in!
Topic: Latest Advancements in Deep Learning
Prerequisites: None
Time: Today, 5PM
Venue: ACM room, ground floor, SAC