aengusng8 Goto Github PK

followers: 31.0 following: 129.0 repos: 29.0 gists: 2.0

Name: Duc Anh (Aengus) N.

Type: User

Company: @VinAIResearch

Bio: Love the combination of mathematics, coding, and intuition. Contributor @huggingface 🤗; AI Research Resident @VinAIResearch

Twitter: aengusng8

My research interest lies in developing robust generative models and applying them to diverse applications, including conditional sampling, disentangled representation learning, and reasoning. Currently, my goal is to build a generative model capable of producing high-fidelity, diverse, and high-dimensional samples in a single forward pass.

My recent works focus on image generation and manipulation using ODE/SDE-based generative models, specifically diffusion probabilistic models.

My huggingface/diffusers pull requests [1*] [2*] [3]
My math derivation of DDPM [PDF]
My literature review on diffusion probabilistic models [Google Sheets]

There's too many problems. So how can you work on all problems simultaneously? You solve the meta-problem, which is to me just intelligence and how do you automate it? - Andrej Karpathy

Personal logs:

This is my fourth time resolving a bug in the long run 🏃‍♂️🏃, as well as medium-difficulty problems such as "How to work effectively with a large codebase?" and "Preparing an agenda and good questions for my presentation." I am still figuring out how to reproduce the phenomenon. My main strategies include: (1) Loading my mental RAM (my working memory) fully with the problem, be obsessed with it when I'm taking a shower, and falling asleep, until it's fully ingrained in my memory. I might be ready to wake up and work on it right there. This process can take a whole day or more. (2) Asking logical, systematic, and non-random questions, frequently.
I don't enjoy encountering old bugs. New bugs provide me with a natural source of dopamine. assert and raise are our friends.
Lots of minor engineering problems must be rapidly solved in an algorithmic way, thus contributing to good research.
Backpropagation and transformer are general ❤️. I like general things. (inductive prior will set a starting point until your model gets informed by your data, while the inductive bias inevitability limits the space of possible model-solutions)
Why? or Why is it important? So what?

Duc Anh (Aengus) N.'s Projects

aengusng.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

aengusng8

My personal repository

applied-ml

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

awesome-computer-vision

A curated list of awesome computer vision resources

awesome-mlops

A curated list of references for MLOps

computervision-recipes

Best Practices, code samples, and documentation for Computer Vision.

consistency-gan

Consistency Model (Song et al., ICML'23) + GAN + Destination-Aware Discriminator + Awareness Scheduler

crowdrender

Layout-to-Image Synthesis with Multiple Bounding Boxes (e.g., 20-100 Boxes)

deep-learning-tricks

Enumerate diverse machine learning training tricks.

delightfuldsa

120+ solutions in Python for intermediate/advanced data structures & algorithms problems from Codeforce, HackerRank, HackerEarth, Spoj, Uva, Codechef.

dialogpt2

gpt 2, multiturn conversations

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

dp

i2i-anything

I2SB: Image-to-Image Schrödinger Bridge, Dual Diffusion Implicit Bridges for Image-to-Image Translation (ICLR 2023)

k-diffusion-explained

Provides math derivations, code comments, and instructional videos to help understand "Elucidating the Design Space of Diffusion-Based Generative Models" (Karras et al., 2022)

ldm-thermal

lightning-convnext

ConvNeXt in Pytorch Lightning⚡ (https://github.com/facebookresearch/ConvNeXt)

lora-dreambooth

minorgrad

Forget Pytorch (in one day)! Building your deep learning framework.

mvf-vit

Multi-View Fusion Vision Transformer

noise-comparative-analysis

Expanding on the second contribution of "Perception Prioritized Training of Diffusion Models" (CVPR'22) with an implementation and extensions.

personal-site

personal site using al-folio

production-level-deep-learning

A guideline for building practical production-level deep learning systems to be deployed in real world applications.

prompt-embeding-enhancement

Image2Prompt with gradient guidance for any diffusion model

relaycontroller

sartorius-cell-instance-segmentation

Instance segmentation: two training stages with transfer learning, two inference stages with EfficientNetV2 and Mask R-CNN R101-FPN, ensemble masks with Weighted Boxes Fusion, heavily rotated Mosaic w/o artifact or tiny bounding boxes, Test time augmentation, five-fold cross-validation, Detectron2 with Albumentations, CIoU loss andGIoU loss.

aengusng8 Goto Github PK

Personal logs:

Duc Anh (Aengus) N.'s Projects

Recommend Projects

Recommend Topics

Recommend Org