ML Research Hub – Telegram
ML Research Hub
32.8K subscribers
4.21K photos
253 videos
23 files
4.54K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 Title: ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20803
• PDF: https://arxiv.org/pdf/2510.20803

🔹 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: Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19600
• PDF: https://arxiv.org/pdf/2510.19600
• Project Page: https://mqleet.github.io/AutoPage_ProjectPage
• Github: https://github.com/AutoLab-SAI-SJTU/AutoPage

🔹 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: Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20470
• PDF: https://arxiv.org/pdf/2510.20470
• Github: https://github.com/OuyangKun10/Conan

🔹 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: AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19779
• PDF: https://arxiv.org/pdf/2510.19779
• Github: https://github.com/yuezhouhu/adaspec

🔹 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 Massive Legal Embedding Benchmark (MLEB)

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19365
• PDF: https://arxiv.org/pdf/2510.19365
• Project Page: https://isaacus.com/mleb
• Github: https://github.com/isaacus-dev/mleb

🔹 Datasets citing this paper:
https://huggingface.co/datasets/isaacus/mteb-barexam-qa
https://huggingface.co/datasets/isaacus/mleb-scalr
https://huggingface.co/datasets/isaacus/australian-tax-guidance-retrieval
https://huggingface.co/datasets/isaacus/gdpr-holdings-retrieval

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20766
• PDF: https://arxiv.org/pdf/2510.20766
• Project Page: https://noamissachar.github.io/DyPE/
• Github: https://github.com/guyyariv/DyPE

🔹 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: Search Self-play: Pushing the Frontier of Agent Capability without Supervision

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18821
• PDF: https://arxiv.org/pdf/2510.18821
• Github: https://github.com/Alibaba-Quark/SSP

🔹 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: From Masks to Worlds: A Hitchhiker's Guide to World Models

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20668
• PDF: https://arxiv.org/pdf/2510.20668
• Github: https://github.com/M-E-AGI-Lab/Awesome-World-Models

🔹 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: Emergence of Linear Truth Encodings in Language Models

🔹 Publication Date: Published on Oct 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.15804
• PDF: https://arxiv.org/pdf/2510.15804

🔹 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: Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19944
• PDF: https://arxiv.org/pdf/2510.19944
• Project Page: https://seed.bytedance.com/seed3d

🔹 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: Thought Communication in Multiagent Collaboration

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20733
• PDF: https://arxiv.org/pdf/2510.20733

🔹 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: SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16917
• PDF: https://arxiv.org/pdf/2510.16917
• Project Page: https://github.com/ckyang1124/SAKE
• Github: https://github.com/ckyang1124/SAKE

🔹 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: Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16893
• PDF: https://arxiv.org/pdf/2510.16893
• Project Page: https://github.com/WoZhenDeShenMeDouBuZhidao/LALM-emotional-vulnerability
• Github: https://github.com/WoZhenDeShenMeDouBuZhidao/LALM-emotional-vulnerability

🔹 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: Diff-XYZ: A Benchmark for Evaluating Diff Understanding

🔹 Publication Date: Published on Oct 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.12487
• PDF: https://arxiv.org/pdf/2510.12487

🔹 Datasets citing this paper:
https://huggingface.co/datasets/JetBrains-Research/diff-xyz

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20362
• PDF: https://arxiv.org/pdf/2510.20362

🔹 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: Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19995
• PDF: https://arxiv.org/pdf/2510.19995

🔹 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
🤖🧠 LangChain: The Ultimate Framework for Building Reliable AI Agents and LLM Applications

🗓️ 24 Oct 2025
📚 AI News & Trends

As artificial intelligence continues to transform industries, developers are racing to build smarter, more adaptive applications powered by Large Language Models (LLMs). Yet, one major challenge remains how to make these models interact intelligently with real-world data and external systems in a scalable, reliable way. Enter LangChain, an open-source framework designed to make LLM-powered application ...

#LangChain #AI #LLM #ArtificialIntelligence #OpenSource #AIAgents
1
🔹 Title: CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation

🔹 Publication Date: Published on Oct 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17853
• PDF: https://arxiv.org/pdf/2510.17853
• Project Page: https://kathcym.github.io/CiteGuard_Page/
• Github: https://kathcym.github.io/CiteGuard_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
1
🔹 Title: Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18245
• PDF: https://arxiv.org/pdf/2510.18245

🔹 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
1
🔹 Title: Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18413
• PDF: https://arxiv.org/pdf/2510.18413

🔹 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: Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17896
• PDF: https://arxiv.org/pdf/2510.17896

🔹 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
1