ML Research Hub – Telegram
ML Research Hub
32.8K subscribers
4.34K photos
264 videos
23 files
4.69K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 Title: DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion

🔹 Publication Date: Published on Oct 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15264
• PDF: https://arxiv.org/pdf/2510.15264

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
2
🤖🧠 NanoChat: The Best ChatGPT That $100 Can Buy

🗓️ 20 Oct 2025
📚 AI News & Trends

In a world dominated by billion-dollar AI models like GPT-4 and Claude 3, it’s refreshing to see a minimalist, open-source alternative that puts the power of Large Language Models (LLMs) back into the hands of hackers, researchers and enthusiasts. Enter NanoChat – an end-to-end, full-stack implementation of a ChatGPT-style AI chatbot developed by Andrej Karpathy, ...

#NanoChat #ChatGPT #AI #LargeLanguageModels #OpenSource #AndrejKarpathy
🤖🧠 PaddleOCR-VL: Redefining Multilingual Document Parsing with a 0.9B Vision-Language Model

🗓️ 20 Oct 2025
📚 AI News & Trends

In an era where information is predominantly digital, the ability to extract, interpret and organize data from documents is crucial. From invoices and research papers to multilingual contracts and handwritten notes, document parsing stands at the intersection of vision and language. Traditional Optical Character Recognition (OCR) systems have made impressive strides but they often fall ...

#PaddleOCR-VL #Multilingual #DocumentParsing #VisionLanguageModel #OCR #AI
🔹 Title: Do LLMs "Feel"? Emotion Circuits Discovery and Control

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11328
• PDF: https://arxiv.org/pdf/2510.11328
• Github: https://github.com/Aurora-cx/EmotionCircuits-LLM

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🤖🧠 Top 30 More Retro Bollywood Diwali Portrait Prompts for Women Using Gemini AI – Part 2

🗓️ 20 Oct 2025
📚 AI News & Trends

The Diwali celebrations continue and so does the nostalgia! After the huge buzz around our Top 20 Retro Bollywood Diwali Portrait Ideas, we’re back with Part 2 featuring prompts 21 to 50 curated to help you create even more magical, cinematic AI portraits using Google Gemini AI. If you loved the 90s-style Diwali aesthetics shimmering ...
🔹 Title: Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

🔹 Publication Date: Published on Oct 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.14630
• PDF: https://arxiv.org/pdf/2510.14630
• Github: https://github.com/CompVis/RepTok

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16872
• PDF: https://arxiv.org/pdf/2510.16872
• Project Page: https://ruc-deepanalyze.github.io/
• Github: https://github.com/ruc-datalab/DeepAnalyze

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17354
• PDF: https://arxiv.org/pdf/2510.17354

🔹 Datasets citing this paper:
https://huggingface.co/datasets/SnowNation/NyxQA

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: PICABench: How Far Are We from Physically Realistic Image Editing?

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17681
• PDF: https://arxiv.org/pdf/2510.17681
• Project Page: https://picabench.github.io/
• Github: https://picabench.github.io/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Executable Knowledge Graphs for Replicating AI Research

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17795
• PDF: https://arxiv.org/pdf/2510.17795

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: ConsistEdit: Highly Consistent and Precise Training-free Visual Editing

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17803
• PDF: https://arxiv.org/pdf/2510.17803
• Project Page: https://zxyin.github.io/ConsistEdit
• Github: https://github.com/zxYin/ConsistEdit_Code

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: FineVision: Open Data Is All You Need

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17269
• PDF: https://arxiv.org/pdf/2510.17269
• Project Page: https://huggingface.co/spaces/HuggingFaceM4/FineVision

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16751
• PDF: https://arxiv.org/pdf/2510.16751

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16720
• PDF: https://arxiv.org/pdf/2510.16720
• Project Page: https://github.com/ADaM-BJTU/model-native-agentic-ai
• Github: https://github.com/ADaM-BJTU/model-native-agentic-ai

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17797
• PDF: https://arxiv.org/pdf/2510.17797
• Github: https://huggingface.co/papers?q=github

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Deep Self-Evolving Reasoning

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17498
• PDF: https://arxiv.org/pdf/2510.17498

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training

🔹 Publication Date: Published on Oct 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15527
• PDF: https://arxiv.org/pdf/2510.15527

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

🔹 Publication Date: Published on Oct 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.14605
• PDF: https://arxiv.org/pdf/2510.14605

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning

🔹 Publication Date: Published on Oct 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16156
• PDF: https://arxiv.org/pdf/2510.16156

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Glyph: Scaling Context Windows via Visual-Text Compression

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17800
• PDF: https://arxiv.org/pdf/2510.17800

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT