ML Research Hub – Telegram
ML Research Hub
32.9K subscribers
4.45K photos
273 videos
23 files
4.81K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 Title: Understanding DeepResearch via Reports

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07861
• PDF: https://arxiv.org/pdf/2510.07861

🔹 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: A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks

🔹 Publication Date: Published on Oct 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.05608
• PDF: https://arxiv.org/pdf/2510.05608

🔹 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 Overthinking through Reasoning Shaping

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09535
• PDF: https://arxiv.org/pdf/2510.09535

🔹 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: Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2510.08994
• PDF: https://arxiv.org/pdf/2510.08994

🔹 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
🤖🧠 Quivr AI: Building Your Second Brain with Open-Source Generative Intelligence

🗓️ 12 Oct 2025
📚 AI News & Trends

In the rapidly evolving landscape of artificial intelligence, developers and businesses are seeking solutions that merge flexibility, power, and simplicity. Enter Quivr — an open-source framework designed to help you build your own “second brain” powered by Generative AI. Whether you’re an indie developer, startup founder or enterprise engineer, it makes it possible to integrate ...

#QuivrAI #SecondBrain #GenerativeAI #OpenSourceAI #AIFramework #AIProductivity
🔹 Title: ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07896
• PDF: https://arxiv.org/pdf/2510.07896

🔹 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: DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07959
• PDF: https://arxiv.org/pdf/2510.07959
• Github: https://github.com/arubique/disco-public

🔹 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: D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

🔹 Publication Date: Published on Oct 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.05684
• PDF: https://arxiv.org/pdf/2510.05684
• Project Page: https://worv-ai.github.io/d2e/
• Github: https://worv-ai.github.io/d2e/

🔹 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: One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

🔹 Publication Date: Published on Oct 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.02898
• PDF: https://arxiv.org/pdf/2510.02898
• Project Page: https://paciosoft.com/Patch-ioner/
• Github: https://github.com/Ruggero1912/Patch-ioner

🔹 Datasets citing this paper:
https://huggingface.co/datasets/Ruggero1912/Trace_Captioning_COCO
https://huggingface.co/datasets/Ruggero1912/Trace_Captioning_Flickr30K

🔹 Spaces citing this paper:
https://huggingface.co/spaces/Ruggero1912/Patch-ioner
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08492
• PDF: https://arxiv.org/pdf/2510.08492
• Project Page: https://unpaired-multimodal.github.io/
• Github: https://github.com/Sharut/Unpaired-Multimodal-Learning/

🔹 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: Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization

🔹 Publication Date: Published on Oct 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06274
• PDF: https://arxiv.org/pdf/2510.06274

🔹 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: Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09462
• PDF: https://arxiv.org/pdf/2510.09462

🔹 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: KORMo: Korean Open Reasoning Model for Everyone

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09426
• PDF: https://arxiv.org/pdf/2510.09426

🔹 Datasets citing this paper:
https://huggingface.co/datasets/KORMo-Team/IF-bilingual-sft
https://huggingface.co/datasets/KORMo-Team/Cosmopedia-ko-synth
https://huggingface.co/datasets/KORMo-Team/UltraFineWeb-ko-synth
https://huggingface.co/datasets/KORMo-Team/OpenCodeReasoning-ko-synth

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Which Heads Matter for Reasoning? RL-Guided KV Cache Compression

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08525
• PDF: https://arxiv.org/pdf/2510.08525

🔹 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: Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2510.09320%5D
• PDF: https://arxiv.org/pdf/2510.09320
• Github: https://github.com/Zhangwenyao1/Hybrid-depth%5D

🔹 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: Formalizing Style in Personal Narratives

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08649
• PDF: https://arxiv.org/pdf/2510.08649

🔹 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: LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07793
• PDF: https://arxiv.org/pdf/2510.07793

🔹 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: ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07151
• PDF: https://arxiv.org/pdf/2510.07151
• Project Page: https://elmur-paper.github.io/
• Github: https://github.com/CognitiveAISystems/RATE

🔹 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: LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07962
• PDF: https://arxiv.org/pdf/2510.07962

🔹 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: MONKEY: Masking ON KEY-Value Activation Adapter for Personalization

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07656
• PDF: https://arxiv.org/pdf/2510.07656

🔹 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
🤖🧠 Ultimate OpenTSLM: Stanford’s Open-Source Framework Bridging LLMs and Medical Time-Series Data

🗓️ 13 Oct 2025
📚 AI News & Trends

In recent years, artificial intelligence (AI) has made remarkable strides in transforming healthcare. From medical imaging to patient monitoring systems, AI-driven solutions are reshaping how clinicians diagnose, treat and manage diseases. One of the most promising developments in this space is the integration of large language models (LLMs) with time-series data, a combination that holds ...

#OpenTSLM #LLMs #MedicalAI #TimeSeriesData #ArtificialIntelligence #OpenSourceFramework