🔹 Title: Deconstructing Attention: Investigating Design Principles for Effective Language Modeling

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11602
• PDF: https://arxiv.org/pdf/2510.11602

🔹 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: SR-Scientist: Scientific Equation Discovery With Agentic AI

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11661
• PDF: https://arxiv.org/pdf/2510.11661

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/GAIR/SR-Scientist

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

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

🔹 Title: Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09259
• PDF: https://arxiv.org/pdf/2510.09259
• Github: https://github.com/yongding-tao/RL-Data-Contamination

🔹 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: Cautious Weight Decay

🔹 Publication Date: Published on Oct 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.12402
• PDF: https://arxiv.org/pdf/2510.12402

🔹 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: Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11330
• PDF: https://arxiv.org/pdf/2510.11330

🔹 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: Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance

🔹 Publication Date: Published on Oct 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.12497
• PDF: https://arxiv.org/pdf/2510.12497

🔹 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: ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11000
• PDF: https://arxiv.org/pdf/2510.11000
• Project Page: https://nenhang.github.io/ContextGen/
• Github: https://github.com/nenhang/ContextGen

🔹 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: Locket: Robust Feature-Locking Technique for Language Models

🔹 Publication Date: Published on Oct 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.12117
• PDF: https://arxiv.org/pdf/2510.12117

🔹 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

🤖🧠 MinerU2.5 by Shanghai AI Lab, Peking University & Shanghai Jiao Tong University Sets New Standard for AI-Powered Document Parsing

🗓️ 15 Oct 2025
📚 AI News & Trends

In the world of digital transformation, the ability to accurately extract and interpret information from complex documents is becoming increasingly essential. Whether for academic research, financial analysis or enterprise automation, document parsing – the process of converting structured and unstructured document data into machine-readable formats plays a vital role. Enter MinerU2.5, a groundbreaking vision-language model ...

🔹 Title: The Geometry of Reasoning: Flowing Logics in Representation Space

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09782
• PDF: https://arxiv.org/pdf/2510.09782
• Github: https://github.com/MasterZhou1/Reasoning-Flow

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/MasterZhou/Reasoning-Flow

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

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

🔹 Title: Why Do Transformers Fail to Forecast Time Series In-Context?

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09776
• PDF: https://arxiv.org/pdf/2510.09776
• Github: https://github.com/MasterZhou1/ICL-Time-Series

🔹 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: Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08532
• PDF: https://arxiv.org/pdf/2510.08532
• Project Page: https://huggingface.co/papers?q=lightweight%20projector%20network
• Github: https://snap-research.github.io/kontinuouskontext/

🔹 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: Scaling Long-Horizon LLM Agent via Context-Folding

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2510.11967
• PDF: https://arxiv.org/pdf/2510.11967

🔹 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: Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2510.06727
• PDF: https://arxiv.org/pdf/2510.06727

🔹 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: The Role of Computing Resources in Publishing Foundation Model Research

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13621
• PDF: https://arxiv.org/pdf/2510.13621

🔹 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: Generative Universal Verifier as Multimodal Meta-Reasoner

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13804
• PDF: https://arxiv.org/pdf/2510.13804
• Project Page: https://omniverifier.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: Trace Anything: Representing Any Video in 4D via Trajectory Fields

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13802
• PDF: https://arxiv.org/pdf/2510.13802

🔹 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: Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13586
• PDF: https://arxiv.org/pdf/2510.13586
• Project Page: https://huggingface.co/collections/Character-lab/emnlp-cpdc-wordplay-2025-68dcd9f5cc8c8bc209875c1c

🔹 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: PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13809
• PDF: https://arxiv.org/pdf/2510.13809
• Project Page: https://sihuiji.github.io/PhysMaster-Page/

🔹 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: Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13744
• PDF: https://arxiv.org/pdf/2510.13744
• Github: https://github.com/SalesforceAIResearch/Hard2Verify

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/Salesforce/Hard2Verify

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

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

🔹 Title: InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.13747
• PDF: https://arxiv.org/pdf/2510.13747

🔹 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