🖥 Transformers From Scratch
PYTHON

In this notebook we have built a transformer model based on the Attention Is All You Need paper following along with Andrej Karpathy’s fantastic YouTube video: Let’s build GPT.

📌 Notebook: https://blog.matdmiller.com/posts/2023-06-10_transformers/notebook.html

https://news.1rj.ru/str/DataScienceT

🧠 BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis

git clone https://github.com/buaavrcg/BakedAvatar
cd BakedAvatar

🖥 Code: https://github.com/buaavrcg/BakedAvatar

📚 Paper: https://dl.acm.org/doi/10.1145/3618399

⚡️ Page: https://buaavrcg.github.io/BakedAvatar/

https://news.1rj.ru/str/DataScienceT

🔥Physics-based Text-to-Motion🔥

🖥 Code: github.com/jiawei-ren/insactor

📚 Paper: arxiv.org/abs/2312.17135

⚡️ Project: https://jiawei-ren.github.io/projects/insactor/

Sign Language Understanding

🖥 Github: https://github.com/FangyunWei/SLRT

📕 Paper: https://arxiv.org/pdf/2401.05336v1.pdf

🔥Datasets: https://paperswithcode.com/dataset/csl-daily

https://news.1rj.ru/str/DataScienceT

Get 30% OFF Top-Notch ClearVPN with code "Developers30" Today!

Your Benefits:
🌍 Explore global resources!
📱 Test app localization!
👀 Research your competitors!
🔒 Enhance your privacy & security!
🖧 Check network infrastructures!
🚀 Bypass ISP restrictions!
🌐 Access regional contents!

Save via this link ONLY! Hurry up !
*Best for developers. Do not forget to paste "Developers30" promo code.

🔗 https://macpaw.audw.net/Developers30

⚡️ SigLIP: a better CLIP model

🖥 Github: https://github.com/NielsRogge/Transformers-Tutorials/blob/master/SigLIP/Inference_with_(multilingual)_SigLIP%2C_a_better_CLIP_model.ipynb

📚 Paper: https://arxiv.org/abs/2303.15343

⚡️HF: https://huggingface.co/docs/transformers/main/en/model_doc/siglip

https://news.1rj.ru/str/DataScienceT

💊 AMIE: A research AI system for diagnostic medical reasoning and conversations

💡 Blog: https://blog.research.google/2024/01/amie-research-ai-system-for-diagnostic_12.html

📚 Paper: https://arxiv.org/abs/2401.05654

https://news.1rj.ru/str/DataScienceT

ViQuAE

🖥 Github: https://github.com/paullerner/viquae

📕 Paper: https://arxiv.org/pdf/2401.05736v1.pdf

🔥Datasets: https://paperswithcode.com/dataset/imagenet

✨ Tasks: https://paperswithcode.com/task/cross-modal-retrieval

Surprise

Our new channel - Datasets repositories

https://news.1rj.ru/str/datasets1

🖼️ DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders 🔥

🖥 Code: github.com/piddnad/DDColor

📚 Paper: arxiv.org/abs/2212.11613

🌟 Colab: https://github.com/camenduru/DDColor-colab

https://news.1rj.ru/str/DataScienceT

🔉 MAGNeT: Masked Audio Generation using a Single Non-Autoregressive Transformer

🖥 Code: https://github.com/facebookresearch/audiocraft/blob/main/docs/MAGNET.md#api

🚀 HF: https://huggingface.co/collections/facebook/magnet-659ef0ceb62804e6f41d1466

📚 Paper: https://arxiv.org/abs/2401.04577

🌟 Project: https://pages.cs.huji.ac.il/adiyoss-lab/MAGNeT/

⚛️ Datasets: https://github.com/facebookresearch/audiocraft/blob/main/docs/DATASETS.md

https://news.1rj.ru/str/DataScienceT

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation

🖥 Github: https://github.com/kaistai/prometheus-vision

📕 Paper: https://arxiv.org/abs/2401.06591v1

🔥Datasets: https://paperswithcode.com/dataset/ok-vqa

https://news.1rj.ru/str/DataScienceT

📐 AlphaGeometry: An Olympiad-level AI system for geometry

https://deepmind.google/discover/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/

🖥 Code: https://github.com/facebookresearch/audiocraft/blob/main/docs/MAGNET.md#api

🚀 Deepmind: https://deepmind.google/discover/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/

📚 Paper: https://www.nature.com/articles/s41586-023-06747-5

💃 (Moore) Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

🖥 Code: https://github.com/MooreThreads/Moore-AnimateAnyone

🚀 Colab: github.com/camenduru/Moore-AnimateAnyone-colab

📚 Paper: arxiv.org/abs/2311.17117

🌟 Project: humanaigc.github.io/animate-anyone/

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation

🖥 Github: https://github.com/kaistai/prometheus-vision

📕 Paper: https://arxiv.org/abs/2401.06591v1

🔥Datasets: https://paperswithcode.com/dataset/ok-vqa

To learn AI from basics:
YouTube: https://www.youtube.com/c/asifimmanad

Telegram: https://news.1rj.ru/str/DataScienceT