generated from daviddmc/daviddmc.github.io
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
a7a952c
commit 3bf87ec
Showing
15 changed files
with
16 additions
and
226 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,7 +0,0 @@ | ||
| @article{gregor2015draw, | ||
| title={DRAW: A recurrent neural network for image generation}, | ||
| author={Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo Jimenez and Wierstra, Daan}, | ||
| journal={arXiv preprint, arXiv:1502.04623}, | ||
| year={2015}, | ||
| url={https://arxiv.org/pdf/1502.04623.pdf} | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,203 +0,0 @@ | ||
|
|
||
| @inproceedings{CLIP, | ||
| title={Learning transferable visual models from natural language supervision}, | ||
| author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others}, | ||
| booktitle={International Conference on Machine Learning}, | ||
| pages={8748--8763}, | ||
| year={2021}, | ||
| organization={PMLR}, | ||
| url={../../2021/CLIP} | ||
| } | ||
|
|
||
| @article{GPT-2, | ||
| title={Language models are unsupervised multitask learners}, | ||
| author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya and others}, | ||
| journal={OpenAI blog}, | ||
| volume={1}, | ||
| number={8}, | ||
| pages={9}, | ||
| year={2019}, | ||
| url={../../2019/GPT-2} | ||
| } | ||
|
|
||
| @inproceedings{GPT-3, | ||
| author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario}, | ||
| booktitle = {Advances in Neural Information Processing Systems}, | ||
| editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin}, | ||
| pages = {1877--1901}, | ||
| publisher = {Curran Associates, Inc.}, | ||
| title = {Language Models are Few-Shot Learners}, | ||
| volume = {33}, | ||
| year = {2020}, | ||
| url={../../2020/GPT-3} | ||
| } | ||
|
|
||
| @article{T5, | ||
| title={Exploring the limits of transfer learning with a unified text-to-text transformer.}, | ||
| author={Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J and others}, | ||
| journal={J. Mach. Learn. Res.}, | ||
| volume={21}, | ||
| number={140}, | ||
| pages={1--67}, | ||
| year={2020}, | ||
| url={../../2019/T5} | ||
| } | ||
|
|
||
| @article{GPT, | ||
| title={Improving language understanding by generative pre-training}, | ||
| author={Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya and others}, | ||
| year={2018}, | ||
| publisher={OpenAI}, | ||
| url={../../2018/GPT} | ||
| } | ||
|
|
||
| @article{BERT, | ||
| title={BERT: Pre-training of deep bidirectional transformers for language understanding}, | ||
| author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, | ||
| journal={arXiv preprint arXiv:1810.04805}, | ||
| year={2018}, | ||
| url={../../2018/BERT} | ||
| } | ||
|
|
||
| @article{Megatron-LM, | ||
| title={Megatron-LM: Training multi-billion parameter language models using model parallelism}, | ||
| author={Shoeybi, Mohammad and Patwary, Mostofa and Puri, Raul and LeGresley, Patrick and Casper, Jared and Catanzaro, Bryan}, | ||
| journal={arXiv preprint arXiv:1909.08053}, | ||
| year={2019}, | ||
| url={https://arxiv.org/pdf/1909.08053.pdf} | ||
| } | ||
|
|
||
| @article{Turing-NLG, | ||
| title={Turing-NLG: A 17-billion-parameter language model by Microsoft}, | ||
| author={Rosset, Corby}, | ||
| journal={Microsoft Blog}, | ||
| volume={1}, | ||
| number={2}, | ||
| year={2020}, | ||
| url={https://www.microsoft.com/en-us/research/blog/turing-nlg-a-17-billion-parameter-language-model-by-microsoft/} | ||
| } | ||
|
|
||
| @misc{InstructGPT, | ||
| doi = {10.48550/ARXIV.2203.02155}, | ||
| url = {../../2022/InstructGPT}, | ||
| author = {Ouyang, Long and Wu, Jeff and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll L. and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and Schulman, John and Hilton, Jacob and Kelton, Fraser and Miller, Luke and Simens, Maddie and Askell, Amanda and Welinder, Peter and Christiano, Paul and Leike, Jan and Lowe, Ryan}, | ||
| keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences}, | ||
| title = {Training language models to follow instructions with human feedback}, | ||
| publisher = {arXiv}, | ||
| year = {2022}, | ||
| copyright = {arXiv.org perpetual, non-exclusive license} | ||
| } | ||
|
|
||
| @misc{Whisper, | ||
| doi = {10.48550/ARXIV.2212.04356}, | ||
