Multivariate Probabilistic Time Series Forecasting with Informer
Efficient transformer-based model for LSTF.
Method introduces a Probabilistic Attention mechanism to select the “active” queries rather than the “lazy” queries and provides a sparse Transformer thus mitigating the quadratic compute and memory requirements of vanilla attention.
🤗Hugging face:
https://huggingface.co/blog/informer
⏩ Paper:
https://huggingface.co/docs/transformers/main/en/model_doc/informer
⭐️ Colab:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multivariate_informer.ipynb
💨 Dataset:
https://huggingface.co/docs/datasets/v2.7.0/en/package_reference/main_classes#datasets.Dataset.set_transform
https://t.iss.one/DataScienceT
Efficient transformer-based model for LSTF.
Method introduces a Probabilistic Attention mechanism to select the “active” queries rather than the “lazy” queries and provides a sparse Transformer thus mitigating the quadratic compute and memory requirements of vanilla attention.
🤗Hugging face:
https://huggingface.co/blog/informer
⏩ Paper:
https://huggingface.co/docs/transformers/main/en/model_doc/informer
⭐️ Colab:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multivariate_informer.ipynb
💨 Dataset:
https://huggingface.co/docs/datasets/v2.7.0/en/package_reference/main_classes#datasets.Dataset.set_transform
https://t.iss.one/DataScienceT
❤🔥2👍1
Linear Algebra in Python: Matrix Inverses and Least Squares
https://realpython.com/python-linear-algebra/
https://realpython.com/python-linear-algebra/
❤🔥4👍1
GPT-4 Technical Report
Source code: https://github.com/openai/evals
Paper: https://cdn.openai.com/papers/gpt-4.pdf
Source code: https://github.com/openai/evals
Paper: https://cdn.openai.com/papers/gpt-4.pdf
❤🔥4
Tuned Lens 🔎
Simple interface training and evaluating tuned lenses. A tuned lens allows us to peak at the iterative computations a transformer uses to compute the next token.
🖥 Github: https://github.com/alignmentresearch/tuned-lens
⏩ Paper: https://arxiv.org/abs/2303.08112v1
⭐️ Dataset: https://paperswithcode.com/dataset/the-pile
🖥 Colab: https://colab.research.google.com/github/AlignmentResearch/tuned-lens/blob/main/notebooks/interactive.ipynb
https://t.iss.one/DataScienceT
Simple interface training and evaluating tuned lenses. A tuned lens allows us to peak at the iterative computations a transformer uses to compute the next token.
pip install tuned-lens
🖥 Github: https://github.com/alignmentresearch/tuned-lens
⏩ Paper: https://arxiv.org/abs/2303.08112v1
⭐️ Dataset: https://paperswithcode.com/dataset/the-pile
🖥 Colab: https://colab.research.google.com/github/AlignmentResearch/tuned-lens/blob/main/notebooks/interactive.ipynb
https://t.iss.one/DataScienceT
❤🔥6
OpenSeeD
A Simple Framework for Open-Vocabulary Segmentation and Detection
🖥 Github: https://github.com/idea-research/openseed
⏩ Paper: https://arxiv.org/abs/2303.08131v2
💨 Dataset: https://paperswithcode.com/dataset/objects365
https://t.iss.one/DataScienceT
A Simple Framework for Open-Vocabulary Segmentation and Detection
🖥 Github: https://github.com/idea-research/openseed
⏩ Paper: https://arxiv.org/abs/2303.08131v2
💨 Dataset: https://paperswithcode.com/dataset/objects365
https://t.iss.one/DataScienceT
❤🔥3
Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank
🖥 Github: https://github.com/huang-shirui/semi-uir
⏩ Paper: https://arxiv.org/abs/2303.09101v1
💨 Project: https://paperswithcode.com/dataset/uieb
https://t.iss.one/DataScienceT
🖥 Github: https://github.com/huang-shirui/semi-uir
⏩ Paper: https://arxiv.org/abs/2303.09101v1
💨 Project: https://paperswithcode.com/dataset/uieb
https://t.iss.one/DataScienceT
❤🔥2
This media is not supported in your browser
VIEW IN TELEGRAM
WebSHAP: Towards Explaining Any Machine Learning Models Anywhere
🖥 Github: https://github.com/poloclub/webshap
⏩ Paper: https://arxiv.org/abs/2303.09545v1
💨 Project: https://poloclub.github.io/webshap
https://t.iss.one/DataScienceT
🖥 Github: https://github.com/poloclub/webshap
⏩ Paper: https://arxiv.org/abs/2303.09545v1
💨 Project: https://poloclub.github.io/webshap
https://t.iss.one/DataScienceT
❤🔥3👍1
🖥 GigaGAN - Pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe.
