🔹 Title: GigaBrain-0: A World Model-Powered Vision-Language-Action Model

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19430
• PDF: https://arxiv.org/pdf/2510.19430
• Project Page: https://gigabrain0.github.io/
• Github: https://github.com/open-gigaai/giga-brain-0

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: From Charts to Code: A Hierarchical Benchmark for Multimodal Models

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17932
• PDF: https://arxiv.org/pdf/2510.17932
• Project Page: https://csu-jpg.github.io/Chart2Code.github.io/
• Github: https://github.com/CSU-JPG/Chart2Code

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/CSU-JPG/Chart2Code

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

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

🔹 Title: Attention Sinks in Diffusion Language Models

🔹 Publication Date: Published on Oct 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15731
• PDF: https://arxiv.org/pdf/2510.15731

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Directional Reasoning Injection for Fine-Tuning MLLMs

🔹 Publication Date: Published on Oct 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15050
• PDF: https://arxiv.org/pdf/2510.15050
• Github: https://github.com/WikiChao/DRIFT

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: See the Text: From Tokenization to Visual Reading

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18840
• PDF: https://arxiv.org/pdf/2510.18840

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

🔹 Publication Date: Published on Oct 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15015
• PDF: https://arxiv.org/pdf/2510.15015

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Language Models are Injective and Hence Invertible

🔹 Publication Date: Published on Oct 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15511
• PDF: https://arxiv.org/pdf/2510.15511

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19592
• PDF: https://arxiv.org/pdf/2510.19592
• Project Page: https://www.jshyun.me/projects/decaf
• Github: https://github.com/HYUNJS/DecAF

🔹 Datasets citing this paper:
No datasets found

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

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

🤖🧠 LangGraph by LangChain-AI: The Framework Powering Stateful, Long-Running AI Agents

🗓️ 23 Oct 2025
📚 AI News & Trends

As artificial intelligence continues to reshape industries, one major challenge remains building reliable, stateful and long-running AI agents that can handle complex workflows over time. Traditional AI frameworks often focus on short interactions, lacking the infrastructure to manage persistent states, durable memory or human feedback loops. That’s where LangGraph from LangChain-AI steps in. Trusted by ...

#LangGraph #LangChainAI #AIAgents #StatefulAI #LongRunningAgents #ArtificialIntelligence

🤖🧠 Master Machine Learning: Explore the Ultimate “Machine-Learning-Tutorials” Repository

🗓️ 23 Oct 2025
📚 AI News & Trends

In today’s data-driven world, Machine Learning (ML) has become the cornerstone of modern technology from intelligent chatbots to predictive analytics and recommendation systems. However, mastering ML isn’t just about coding, it requires a structured understanding of algorithms, statistics, optimization techniques and real-world problem-solving. That’s where Ujjwal Karn’s Machine-Learning-Tutorials GitHub repository stands out. This open-source, topic-wise ...

#MachineLearning #MLTutorials #ArtificialIntelligence #DataScience #OpenSource #AIEducation

🔹 Title: What Questions Should Robots Be Able to Answer? A Dataset of User Questions for Explainable Robotics

🔹 Publication Date: Published on Oct 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16435
• PDF: https://arxiv.org/pdf/2510.16435

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/lwachowiak/xai-questions-dataset

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

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

🔹 Title: Steering Autoregressive Music Generation with Recursive Feature Machines

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19127
• PDF: https://arxiv.org/pdf/2510.19127
• Github: https://github.com/astradzhao/music-rfm

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18034
• PDF: https://arxiv.org/pdf/2510.18034

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Accelerating Vision Transformers with Adaptive Patch Sizes

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18091
• PDF: https://arxiv.org/pdf/2510.18091
• Github: https://github.com/rccchoudhury/apt

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18279
• PDF: https://arxiv.org/pdf/2510.18279
• Github: https://github.com/yanhong-lbh/text_or_pixels

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20187
• PDF: https://arxiv.org/pdf/2510.20187

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/sarosavo/RLEV

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

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

🔹 Title: HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20822
• PDF: https://arxiv.org/pdf/2510.20822
• Project Page: https://holo-cine.github.io

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20820
• PDF: https://arxiv.org/pdf/2510.20820
• Project Page: https://snap-research.github.io/layercomposer/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: AlphaFlow: Understanding and Improving MeanFlow Models

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20771
• PDF: https://arxiv.org/pdf/2510.20771
• Github: https://github.com/snap-research/alphaflow

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20579
• PDF: https://arxiv.org/pdf/2510.20579
• Project Page: https://marinero4972.github.io/projects/Open-o3-Video/

🔹 Datasets citing this paper:
No datasets found

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

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