Weekly Research Newsletter - KIIT

By Priyansi, Junaid Rahim and Biswaroop Bhattacharjee

An opt-in weekly newsletter for the undergraduate research enthusiasts in KIIT. We intend to share interesting research articles and start conversations about the latest ideas in artificial intelligence, computer science and mathematics. Every Friday, all subscribers will receive some researc... Read more

An opt-in weekly newsletter for the undergraduate research enthusiasts in KIIT. We intend to share interesting research articles and start conversations about the latest ideas in artificial intelligence, computer science and mathematics.

Every Friday, all subscribers will receive some research articles straight in their inbox. The papers will usually be a mix of that week’s popular research articles, review articles and some seminal papers in the various fields mentioned above.

By subscribing, you agree with Revue’s Terms of Service and Privacy Policy and understand that Weekly Research Newsletter - KIIT will receive your email address.

Weekly Research Newsletter - KIIT
430

subscribers

18

issues

#18・

Weekly Research Newsletter - KIIT - Issue #18

By Mark Chen, Jerry Tworek, Heewoo Jun et al.We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex powers GitHub Copilot. On HumanEval…

#17・

Weekly Research Newsletter - KIIT - Issue #17

By David Silver, Satinder Singh, Doina Precup, Richard S. SuttonIn this article we hypothesise that intelligence, and its associated abilities, can be understood as subserving the maximisation of reward. Accordingly, reward is enough to drive behaviour that e…

#16・

Weekly Research Newsletter - KIIT - Issue #16

By Xiangning Chen, Cho-Jui Hsieh, Boqing GongVision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures. Existing works empower the models by massive data, such as …

#15・

Weekly Research Newsletter - KIIT - Issue #15

AI-generated images have been advancing at breakneck speed — capable of synthetically reconstructing historical scenes or changing a photo to resemble the style of Van Gogh or Renoir. Now, we’ve built a system that can replace text both in scenes and handwrit…

#14・

Weekly Research Newsletter - KIIT - Issue #14

By Tanmay Gupta, Amita Kamath, Aniruddha Kembhavi, Derek HoiemA special purpose learning system assumes knowledge of admissible tasks at design time. Adapting such a system to unforeseen tasks requires architecture manipulation such as adding an output head f…

#13・

Weekly Research Newsletter - KIIT - Issue #13

By Mike Lambeta, Huazhe Xu, Jingwei Xu, Po-Wei Chou, Shaoxiong Wang, Trevor Darrell, Roberto CalandraWith the increased availability of rich tactile sensors, there is an equally proportional need for open-source and integrated software capable of efficiently …

#12・

Weekly Research Newsletter - KIIT - Issue #12

By Hanxiao Liu, Zihang Dai, David R. So, Quoc V. LeTransformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple attention-free network archi…

#11・

Weekly Research Newsletter - KIIT - Issue #11

Stephan R. Richter, Hassan Abu AlHaija, Vladlen KoltunWe present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipeli…

#10・

Weekly Research Newsletter - KIIT - Issue #10

By Tanmay Gupta, Amita Kamath, Aniruddha Kembhavi, Derek HoiemA special purpose learning system assumes knowledge of admissible tasks at design time. Adapting such a system to unforeseen tasks requires architecture manipulation such as adding an output head f…

#9・

Weekly Research Newsletter - KIIT

By Mingxing Tan, Quoc V. LeThis paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aw…

#8・

Weekly Research Newsletter - KIIT - Issue #8

By Ben Jaderberg, Lewis W. Anderson, Weidi Xie, Samuel Albanie, Martin Kiffner, Dieter Jaksch

#7・

Weekly Research Newsletter - KIIT

By Pratik Fegade, Tianqi Chen, Phillip Gibbons, Todd MowryOptimizing deep learning models is generally performed in two steps: (i) high-level graph optimizations such as kernel fusion and (ii) low level kernel optimizations such as those found in vendor libra…

#6・

Weekly Research Newsletter - KIIT - Issue #6

By Hans-Martin Heyn, Eric Knauss, Amna Pir Muhammad, Olof Erikssonz, Jennifer Linder, Padmini Subbiah, Shameer Kumar Pradhan, Sagar TungalAvailability of powerful computation and communication technology as well as advances in artificial intelligence enable a…

#5・

Weekly Research Newsletter - KIIT

By Emilien Dupont, Adam Goliński, Milad Alizadeh, Yee Whye Teh, Arnaud DoucetWe propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image…

#4・

Weekly Research Newsletter - KIIT

By OpenAIWe’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step towa…

#3・

Weekly Research Newsletter - KIIT

By Yifan Jiang, Shiyu Chang, Zhangyang Wang

#2・

Weekly Research Newsletter - KIIT

By Andrew Brock, Soham De, Samuel L. Smith, Karen SimonyanBatch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Alth…

#1・

Weekly Research Newsletter

By Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since …