https://github.com/lucidrains/gigagan-pytorch
https://t.iss.one/DataScienceT
Implementation of GigaGAN, new SOTA GAN out of Adobe.
https://github.com/lucidrains/gigagan-pytorch
https://t.iss.one/DataScienceT
❤🔥2
Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation (CVPR 2023)
Novel Diffusion Audio-Gesture Transformer is devised to better attend to the information from multiple modalities and model the long-term temporal dependency.
🖥 Github: https://github.com/advocate99/diffgesture
⏩ Paper: https://arxiv.org/abs/2303.09119v1
💨 Dataset: https://paperswithcode.com/dataset/beat
https://t.iss.one/DataScienceT
Novel Diffusion Audio-Gesture Transformer is devised to better attend to the information from multiple modalities and model the long-term temporal dependency.
🖥 Github: https://github.com/advocate99/diffgesture
⏩ Paper: https://arxiv.org/abs/2303.09119v1
💨 Dataset: https://paperswithcode.com/dataset/beat
https://t.iss.one/DataScienceT
👍3❤🔥2
Deep Metric Learning for Unsupervised CD
🖥 Github: https://github.com/wgcban/metric-cd
⏩ Paper: https://arxiv.org/abs/2303.09536v1
https://t.iss.one/DataScienceT
🖥 Github: https://github.com/wgcban/metric-cd
⏩ Paper: https://arxiv.org/abs/2303.09536v1
https://t.iss.one/DataScienceT
👍2❤🔥1
This media is not supported in your browser
VIEW IN TELEGRAM
⚜️ ViperGPT: Visual Inference via Python Execution for Reasoning
ViperGPT, a framework that leverages code-generation models to compose vision-and-language models into subroutines to produce a result for any query.
🖥 Github: https://github.com/cvlab-columbia/viper
⏩ Paper: https://arxiv.org/pdf/2303.08128.pdf
💨 Project: https://paperswithcode.com/dataset/beat
https://t.iss.one/DataScienceT
ViperGPT, a framework that leverages code-generation models to compose vision-and-language models into subroutines to produce a result for any query.
🖥 Github: https://github.com/cvlab-columbia/viper
⏩ Paper: https://arxiv.org/pdf/2303.08128.pdf
💨 Project: https://paperswithcode.com/dataset/beat
https://t.iss.one/DataScienceT
👍3🏆2❤🔥1
🎥 Zero-1-to-3: Zero-shot One Image to 3D Object
Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image.
🖥 Github: https://github.com/cvlab-columbia/zero123
🤗 Hugging face: https://huggingface.co/spaces/cvlab/zero123-live
⏩ Paper: https://arxiv.org/abs/2303.11328v1
⏩ Dataset: https://zero123.cs.columbia.edu/
💨 Project: https://paperswithcode.com/dataset/beat
⭐️ Demo: https://huggingface.co/spaces/cvlab/zero123
https://t.iss.one/DataScienceT
Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image.
🖥 Github: https://github.com/cvlab-columbia/zero123
🤗 Hugging face: https://huggingface.co/spaces/cvlab/zero123-live
⏩ Paper: https://arxiv.org/abs/2303.11328v1
⏩ Dataset: https://zero123.cs.columbia.edu/
💨 Project: https://paperswithcode.com/dataset/beat
⭐️ Demo: https://huggingface.co/spaces/cvlab/zero123
https://t.iss.one/DataScienceT
❤3❤🔥3🏆2👍1
MIT Introduction to Deep Learning - 2023 Starting soon! MIT Intro to DL is one of the most concise AI courses on the web that cover basic deep learning techniques, architectures, and applications.
2023 lectures are starting in just one day, Jan 9th!
