ML Research Hub – Telegram
ML Research Hub
32.7K subscribers
4.01K photos
229 videos
23 files
4.32K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🌆Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback

🖥 Github: https://github.com/tetrzim/diffusion-human-feedback

Paper: https://arxiv.org/pdf/2307.02770v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/imagenet

https://news.1rj.ru/str/DataScienceT
4👍2
FLASK: Fine-grained Language Model Evaluation Based on Alignment Skill Sets

🖥 Github: https://github.com/kaistai/flask

Paper: https://arxiv.org/pdf/2307.10928v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/gsm8k

https://news.1rj.ru/str/DataScienceT
4
A special bot is available to download any book you want without waiting for it to be published here in the channel. The bot contains 30 million books or more and all books are in PDF and other format.

Contact @hussein_sheikho

Price: 9$ forever
👍51👎1
🐋 FreeWilly, Large And Mighty Instruction Fine-Tuned Models
.
FreeWilly1 and FreeWilly2 set a new standard in the field of open access Large Language Models.

⭐️ Post: https://stability.ai/blog/freewilly-large-instruction-fine-tuned-models

📌 FreeWilly1: https://huggingface.co/stabilityai/FreeWilly1-Delta-SafeTensor

📌 FreeWilly2: https://huggingface.co/stabilityai/FreeWilly1-Delta-SafeTensor

https://news.1rj.ru/str/DataScienceT
👍31
↗️ L-Eval: Instituting Standardized Evaluation for Long Context Language Models

Data and code for L-Eval, a comprehensive long context language models evaluation benchmark.

🖥 Github: https://github.com/bshall/urhythmic

🧑‍💻Model: https://huggingface.co/datasets/L4NLP/LEval

📕 Paper: https://arxiv.org/abs/2307.11088

🚀 Dataset: https://paperswithcode.com/dataset/quality

https://news.1rj.ru/str/DataScienceT
👍31
⭐️ CNOS: A Strong Baseline for CAD-based Novel Object Segmentation

Three-stage approach to segment unseen objects in RGB images using their CAD models.

🖥 Github: https://github.com/nv-nguyen/cnos

📕 Paper: http://arxiv.org/abs/2307.11067

🚀 Dataset: https://bop.felk.cvut.cz/datasets/

https://news.1rj.ru/str/DataScienceT
👍1
❤‍🔥3👍3🏆3
🗣 DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI.

🖥 Github: https://github.com/salesforce/DialogStudio

📕 Paper: https://arxiv.org/abs/2307.10172v2

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

https://news.1rj.ru/str/DataScienceT
👍42
Kaggle is one of the goto platforms for Machine Learning

Here's how to use it to it's maximum potential 💯

{ Explore Learn Section }
kaggle.com/learn

{ Explore Datasets }
kaggle.com/datasets

{ Explore Challenges}
kaggle.com/competitions

{ Learn By Building }
kaggle.com/code

{ Seek & Give Help }
kaggle.com/discussion

https://news.1rj.ru/str/DataScienceT
👍106
Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis

🖥 Github: https://github.com/ha0tang/ecgan

📕 Paper: https://arxiv.org/abs/2307.12084v1

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

https://news.1rj.ru/str/DataScienceT
Remote Bio-Sensing: Open Source Benchmark Framework for Fair Evaluation of rPPG

🖥 Github: https://github.com/remotebiosensing/rppg

📕 Paper: https://arxiv.org/abs/2307.12644v1

🔥 Dataset: https://paperswithcode.com/dataset/ubfc-rppg

https://news.1rj.ru/str/DataScienceT
👍5
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition (ICCV 2023)

🖥 Github: https://github.com/Shilin-LU/TF-ICON

📕 Paper: https://arxiv.org/abs/2307.12644v1

🔥 Dataset: https://paperswithcode.com/dataset/ubfc-rppg

https://news.1rj.ru/str/DataScienceT
👍5
ANNOUNCING SDXL 1.0

The Stability AI team is proud to release as an open model SDXL 1.0, the next iteration in the evolution of text-to-image generation models.

💫 Announcement: https://stability.ai/blog/stable-diffusion-sdxl-1-announcement

🖥 Github: https://github.com/Stability-AI/generative-models

⭐️ Clip: https://clipdrop.co/stable-diffusion

https://news.1rj.ru/str/DataScienceT
👍41
🚀 Even students earn $100 per day!

10 years ago the Bitcoin costed only 10 cents, and today it’s $55k. Everyone who invested then $10 already became a millionaire. 💰

Since the beginning of autumn the cryptocurrency has grown up in 3-4 times and it’s just a beginning. Don’t miss the opportunities!

Right now the founder of the biggest channel on this theme @CoinPost opens access to a private channel, where he shows the ways to earn thousands dollars on cryptocurrency.

Subscribe or you’ll miss your chance to become rich. 👇

https://news.1rj.ru/str/+if7bANKpX_5hYjgy
👍31