Skip to content

Paper Readings Workshop (Spring 2023)

This assignment can be done in teams of 1 or 2 students. For each selected paper, your team is required to prepare and deliver a presentation (max 15 mins) to the class. For each selected topic, students must show thorough understanding of the paper and technical knowledge that reflects the topics covered in this class.

Workshop

Friday April 28th, 2023 at Tyler 55.

Acknowledgement

This workshop is being sponsored by a TensorFlow and Google AI award to support machine learning courses and diversity programs.

Placeholder

List of Presentations (papers)

Session 1: 2pm

  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, ICLR 2021, Nick and Alex [PDF]

  • Scaling Vision Transformers, CVPR 2022, Arlen and Tuyetlinh [PDF]

  • When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations, ICLR 2022, Calvin [PDF]

  • Masked Autoencoders Are Scalable Vision Learners, CVPR 2022, Benedikt [PDF]

  • A ConvNet for the 2020s, CVPR 2022, Maryam and Supti [PDF]

  • High-Resolution Image Synthesis with Latent Diffusion Models, CVPR 2022, Jacob [PDF]

  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding, Neurips 2022, Lingchao [PDF]

Lunch and Refreshments

Session 2: 4pm

  • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, ACL 2019, Guanhua [PDF]

  • Finetuned Language Models Are Zero-Shot Learners, ICLR 2022, Priyankan and Arup [PDF]

  • Training Compute-Optimal Large Language Models, Neurips 2022, Behrooz [PDF]

  • Gradient Descent: The Ultimate Optimizer, Neurips 2022, Timothy and Borano [PDF]

  • GradMax: Growing Neural Networks using Gradient Information, ICLR 2022 Mojgan and Arash [PDF]