ML Research Hub
32.8K subscribers
4.31K photos
260 videos
23 files
4.66K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
πŸ”Ή Title: A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

πŸ”Ή Publication Date: Published on Oct 17

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.15444
β€’ PDF: https://arxiv.org/pdf/2510.15444
β€’ Project Page: https://zhouz.dev/RPC/
β€’ Github: https://github.com/WNJXYK/RPC/

πŸ”Ή Datasets citing this paper:
β€’ https://huggingface.co/datasets/WNJXYK/MathOdyssey-Reasoning-Paths
β€’ https://huggingface.co/datasets/WNJXYK/AIME_1983_2024-Reasoning-Paths
β€’ https://huggingface.co/datasets/WNJXYK/OlympiadBench-Reasoning-Paths
β€’ https://huggingface.co/datasets/WNJXYK/MATH-Reasoning-Paths

πŸ”Ή Spaces citing this paper:
β€’ https://huggingface.co/spaces/WNJXYK/RPC
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
❀1
πŸ”Ή Title: DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion

πŸ”Ή Publication Date: Published on Oct 17

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.15264
β€’ PDF: https://arxiv.org/pdf/2510.15264

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
❀2
πŸ€–πŸ§  NanoChat: The Best ChatGPT That $100 Can Buy

πŸ—“οΈ 20 Oct 2025
πŸ“š 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
πŸ€–πŸ§  PaddleOCR-VL: Redefining Multilingual Document Parsing with a 0.9B Vision-Language Model

πŸ—“οΈ 20 Oct 2025
πŸ“š 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
πŸ”Ή Title: Do LLMs "Feel"? Emotion Circuits Discovery and Control

πŸ”Ή Publication Date: Published on Oct 13

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.11328
β€’ PDF: https://arxiv.org/pdf/2510.11328
β€’ Github: https://github.com/Aurora-cx/EmotionCircuits-LLM

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ€–πŸ§  Top 30 More Retro Bollywood Diwali Portrait Prompts for Women Using Gemini AI – Part 2

πŸ—“οΈ 20 Oct 2025
πŸ“š 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 ...
πŸ”Ή Title: Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

πŸ”Ή Publication Date: Published on Oct 16

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.14630
β€’ PDF: https://arxiv.org/pdf/2510.14630
β€’ Github: https://github.com/CompVis/RepTok

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

πŸ”Ή Publication Date: Published on Oct 19

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.16872
β€’ PDF: https://arxiv.org/pdf/2510.16872
β€’ Project Page: https://ruc-deepanalyze.github.io/
β€’ Github: https://github.com/ruc-datalab/DeepAnalyze

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17354
β€’ PDF: https://arxiv.org/pdf/2510.17354

πŸ”Ή Datasets citing this paper:
β€’ https://huggingface.co/datasets/SnowNation/NyxQA

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: PICABench: How Far Are We from Physically Realistic Image Editing?

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17681
β€’ PDF: https://arxiv.org/pdf/2510.17681
β€’ Project Page: https://picabench.github.io/
β€’ Github: https://picabench.github.io/

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Executable Knowledge Graphs for Replicating AI Research

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17795
β€’ PDF: https://arxiv.org/pdf/2510.17795

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: ConsistEdit: Highly Consistent and Precise Training-free Visual Editing

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17803
β€’ PDF: https://arxiv.org/pdf/2510.17803
β€’ Project Page: https://zxyin.github.io/ConsistEdit
β€’ Github: https://github.com/zxYin/ConsistEdit_Code

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense

πŸ”Ή Publication Date: Published on Oct 17

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.16259
β€’ PDF: https://arxiv.org/pdf/2510.16259

πŸ”Ή Datasets citing this paper:
β€’ https://huggingface.co/datasets/groupfairnessllm/tulu-3-preference-data-with-distraction
β€’ https://huggingface.co/datasets/groupfairnessllm/tulu-3-sft-personas-instruction-following-with-distraction
β€’ https://huggingface.co/datasets/groupfairnessllm/tulu-3-preference-personas-math-with-distraction
β€’ https://huggingface.co/datasets/groupfairnessllm/tulu-3-preference-personas-instruction-following-with-distraction

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: FineVision: Open Data Is All You Need

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17269
β€’ PDF: https://arxiv.org/pdf/2510.17269
β€’ Project Page: https://huggingface.co/spaces/HuggingFaceM4/FineVision

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling

πŸ”Ή Publication Date: Published on Oct 19

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.16751
β€’ PDF: https://arxiv.org/pdf/2510.16751

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI

πŸ”Ή Publication Date: Published on Oct 19

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.16720
β€’ PDF: https://arxiv.org/pdf/2510.16720
β€’ Project Page: https://github.com/ADaM-BJTU/model-native-agentic-ai
β€’ Github: https://github.com/ADaM-BJTU/model-native-agentic-ai

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17797
β€’ PDF: https://arxiv.org/pdf/2510.17797
β€’ Github: https://huggingface.co/papers?q=github

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Deep Self-Evolving Reasoning

πŸ”Ή Publication Date: Published on Oct 20

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.17498
β€’ PDF: https://arxiv.org/pdf/2510.17498

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training

πŸ”Ή Publication Date: Published on Oct 17

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.15527
β€’ PDF: https://arxiv.org/pdf/2510.15527

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

πŸ”Ή Publication Date: Published on Oct 16

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.14605
β€’ PDF: https://arxiv.org/pdf/2510.14605

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning

πŸ”Ή Publication Date: Published on Oct 17

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.16156
β€’ PDF: https://arxiv.org/pdf/2510.16156

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT