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
📃Graph Machine Learning in the Era of Large Language Models (LLMs)

🗓 Publish year: 2023

🧑‍💻Authors: Wenqi Fan, Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li

🏢Universities: The Hong Kong Polytechnic University,Michigan State University, North Carolina State University

📎  Study the paper
👍3
Acquired global fresh database Please send me a sample Scammer please don't waste your time @yuefu666
⭐️ The PyTorch team is developing a library for learning LLM called torch titan.

Today the library has become publicly available on GitHub, but it is still in a pre-release state and is actively being developed.

- Library link: https://github.com/pytorch/torchtitan

- Tutorial on working with torch titan: https://www.youtube.com/watch?v=ee5DOEqD35I

The library was created for preliminary training of models, and for fine tuning PyTorch has another library, torchtune:
https://github.com/pytorch/torchtune

https://news.1rj.ru/str/DataScienceT ⚙️
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
👍6❤‍🔥31🏆1
MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition

🖥 Github: https://github.com/zeroqiaoba/mertools

📕 Paper: https://arxiv.org/abs/2404.17113v1

🔥 Dataset: https://paperswithcode.com/dataset/voxceleb2


https://news.1rj.ru/str/DataScienceT 💋
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3
⚡️ Arena-Hard is an evaluation tool for instruction-tuned LLMs.

Arena-Hard - Creating High Quality Tests for LLM Assessment

Arena-Hard allows you to evaluate LLM responses using 7 specific metrics; criteria in the image

▶️ More about Arena-Hard
🖥 GitHub

https://news.1rj.ru/str/DataScienceT 💋
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
👍5❤‍🔥1
India's Largest Free Webinar on LLMs especially focused on the recently released LLAMA-3 by Meta.

How do you use these models?
How can you create apps with them?

Join our free workshop on to learn how to use Llama 3 and create apps with it.

Register here: https://www.buildfastwithai.com/events/llama-3-deep-dive

You can connect with Founder;
https://www.linkedin.com/in/satvik-paramkusham/

This Event is especially designed for people interested in the field of AI, ML, GenAI & LLMs.
👍3
RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation

🖥 Github: https://github.com/hmorimitsu/ptlflow

📕 Paper: https://hmorimitsu.com/publication/2024-icra-rapidflow/

⚡️ Dataset: https://paperswithcode.com/dataset/kitti
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
1
They predicted yesterday the DUMP of Bitcoin
Already in the channel published the dates of the next BTC PUMP!

Click 👉 CHECK NEXT PUMP DATES 👈
Click 👉 CHECK NEXT PUMP DATES 👈
Click 👉 CHECK NEXT PUMP DATES 👈

JOIN FAST! Only the first 1000 people will be accepted! 🔥
Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

🖥 Github: https://github.com/wangkai930418/DPL

📕 Paper: https://arxiv.org/abs/2405.01496v1

🔥 Dataset: https://neurips.cc/virtual/2023/poster/72801
Please open Telegram to view this post
VIEW IN TELEGRAM
👍5
Distillation for Multilingual Information Retrieval

🖥 Github: https://github.com/hltcoe/colbert-x

📕 Paper: https://arxiv.org/abs/2405.00977v1

🔥Docs: pypi.org/project/PLAID-X/
Please open Telegram to view this post
VIEW IN TELEGRAM
👍2
⚡️ Finetuning for Text Classification

If you're looking for something to do this weekend and want to do a little reading and coding, here's the latest chapter from the book Build an LLM from Scratch , on setting up a GPT model to classify SPAM messages with up to 96% accuracy.

The model is small and training on a MacBook Air M3 takes ~ 5 minutes.

Github

https://news.1rj.ru/str/DataScienceT ✅️
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3
The time for altcoins is coming soon, many coins are set to give 10-20x returns.

2024 is the year of the bull run, with clear confirmations you'll be briefed on here — https://news.1rj.ru/str/+oVU9m7RyePFmYWYy

Crypto Baron provides daily market analysis and coins projected to generate hundreds of percent in profit this year!
👉🏼Subscribe
👍1