ML Research Hub – Telegram
ML Research Hub
@DataScienceT
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
About
Blog
Apps
Platform
Join
ML Research Hub
32.7K subscribers
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
⚡️ LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

🖥 Github: https://github.com/3DTopia/LGM

📚 Paper: https://arxiv.org/abs/2402.05054

🔗 Demo: https://huggingface.co/spaces/ashawkey/LGM

💻 Weights: https://huggingface.co/ashawkey/LGM

⏩ Project: https://me.kiui.moe/lgm/

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍5
3.33K views
ML Research Hub
🦾 Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

🖥 Github: https://github.com/uclaml/SPIN

📚 Paper: https://arxiv.org/abs/2401.01335

⏩ Project: https://uclaml.github.io/SPIN/

💻 Model: https://huggingface.co/collections/UCLA-AGI/zephyr-7b-sft-full-spin-65c361dfca65637272a02c40

🛡 Dataset: https://huggingface.co/collections/UCLA-AGI/datasets-spin-65c3624e98d4b589bbc76f3a

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍4
3.59K views
ML Research Hub
SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels

🖥 Github: https://github.com/IIPL-CAU/SoftEDA

📕 Paper: https://arxiv.org/pdf/2402.05591v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/cola

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍2
3.52K viewsedited  
ML Research Hub
EasyKV

🖥 Github: https://github.com/drsy/easykv

📕 Paper: https://arxiv.org/pdf/2402.06262v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/webtext

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍3
3.39K viewsedited  
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
👁️ HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

🖥 Github: https://github.com/Shengcao-Cao/HASSOD

📚 Paper: https://arxiv.org/abs/2402.03311

⏩ Project: https://hassod-neurips23.github.io/

💻 Video: https://www.youtube.com/watch?v=s8u7tEKg5ew

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍3
3.5K views
ML Research Hub
Leveraging SAM for Single-Source Domain Generalization in Medical Image Segmentation

📄 https://arxiv.org/pdf/2401.02076.pdf

💻 https://github.com/SARIHUST/SAMMed

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍3
3.33K viewsedited  
ML Research Hub
🧠 SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures

▪Paper: https://arxiv.org/pdf/2402.03620.pdf

▪LangChain example: https://github.com/langchain-ai/langchain/blob/master/cookbook/self-discover.ipynb

▪LangGraph example: https://github.com/langchain-ai/langgraph/blob/main/examples/self-discover/self-discover.ipynb

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍4
4.26K views
ML Research Hub
SQ-Transformer: Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

🖥 Github: https://github.com/jiangyctarheel/sq-transformer

📕 Paper: https://arxiv.org/pdf/2402.06492v1.pdf

🔥Datasets: https://paperswithcode.com/dataset/wmt-2014

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍2
3.64K viewsedited  
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
⚡️ Magic-Me: Identity-Specific Video Customized Diffusion.

▪Github: https://github.com/Zhen-Dong/Magic-Me

▪Colab: https://colab.research.google.com/drive/1gMialn4nkGeDZ72yx1Wob1E1QBgrqeGa

▪Project: https://magic-me-webpage.github.io

▪Paper: arxiv.org/abs/2402.09368

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
3.53K views
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
⚡️ V-JEPA: The next step toward Yann LeCun’s vision of advanced machine intelligence (AMI)

▪Github: https://github.com/facebookresearch/jepa

▪Paper: https://ai.meta.com/research/publications/revisiting-feature-prediction-for-learning-visual-representations-from-video/

▪Blog: https://ai.meta.com/blog/v-jepa-yann-lecun-ai-model-video-joint-embedding-predictive-architecture/

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
👍5
3.39K viewsedited  
ML Research Hub
MIM-Refiner

🖥 Github: https://github.com/ml-jku/MIM-Refiner

🔖 Paper: https://arxiv.org/pdf/2402.10093v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/imagenet

✨ Tasks: https://paperswithcode.com/task/image-clustering

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
Please open Telegram to view this post
VIEW IN TELEGRAM
👍4
3.89K viewsedited  
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
💃 MagicDance: Realistic Human Dance

Video Generation with Motions & Facial Expressions Transfer.

🔔 page: https://boese0601.github.io/magicdance/

➕ paper: https://arxiv.org/abs/2311.12052

➕ code: https://github.com/Boese0601/MagicDance

📝jupyter: https://github.com/camenduru/MagicDance-jupyter

🌐 Telegram: https://news.1rj.ru/str/DataScienceT
Please open Telegram to view this post
VIEW IN TELEGRAM
👍4❤1
3.95K viewsedited  
ML Research Hub
TIA Toolbox

🖥 Github: https://github.com/tissueimageanalytics/tiatoolbox

📕 Paper: https://arxiv.org/pdf/2402.09990v1.pdf

✨ Tasks: https://paperswithcode.com/task/whole-slide-images

🟢 Telegram: https://news.1rj.ru/str/DataScienceT
3.55K viewsedited  
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
💍 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
Please open Telegram to view this post
VIEW IN TELEGRAM
👍4
3.54K viewsedited  
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
🤖 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
Please open Telegram to view this post
VIEW IN TELEGRAM
👍2
3.3K viewsedited  
ML Research Hub
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
Please open Telegram to view this post
VIEW IN TELEGRAM
👍4❤‍🔥3
3.42K viewsedited  
ML Research Hub
📄 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
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1❤‍🔥1👍1
3.07K viewsedited  
ML Research Hub
This media is not supported in your browser
VIEW IN TELEGRAM
💐 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
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3❤‍🔥1
3.26K viewsedited  
ML Research Hub
🔝 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
Please open Telegram to view this post
VIEW IN TELEGRAM
👍6❤2🏆1
3.19K views