ML Research Hub
32.6K subscribers
3.39K photos
133 videos
23 files
3.62K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho
Download Telegram
🌉Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution

Experiments demonstrate that our method achieves a PSNR of 30.72dB, outperforming state-of-the-art methods by 14
on GTA5 nighttime haze dataset.

🖥 Github: https://github.com/jinyeying/nighttime_dehaze/tree/main

📕 Paper: https://arxiv.org/abs/2308.01738v1

☑️ Dataset: https://www.dropbox.com/sh/7qzmb3y9akejape/AABYf2ZAqn_5vmPsOPg7KqoMa?dl=0

https://t.iss.one/DataScienceT
Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

🖥 Github: https://github.com/bytedance/dq-det

📕 Paper: https://arxiv.org/pdf/2307.12239v1.pdf

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

https://t.iss.one/DataScienceT
👍1
5👍2
🚀 AgentBench: Evaluating LLMs as Agents.

AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting.

🖥 Github: https://github.com/thudm/agentbench

📕 Paper: https://arxiv.org/abs/2308.03688v1

☑️ Dataset: https://paperswithcode.com/dataset/alfworld

https://t.iss.one/DataScienceT
👍31
EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms

🖥 Github: https://github.com/DSL-Lab/echoglad

📕 Paper: https://arxiv.org/pdf/2307.12229v1.pdf

https://t.iss.one/DataScienceT
Revisiting the Minimalist Approach to Offline Reinforcement Learning

🖥 Github: https://github.com/tinkoff-ai/rebrac

📕 Paper: https://arxiv.org/pdf/2305.09836v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/d4rl

https://t.iss.one/DataScienceT
👍31
🔥Platypus: Quick, Cheap, and Powerful Refinement of LLMs

Family of fine-tuned and merged LLMs that achieves the strongest performance and currently stands at first place in HuggingFace's

git clone https://github.com/lm-sys/FastChat.git
cd FastChat

🖥 Github: https://github.com/arielnlee/Platypus

💻 Project: https://platypus-llm.github.io/

📕 Paper: https://arxiv.org/abs/2308.07317v1

⭐️ Dataset: https://huggingface.co/datasets/garage-bAInd/Open-Platypus

https://t.iss.one/DataScienceT
👍3
Forwarded from Machine Learning
Encyclopedia of Data Science and Machine Learning (2023)

This book was released two days ago and this book is more than 3400 pages.

With this book, you can become a first-class professional data scientist

The price of the book is $3,400

To get a discount of up to 95%, contact me immediately

Contact @hussein_sheikho
👍8👎4🏆1
This media is not supported in your browser
VIEW IN TELEGRAM
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

EasyEdit, demonstrating that knowledge editing surpasses traditional fine-tuning in terms of reliability and generalization.

🖥 Github: https://github.com/zjunlp/easyedit

📕 Paper: https://arxiv.org/abs/2308.07269v1

⭐️ Demo: https://knowlm.zjukg.cn/demo_edit

🎓Online Tutorial: https://colab.research.google.com/drive/1zcj8YgeqttwkpfoHXz9O9_rWxFFufXSO?usp=sharing

☑️ Docs: https://zjunlp.gitbook.io/easyedit

🤓 Dataset: https://drive.google.com/file/d/1IVcf5ikpfKuuuYeedUGomH01i1zaWuI6/view?usp=sharing

https://t.iss.one/DataScienceT
👍41
🧑‍💻DeciCoder: A new open-source LLM, specialized for generating code in Python, Java, and Javascript..

- parameters: 1 B
- dataset: 'The Stack' dataset
- supports: Python, Javascript, Java
- context: 2048 tokens

Model
Colab
Dataset

https://t.iss.one/DataScienceT
👍52
✔️ DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching

🖥 Github: https://github.com/parskatt/dedode

☑️ TensorRT: https://github.com/fabio-sim/DeDoDe-ONNX-TensorRT

📕 Paper: https://arxiv.org/abs/2308.08479

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

https://t.iss.one/DataScienceT
👍21
❤‍🔥1👍1