LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

🖥 Github: https://github.com/dvlab-research/longlora

📕 Paper: https://arxiv.org/pdf/2309.12307v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/pg-19

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

Do you enjoy reading this channel?

Perhaps you have thought about placing ads on it?

To do this, follow three simple steps:

1) Sign up: https://telega.io/c/dataScienceT
2) Top up the balance in a convenient way
3) Create an advertising post

If the topic of your post fits our channel, we will publish it with pleasure.

🔊 Listen, Think, and Understand

AI model that has both audio perception and a reasoning ability

🖥 Github: https://github.com/YuanGongND/ltu

☑️ Demo: https://18c618fc8f07ec494e.gradio.live/

📕 Paper: https://arxiv.org/abs/2309.14405v1

🤗 HH: https://huggingface.co/spaces/yuangongfdu/ltu-2

⭐️ Dataset: https://paperswithcode.com/dataset/iemocap

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

🤖 Machine Learning Tutorials Repository

1. Python
2. Computer Vision: Techniques, algorithms
3. NLP
4. Matplotlib
5. NumPy
6. Pandas
7. MLOps
8. LLMs
9. PyTorch/TensorFlow

git clone https://github.com/patchy631/machine-learning

🔗 GitHub: https://github.com/patchy631/machine-learning/tree/main

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

Total interactions required: 20 👍

⭐️ Decaf: 3D Face-Hand Interactions

⭐️ The first learning-based MoCap to track human hands interacting with human faces in #3D from single monocular RGB videos

🔗 Review: https://t.ly/070Tj

🔗 Paper: arxiv.org/pdf/2309.16670.pdf

🔗 Project: vcai.mpi-inf.mpg.de/projects/Decaf

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

🔊 Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

git clone git@github.com:guyyariv/TempoTokens.git

🖥 Github: https://github.com/guyyariv/TempoTokens

📕 Paper: https://arxiv.org/abs/2309.16429v1

⭐️ Dataset: https://paperswithcode.com/dataset/audioset

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

The future is already here, and it's scary!
Today we can become half cyborgs, print food on a 3d printer, and live in a revolving skyscraper. It's real!
Tomorrow Technology shows the latest innovations that will take your breath away!
Stay tuned by subscribing to the channel to get the latest news from the world of technology!
Link to the channel: Tomorrow Technology 

☑️ IBM Free course: Python Basics for Data Science

Course Link: https://www.edx.org/learn/python/ibm-python-basics-for-data-science

⭐️ https://news.1rj.ru/str/CodeProgrammer

🦅 Jury: A Comprehensive Evaluation Toolkit

pip install jury

🖥 Github: https://github.com/obss/jury

📕 Paper: https://arxiv.org/abs/2310.02040v1

🖥 Colab: https://colab.research.google.com/github/obss/jury/blob/main/examples/jury_evaluate.ipynb

⭐️ Demos: https://github.com/Parskatt/DeDoDe/blob/main/demo

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

⚡️ Memory Gym: Partially Observable Challenges to Memory-Based Agents in Endless Episodes

🖥 Github: https://github.com/marcometer/endless-memory-gym

🖥 Colab: https://colab.research.google.com/drive/1LjlUOEer8vjGrz0rLM8pP5UyeNCsURkY?usp=sharing

📕 Paper: https://openreview.net/forum?id=jHc8dCx6DDr

⭐️ Dataset: https://paperswithcode.com/dataset/arcade-learning-environment

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

🔊 Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

git clone git@github.com:guyyariv/TempoTokens.git

🖥 Github: https://github.com/guyyariv/TempoTokens

📕 Paper: https://arxiv.org/abs/2309.16429v1

⭐️ Dataset: https://paperswithcode.com/dataset/audioset

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

✅️ T3Bench: Benchmarking Current Progress in Text-to-3D Generation

🖥 Github: https://github.com/THU-LYJ-Lab/T3Bench

📕 Paper: https://arxiv.org/abs/2310.02977v1

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

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