🟢 MeloTTS is a high-quality multi-lingual text-to-speech library

Mellott is one of the best open source text-to-speech libraries that supports multiple languages.

🟢 Github
🟢 Project
🟢 Docs

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

🎳 Supervision: reusable computer vision tools

Supervision - received another update.

This is an open source library for various computer vision tasks for object tracking.

Over 2000 commits, over 500 PRs and over 50 contributors.

pip install supervision

🏆 Github :
🏆 Project
🏆 Colab
🏆 Supervision Cookbooks

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

📝 Tutorial on survival modeling with applications to omics data

📕Journal: Bioinformatics (I.F.= 5.8)
🗓 Publish year: March, 2024

🧑‍💻Authors: Zhi Zhao, John Zobolas, Manuela Zucknick, Tero Aittokallio
➡️ University: University of Oslo - Oslo University Hospital, Norway

📎 Study the paper
🤓 Step-by-step R tutorial

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

🆗 One-Step Image Translation with Text-to-Image Models

CycleGAN-Turbo outperforms existing GAN and diffusion based methods for various image modification tasks, such as day to night conversion, adding/removing weather effects such as fog, snow and rain, etc.

💐 Paper : https://arxiv.org/abs/2403.12036

⭐️ Code : https://github.com/GaParmar/img2img-turbo

👍 Demo : http://huggingface.co/spaces/gparmar/img2img-turbo-sketch

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

🟢 FaceXFormer: Unified Face-Transformer

👉 FaceXFormer, the first unified transformer for facial analysis: face parsing, landmark detection, head pose, attributes recognition, age, gender, race, and landmarks.

👉 Review: https://t.ly/MfAFI

👉 Paper: https://arxiv.org/pdf/2403.12960.pdf

🤨 Project: kartik-3004.github.io/facexformer_web/

😏 Code: github.com/Kartik-3004/facexformer

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

[CVPR 2024] Diversity-aware Channel Pruning for StyleGAN Compression

🖥 Github: https://github.com/jiwoogit/dcp-gan

📕 Paper: https://arxiv.org/pdf/2403.13548v1.pdf

⭐️ Tasks: https://paperswithcode.com/task/image-generation

🔥Dataset: https://paperswithcode.com/dataset/ffhq

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

📃Machine Learning Empowering Drug Discovery: Applications, Opportunities and Challenges

📘 Journal: Molecules (I.F.= 4.6)
🗓 Publish year: 2024

🧑‍💻Authors: by Xin Qi,Yuanchun Zhao,Zhuang Qi,Siyu Hou,...
🏢University: Suzhou University of Science and Technology-Shandong University, China

📎 Study the paper

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

📢 𝐕𝐨𝐢𝐜𝐞𝐂𝐫𝐚𝐟𝐭: Zero-Shot Speech Editing and Text-to-Speech in the Wild🪄

SotA for both speech editing and text-to-speech, superior to VALL-E, XTTS-v 2, etc.

VoiceCraft works with movies, videos, podcasts, and more.

🟢 Github
🟢 Paper
🟢 Project

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

🦕 DINO-based Video Tracking 🦖

😏 The Weizmann Institute announced the new SOTA in point-tracking via pre-trained DINO features. Source code announced (not yet released)💙

😏 Revie:w https://t.ly/_GIMT

🤨 Paper: https://lnkd.in/dsGVDcar

🤨 Project: dino-tracker.github.io/

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

⚡️ StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control

Interactively generate images from scratch with detailed area control using text.

🧠 Code : https://github.com/ironjr/StreamMultiDiffusion

🧠 Paper : https://arxiv.org/abs/2403.09055

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

📄 Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges

🔖Journal: ACS Omega (I.F.= 4.1)
📅 Publish year: 2024

🧑‍💻Authors: Manoj Kumar Goshisht
💐University: University of Wisconsin-Green Bay, USA

📎 Study the paper

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

📃 A review on graph neural networks for predicting synergistic drug combinations

📕 Journal:  Artificial Intelligence Review (I.F=12)
🗓 Publish year: 2024

🧑‍💻Authors: Milad Besharatifard, Fatemeh Vafaee
👌 University: University of New South Wales (UNSW), Sydney, Australia

📎 Study the paper

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

❤️ LaVague: automate automation with Large Action Model framework

Model for generating selenium noscripts to automate Internet surfing, actions on websites and parsing 🔥

🌸 Github: https://github.com/lavague-ai/LaVague

🌸 Docs: https://docs.lavague.ai/en/latest/docs/

🌸 Colab: https://colab.research.google.com/github/lavague-ai/LaVague/blob/main/docs/docs/get-started/quick-tour.ipynb

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

H-SAM

🖥 Github: https://github.com/cccccczh404/h-sam

📕 Paper: https://arxiv.org/pdf/2403.18271v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/promise12

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

🌐 𝗠𝗮𝗷𝗼𝗿 𝗧𝗢𝗠: 𝗣𝗹𝗮𝗻𝗲𝘁 𝗘𝗮𝗿𝘁𝗵 𝗶𝘀 𝗯̶𝗹̶𝘂̶𝗲̶ 𝟱.𝟰𝟬𝟱 𝗚𝗛𝘇

MajorTom-Core-S1RTC is a new satellite image standard and dataset that contains 1,469,955 images.

16 TB of radiometrically calibrated images.

▪ HF: https://huggingface.co/Major-TOM
▪ Github: https://github.com/ESA-PhiLab/Major-TOM/
▪ Colab: https://colab.research.google.com/github/ESA-PhiLab/Major-TOM/blob/main/03-Filtering-in-Colab.ipynb
▪ Paper: https://www.arxiv.org/abs/2402.12095
▪ MajorTOM-Core-Viewer: https://huggingface.co/spaces/Major-TOM/MajorTOM-Core-Viewer

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

⭐️ DBRX, a groundbreaking open-source Large Language Model (LLM) with a staggering 132 billion parameters.

Databricks has just introduced DBRX, a new open source large language (LM) model with a staggering 132 billion parameters.

The model outperforms all open models on most benchmarks.

Here's what you need to know 👇

• DBRX is a new free artificial intelligence model with 132 billion parameters.
•Can process up to 32,000 tokens simultaneously.
•Trained on 12 trillion tokens.
•Follow instructions exactly.
•Open source on GitHub.
•Integrated with HuggingFace.
•Optimized for NVIDIA systems.
•Advanced configuration with Docker support.

🟠 Github: https://github.com/databricks/dbrx

🟠 HF: https://huggingface.co/databricks/dbrx-base

🟠 Demo: https://huggingface.co/spaces/databricks/dbrx-instruct

🟠 Docs: https://docs.databricks.com/en/machine-learning/foundation-models/index.html

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

🟠 DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing

Microsoft presents DesignEd it!

This is an image editing method that allows you to remove objects, swap objects, move them, resize them, add and flip multiple objects, make panoramas and scale images, remove objects from images.

🟠 Github: https://github.com/design-edit/DesignEdit.git

🟠 Paper: https://arxiv.org/abs/2403.14487

🟠 Project: https://design-edit.github.io/

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

🔥Unbounded 3D City Generation🔥

🏙️ CityDreamer 🏙️ compositional generative model for creating full-fledged 3D cities.

▪ Project : https://infinitenoscript.com/project/city-dreamer/
▪ Code : https://github.com/hzxie/CityDreamer
▪ Demo : https://huggingface.co/spaces/hzxie/

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

SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations

🖥 Github: https://github.com/divelab/AIRS

📕 Paper: https://arxiv.org/abs/2403.19507v1

🔥Project: www.air4.science/
Resources

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