| 1. | | Tiny Titans: Can Smaller LLMs Punch Above Their Weight? (arxiv.org) |
| 1 point by deeplstm on Feb 5, 2024 | past |
|
| 2. | | Wav2CLIP: Connecting Text, Images, and Audio [video] (youtube.com) |
| 2 points by deeplstm on Nov 3, 2021 | past | 1 comment |
|
| 3. | | 16x smaller than GPT3 but better [video] (youtube.com) |
| 3 points by deeplstm on Oct 24, 2021 | past | 1 comment |
|
| 4. | | Leveraging Free Data to Improve Punctuation Model [video] (youtube.com) |
| 2 points by deeplstm on Oct 23, 2021 | past | 1 comment |
|
| 5. | | BART: Denoising Seq2Seq Pre-training for NLG (explained) (youtube.com) |
| 1 point by deeplstm on Oct 8, 2021 | past | 1 comment |
|
| 6. | | VideoCLIP: Contrastive Pre-Training ForZero-Shot Video-Text Understanding (youtube.com) |
| 2 points by deeplstm on Oct 3, 2021 | past |
|
| 7. | | Teach Computers to Understand Videos and Text – VideoClip (youtube.com) |
| 1 point by deeplstm on Oct 2, 2021 | past |
|
| 8. | | Self Training for Better Few Shot Learning (Video Explained) (youtube.com) |
| 3 points by deeplstm on Sept 19, 2021 | past |
|
| 9. | | Shortformer: Better Language Modeling Using Shorter Inputs (Paper Explained) (youtube.com) |
| 3 points by deeplstm on Feb 15, 2021 | past | 1 comment |
|
| 10. | | TLDR – Extreme Summarization of Scientific Documents (youtube.com) |
| 4 points by deeplstm on Nov 23, 2020 | past | 1 comment |
|
| 11. | | AI Detects Covid-19 by Listening to Coughs [video] (youtube.com) |
| 4 points by deeplstm on Nov 9, 2020 | past | 1 comment |
|
| 12. | | Efficient End to End Entity Linking [video] (youtube.com) |
| 4 points by deeplstm on Oct 27, 2020 | past | 1 comment |
|
| 13. | | Vokenization Improving Language Understanding [video] (youtube.com) |
| 5 points by deeplstm on Oct 22, 2020 | past | 1 comment |
|
| 14. | | Deep Bidirectional Transformers for Language Understanding [video] (youtube.com) |
| 6 points by deeplstm on Oct 19, 2020 | past | 1 comment |
|
| 15. | | Transformers for Image Recognition at Scale [video] (youtu.be) |
| 43 points by deeplstm on Oct 12, 2020 | past | 11 comments |
|
| 16. | | Improving Transformer Models by Reordering Their Sublayers (youtu.be) |
| 5 points by deeplstm on Sept 27, 2020 | past |
|
| 17. | | Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (youtu.be) |
| 4 points by deeplstm on Sept 20, 2020 | past |
|
| 18. | | Well Read Students Learn Better: On the Important of Pre-Training Compact Models (youtu.be) |
| 6 points by deeplstm on Sept 13, 2020 | past |
|
| 19. | | Why Virtual Small Talk Is Intimidating (youtu.be) |
| 1 point by deeplstm on Sept 9, 2020 | past |
|
| 20. | | Transformer Architecture Explained (youtu.be) |
| 1 point by deeplstm on Sept 7, 2020 | past |
|
| 21. | | Question and Answer Test-Train Overlap in Open Domain Question Answering Data (youtu.be) |
| 3 points by deeplstm on Aug 30, 2020 | past |
|
| 22. | | LinkedIn's New Ranking Model – DeText: A Deep Text Ranking Framework with Bert (youtu.be) |
| 6 points by deeplstm on Aug 23, 2020 | past |
|
| 23. | | QpenQA State-of-the-Art – Realm: Retrieval-Augmented Language Model Pre-Training (youtu.be) |
| 3 points by deeplstm on Aug 15, 2020 | past | 1 comment |
|
| 24. | | GAN Bert: Generative Adversarial Learning for Text Classification (Explained) (youtu.be) |
| 3 points by deeplstm on Aug 6, 2020 | past |
|
| 25. | | Pre-Training Is (Almost) All You Need: An Application to Commonsense Reasoning (youtu.be) |
| 2 points by deeplstm on Aug 4, 2020 | past |
|
| 26. | | Quantifying Attention Flow in Transformers (Explained) (youtu.be) |
| 4 points by deeplstm on July 27, 2020 | past |
|
| 27. | | Revealing Dark Secrets of Bert (Analysis of BERT's Attention Heads) Explained (youtu.be) |
| 2 points by deeplstm on June 29, 2020 | past |
|
| 28. | | Distilling Task Specific Knowledge from Bert into Simple Neural Networks (youtu.be) |
| 3 points by deeplstm on March 28, 2020 | past |
|
| 29. | | Electra Pre-training Text Encoders as Discriminators (paper explained) (youtu.be) |
| 3 points by deeplstm on March 16, 2020 | past |
|
| 30. | | Molecule Attention Transformer (Deep Learning Paper Explained) (youtu.be) |
| 2 points by deeplstm on March 11, 2020 | past |
|
|
| More |
