Paper Notes Archive
Reading notes I wrote in 2022 while working through papers on sequence models, transformers, generative models, and holographic displays. Each note follows the same shape: summary, strengths, critique, and the resources I found useful.
These are kept online because people still link to them. Newer notes live in Knowledge Share.
-
November 2022 Cascaded Diffusion for Super-resolution Image Generation Cascaded Diffusion Models for High Fidelity Image Generation
-
November 2022 Review of the Guidance in Diffusion Models I plan to use Diffusion Models Beat GANs on Image Synthesis NIPS2021 paper as a foundation and review several diffusion guidance methods in this article…
-
November 2022 VQ-VAE VQ-VAE is aiming to provide a discrete latent representation space rather than continuous VAE ones so that it could better model discrete modalities such as…
-
November 2022 VAE: Variational Auto Encoder The motivation of VAE came from improving the representation (latent space, z) quality of the traditional autoencoder, so that we could take random samples…
-
November 2022 StyleGAN StyleGAN: A Style-Based Generator Architecture for Generative Adversarial Networks
-
November 2022 GAN: Generative Adversarial Nets Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua
-
November 2022 GLIDE: Text Guided Photorealistic Image Generation and Editing using Diffusion GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
-
November 2022 DDPM: Diffusion Model for Image Generation Come down to the implementation level, there are several modules to implement diffusion model: the noise scheduler, which sequentially adds up noise; the…
-
November 2022 Hogel-free Holography Praneeth Chakravarthula, Ethan Tseng, Henry Fuchs, Felix Heide
-
November 2022 DALL-E Ramesh, Aditya and Pavlov, Mikhail and Goh, Gabriel and Gray, and others PMLR 2021
-
October 2022 Efficient Geometry-aware 3D Generative Adversarial Networks I review this paper mainly for curiosity of the term ‘geometry-aware’ and ‘3D’. We always see works from 2D face generation and the physical correctness the…
-
October 2022 Holographic Glasses for Virtual Reality Jonghyun Kim, Manu Gopakumar, Suyeon Choi, Yifan Peng, Ward Lopes, Gordon Wetzstein
-
October 2022 Reformer: The Efficient Transformer The original Transformer self-attention takes NND parameter space in Q K dot product operation. A sequence of 64k will thus result in 16GB of memory. However…
-
October 2022 CLIP The intuition behind such success is that the task for model now is not blindly find the discrimination line for image data distribution and assign clusters…
-
October 2022 ImageGPT Recall that for Transformer structure, the parameter space of the self-attention layer is $$O(dn^2)$$ where n is the sequence token number. Even for a 300300…
-
October 2022 GPT-2 The revision of the Transformer decoder to fit for unsupervised training is quite straightforward. First, since there is no Transform encoder part in the…
-
October 2022 BERT Language Model Fine-tunning demands the BERT to model the context information (both left-to-right and right-to-left) of each word to better capture the semantics. By that…
-
October 2022 Self-attention with Relative Position Representations Absolute position encodes the relative position information based on the fact that for any fixed position offset k, $$sin((pos+k)/c)$$ can be acquired by the…
-
October 2022 Attention Is All You Need For encoder stack, the intuition behind self-attention comes from the coreference phenomenon in language. When considering the semantics of a word in the…
-
October 2022 Pixel Recurrent Neural Network The LSTM contains two components: state-to-state and input-to-state. For input-to-state component, the Row LSTM will take the whole input map and apply k1…
-
September 2022 Sequence to Sequence Learning with Neural Networks Second it stacks multiple LSTM layers rather than one by having multiple hidden states for a single timestep. The increase of the parameter numbers help the…
-
September 2022 Sequence to Sequence Learning with Neural Networks First is using separated LSTMs for encoder and decoder rather than a straight end to end design. This indirect idea makes it possible to train multiple…