💍 OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

▪Dataset: https://huggingface.co/datasets/nvidia/OpenMathInstruct-1

▪Paper: https://huggingface.co/papers/2402.10176

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

🤖 Learning to Learn Faster from Human Feedback with Language Model Predictive Control

▪proj: https://robot-teaching.github.io

▪paper: https://arxiv.org/abs/2402.11450

🔐 code: https://colab.research.google.com/drive/1YcRN_kklw3cVVJNvgK_IEV6nDce9EJWK

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

PDD: Positional Discourse Divergence

🖥 Github: https://github.com/williamlyh/pos_div_metric

📕 Paper: https://arxiv.org/pdf/2402.10175v1.pdf

💔 Dataset: https://paperswithcode.com/dataset/recipe1m-1

✨ Tasks: https://paperswithcode.com/task/coherence-evaluation

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

📄 Drug-drug interactions prediction based on deep learning and knowledge graph: a review

🗓 Journal: IScience (I.F.=5.8)
🗓 Publish year: 2024

🧑‍💻 Authors: Huimin Luo, Weijie Yin, Jianlin Wang, ...

📎 Study the paper

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

💐 Neuromorphic Video Binarization

🤨 University of HK unveils the new SOTA in event-based neuromorphic binary reconstruction: stunning results on QR Code, barcode, & Text. Real-Time, only CPU, up to 10,000 FPS!

👉 Review: https://t.ly/V-NFa

👉 Paper: arxiv.org/pdf/2402.12644.pdf

😏 Project: github.com/eleboss/EBR

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

🔝 ByteDance presents SDXL-Lightning: a lightning fast 1024px text-to-image generation model

☄️ HF: https://huggingface.co/ByteDance/SDXL-Lightning

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

📁 Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directions

🗓 Publish year: 2023

🫥 Authors: Fang Li, Yi Nian, Zenan Sun, Cui Tao

📎 Study the paper

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

💎 Visually Dehallucinative Instruction Generation: Know What You Don't Know

🍏 Github: https://github.com/ncsoft/idk

📕 Paper: https://arxiv.org/pdf/2402.09717v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/visual-question-answering

⭐ Tasks: https://paperswithcode.com/task/hallucination

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

SOTA🚀 YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

☄️ Github
☄️ Paper
☄️ Hugging face

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

👺 Pose via Ray Diffusion 😻

🤨 Novel distributed representation of camera pose that treats a camera as a bundle of rays. Naturally suited for set-level transformers, it's the new SOTA on camera pose estimation. Source code released 📱

👉 Review: https://t.ly/qBsFK

🥺 Paper: arxiv.org/pdf/2402.14817.pdf

👉Project: jasonyzhang.com/RayDiffusion

👉 Code: github.com/jasonyzhang/RayDiffusion

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

⭐ MATH-Vision Dataset 🕹

😏 MATH-V is a curated dataset of 3,040 HQ mat problems with visual contexts sourced from real math competitions. Dataset released 📱

😏 Review: https://t.ly/gmIAu

🤨 Paper: arxiv.org/pdf/2402.14804.pdf

🥺 Project: mathvision-cuhk.github.io/

👉 Code: github.com/mathvision-cuhk/MathVision

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

📄 Graph-Theoretical Analysis of Biological Networks: A Survey

🗓 Publish year: 2023

🧑‍💻Author: Kayhan Erciyes

📎 Study the paper

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

​​😶‍🌫️ DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

🖥 Github: https://github.com/deepseek-ai/deepseek-math

📚 Paper: https://arxiv.org/abs/2402.03300v1

🗣 Dataset: https://paperswithcode.com/dataset/math

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

Energy-Time-series-anomaly-detection

⛓ Github: https://github.com/HardikPrabhu/Energy-Time-series-anomaly-detection

🔖 Paper: https://arxiv.org/pdf/2402.14384v1.pdf

✨ Tasks: https://paperswithcode.com/task/anomaly-detection

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

🎓 Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot.

Multi-HMR is a simple but powerful model that takes an RGB image as input and performs 3D-reconstruction of multiple people in space.

👑 Github

💍 Paper

🐻 Dataset

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

​​🧠 EasyVolcap: Accelerating Neural Volumetric Video Research

🧑‍💻 Code: https://github.com/zju3dv/easyvolcap

👩‍🎨 Metrics: https://short.llm360.ai/amber-metrics

🌹 Paper: https://arxiv.org/abs/2312.06575v1

👀 Dataset: https://paperswithcode.com/dataset/nerf

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

😀 OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on.

🤡 Github: https://github.com/levihsu/OOTDiffusion

👻 Demo: https://ootd.ibot.cn

😀 Jupyter: https://github.com/camenduru/OOTDiffusion-jupyter

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

🔒 Graph Diffusion Policy Optimization

🧑‍💻 Github: https://github.com/sail-sg/gdpo

📕 Paper: https://arxiv.org/pdf/2402.16302v1.pdf

💔 Dataset: https://paperswithcode.com/dataset/zinc

✨ Tasks: https://paperswithcode.com/task/graph-generation

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

DCVSMNet: Double Cost Volume Stereo Matching Network

🖥 Github: https://github.com/m2219/dcvsmnet

⚙️ Paper: https://arxiv.org/pdf/2402.16473v1.pdf

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

⭐️ Tasks: https://paperswithcode.com/task/stereo-matching-1

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

🔥 New free course: Prompt Engineering with Llama 2 from Andrew YNg and and DeepLearning.AI

Llama 2 has become a very important model for the entire AI world.

Llama is not one model, but a whole collection of models. In this course you will learn: - Learn the differences between the different types of Llama 2 and when to use each one.

⭐️ You'll also learn how prompt tags for Llama work - how they can help you with everyday tasks.

⭐️ Learn to use advanced prompts, such as multiple screenshot prompts for classification or chain-of-thought prompts for solving logic problems.

😡 Learn to use specialized models from the Llama collection to solve specific problems, such as Code Llama, which helps you write, analyze and improve code, and Llama Guard , which checks model prompts and responses for malicious content.

The course also covers how to run Llama 2 locally on your own computer.

📌 https://deeplearning.ai/short-courses/prompt-engineering-with-llama-2

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

⏺ZHEM: An Integrated Data Processing Framework for Pretraining Foundation Models

🖥 Github: https://github.com/emanual20/zhem

💤 Paper: https://arxiv.org/pdf/2402.16358v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/wikitext-2

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