| url = {../../2022/Whisper}, | ||
| author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya}, | ||
| title = {Robust Speech Recognition via Large-Scale Weak Supervision}, | ||
| publisher = {arXiv}, | ||
| year = {2022}, | ||
| copyright = {arXiv.org perpetual, non-exclusive license} | ||
| } | ||
|
|
||
| @inproceedings{ELMo, | ||
| title = "Deep Contextualized Word Representations", | ||
| author = "Peters, Matthew E. and | ||
| Neumann, Mark and | ||
| Iyyer, Mohit and | ||
| Gardner, Matt and | ||
| Clark, Christopher and | ||
| Lee, Kenton and | ||
| Zettlemoyer, Luke", | ||
| booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)", | ||
| month = jun, | ||
| year = "2018", | ||
| address = "New Orleans, Louisiana", | ||
| publisher = "Association for Computational Linguistics", | ||
| url = "https://arxiv.org/pdf/1802.05365.pdf", | ||
| doi = "10.18653/v1/N18-1202", | ||
| pages = "2227--2237", | ||
| } | ||
|
|
||
| @inproceedings{Transformer, | ||
| author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \L ukasz and Polosukhin, Illia}, | ||
| booktitle = {Advances in Neural Information Processing Systems}, | ||
| editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett}, | ||
| pages = {}, | ||
| publisher = {Curran Associates, Inc.}, | ||
| title = {Attention is All you Need}, | ||
| url = {https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf}, | ||
| volume = {30}, | ||
| year = {2017} | ||
| } | ||
|
|
||
| @article{Gumbel-Softmax, | ||
| title={Categorical reparameterization with gumbel-softmax}, | ||
| author={Jang, Eric and Gu, Shixiang and Poole, Ben}, | ||
| journal={arXiv preprint arXiv:1611.01144}, | ||
| year={2016}, | ||
| url={../../2017/Gumbel-Softmax} | ||
| } | ||
|
|
||
| @inproceedings{Stable-Diffusion, | ||
| title={High-resolution image synthesis with latent diffusion models}, | ||
| author={Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj{\"o}rn}, | ||
| booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, | ||
| pages={10684--10695}, | ||
| year={2022}, | ||
| url={../../2022/Stable-Diffusion} | ||
| } | ||
|
|
||
| @inproceedings{DALL-E, | ||
| title={Zero-shot text-to-image generation}, | ||
| author={Ramesh, Aditya and Pavlov, Mikhail and Goh, Gabriel and Gray, Scott and Voss, Chelsea and Radford, Alec and Chen, Mark and Sutskever, Ilya}, | ||
| booktitle={International Conference on Machine Learning}, | ||
| pages={8821--8831}, | ||
| year={2021}, | ||
| organization={PMLR}, | ||
| url={https://arxiv.org/pdf/2102.12092.pdf} | ||
| } | ||
|
|
||
| @article{VQ-VAE-2, | ||
| title={Generating diverse high-fidelity images with vq-vae-2}, | ||
| author={Razavi, Ali and Van den Oord, Aaron and Vinyals, Oriol}, | ||
| journal={Advances in neural information processing systems}, | ||
| volume={32}, | ||
| year={2019}, | ||
| url={https://proceedings.neurips.cc/paper/2019/file/5f8e2fa1718d1bbcadf1cd9c7a54fb8c-Paper.pdf} | ||
| } | ||
|
|
||
| @article{ADM, | ||
| title={Diffusion models beat gans on image synthesis}, | ||
| author={Dhariwal, Prafulla and Nichol, Alexander}, | ||
| journal={Advances in Neural Information Processing Systems}, | ||
| volume={34}, | ||
| pages={8780--8794}, | ||
| year={2021}, | ||
| url={https://arxiv.org/pdf/2105.05233.pdf} | ||
| } | ||
|
|
||
| @article{SR3, | ||
| title={Image super-resolution via iterative refinement}, | ||
| author={Saharia, Chitwan and Ho, Jonathan and Chan, William and Salimans, Tim and Fleet, David J and Norouzi, Mohammad}, | ||
| journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, | ||
| year={2022}, | ||
| publisher={IEEE}, | ||
| url={https://arxiv.org/pdf/2104.07636.pdf} | ||
| } | ||
|
|
||
| @article{DDPM, | ||
| title={Denoising diffusion probabilistic models}, | ||
| author={Ho, Jonathan and Jain, Ajay and Abbeel, Pieter}, | ||
| journal={Advances in Neural Information Processing Systems}, | ||
| volume={33}, | ||
| pages={6840--6851}, | ||
| year={2020}, | ||
| url={../../2020/DDPM} | ||
| } | ||
|
|
||
| @article{DDIM, | ||
| title={Denoising diffusion implicit models}, | ||
| author={Song, Jiaming and Meng, Chenlin and Ermon, Stefano}, | ||
| journal={arXiv preprint arXiv:2010.02502}, | ||
| year={2020}, | ||
| url={../../2020/DDIM} | ||
| } | ||
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.