Link to register:
https://introtodeeplearning.com
MIT Introduction to Deep Learning The 2022 lectures can be found here:
https://m.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
https://t.iss.one/DataScienceT
2023 lectures are starting in just one day, Jan 9th!
Link to register:
https://introtodeeplearning.com
MIT Introduction to Deep Learning The 2022 lectures can be found here:
https://m.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
https://t.iss.one/DataScienceT
❤🔥3👍3🏆2
Train your ControlNet with diffusers 🧨
ControlNet is a neural network structure that allows fine-grained control of diffusion models by adding extra conditions.
🤗 Hugging face: https://huggingface.co/blog/train-your-controlnet#
🖥 Github: https://github.com/huggingface/blog/blob/main/train-your-controlnet.md
⏩ ControlNet training example: https://github.com/huggingface/diffusers/tree/main/examples/controlnet
https://t.iss.one/DataScienceT
ControlNet is a neural network structure that allows fine-grained control of diffusion models by adding extra conditions.
🤗 Hugging face: https://huggingface.co/blog/train-your-controlnet#
🖥 Github: https://github.com/huggingface/blog/blob/main/train-your-controlnet.md
⏩ ControlNet training example: https://github.com/huggingface/diffusers/tree/main/examples/controlnet
https://t.iss.one/DataScienceT
❤🔥3🏆2
🔥 Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
A new approach for high-quality domain translation with better controllability.
🖥 Github: https://github.com/LeeDongYeun/FixNoise
⏩ Paper: https://arxiv.org/abs/2303.11545v1
💨 Dataset: https://paperswithcode.com/dataset/metfaces
https://t.iss.one/DataScienceT
A new approach for high-quality domain translation with better controllability.
🖥 Github: https://github.com/LeeDongYeun/FixNoise
⏩ Paper: https://arxiv.org/abs/2303.11545v1
💨 Dataset: https://paperswithcode.com/dataset/metfaces
https://t.iss.one/DataScienceT
❤1
This media is not supported in your browser
VIEW IN TELEGRAM
"A panda is playing guitar on times square"
Text2Video-Zero
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Paper: https://arxiv.org/abs/2303.13439
Video Result: video result link
Source code: https://github.com/picsart-ai-research/text2video-zero
https://t.iss.one/DataScienceT
Text2Video-Zero
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Paper: https://arxiv.org/abs/2303.13439
Video Result: video result link
Source code: https://github.com/picsart-ai-research/text2video-zero
https://t.iss.one/DataScienceT
❤1
This media is not supported in your browser
VIEW IN TELEGRAM
Conditional Image-to-Video Generation with Latent Flow Diffusion Models
New approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image.
🖥 Github: https://github.com/nihaomiao/cvpr23_lfdm
⏩ Paper: https://arxiv.org/abs/2303.13744v1
💨 Dataset: https://drive.google.com/file/d/1dRn1wl5TUaZJiiDpIQADt1JJ0_q36MVG/view?usp=share_link
https://t.iss.one/DataScienceT
New approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image.
🖥 Github: https://github.com/nihaomiao/cvpr23_lfdm
⏩ Paper: https://arxiv.org/abs/2303.13744v1
💨 Dataset: https://drive.google.com/file/d/1dRn1wl5TUaZJiiDpIQADt1JJ0_q36MVG/view?usp=share_link
https://t.iss.one/DataScienceT
❤🔥2❤2👍1
What's your gender?
This media is not supported in your browser
VIEW IN TELEGRAM
Test of Time: Instilling Video-Language Models with a Sense of Time
GPT-5 will likely have video abilities, but will it have a sense of time? Here is answer to this question in #CVPR2023 paper by student of University of Amsterdam to learn how to instil time into video-language foundation models.
Paper:
https://arxiv.org/abs/2301.02074
Code:
https://github.com/bpiyush/TestOfTime
Project Page:
https://bpiyush.github.io/testoftime-website/
https://t.iss.one/DataScienceT
GPT-5 will likely have video abilities, but will it have a sense of time? Here is answer to this question in #CVPR2023 paper by student of University of Amsterdam to learn how to instil time into video-language foundation models.
Paper:
https://arxiv.org/abs/2301.02074
Code:
https://github.com/bpiyush/TestOfTime
Project Page:
https://bpiyush.github.io/testoftime-website/
https://t.iss.one/DataScienceT
❤🔥3