ML Research Hub
32.8K subscribers
4.32K photos
263 videos
23 files
4.67K links
Advancing research in Machine Learning โ€“ practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
๐Ÿ”น Title: KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints

๐Ÿ”น Publication Date: Published on Oct 22

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.19316
โ€ข PDF: https://arxiv.org/pdf/2510.19316
โ€ข Project Page: https://kore-lmm.github.io/

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: FinSight: Towards Real-World Financial Deep Research

๐Ÿ”น Publication Date: Published on Oct 19

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.16844
โ€ข PDF: https://arxiv.org/pdf/2510.16844

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18428
โ€ข PDF: https://arxiv.org/pdf/2510.18428

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18927
โ€ข PDF: https://arxiv.org/pdf/2510.18927
โ€ข Project Page: https://github.com/WooooDyy/BAPO
โ€ข Github: https://github.com/WooooDyy/BAPO

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18941
โ€ข PDF: https://arxiv.org/pdf/2510.18941

๐Ÿ”น Datasets citing this paper:
โ€ข https://huggingface.co/datasets/nvidia/ProfBench

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18940
โ€ข PDF: https://arxiv.org/pdf/2510.18940
โ€ข Github: https://github.com/FightingFighting/NeuroAda.git

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: RIR-Mega: a large-scale simulated room impulse response dataset for machine learning and room acoustics modeling

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18917
โ€ข PDF: https://arxiv.org/pdf/2510.18917
โ€ข Project Page: https://doi.org/10.5281/zenodo.17387402
โ€ข Github: https://github.com/mandip42/rirmega

๐Ÿ”น Datasets citing this paper:
โ€ข https://huggingface.co/datasets/mandipgoswami/rirmega

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
โค1
๐Ÿ”น Title: Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.19028
โ€ข PDF: https://arxiv.org/pdf/2510.19028
โ€ข Github: https://github.com/rladmstn1714/SCRIPTS

๐Ÿ”น Datasets citing this paper:
โ€ข https://huggingface.co/datasets/EunsuKim/SCRIPTS

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18909
โ€ข PDF: https://arxiv.org/pdf/2510.18909

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: When Do Transformers Learn Heuristics for Graph Connectivity?

๐Ÿ”น Publication Date: Published on Oct 22

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.19753
โ€ข PDF: https://arxiv.org/pdf/2510.19753

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: Machine Text Detectors are Membership Inference Attacks

๐Ÿ”น Publication Date: Published on Oct 22

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.19492
โ€ข PDF: https://arxiv.org/pdf/2510.19492
โ€ข Github: https://github.com/ryuryukke/mint

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: GigaBrain-0: A World Model-Powered Vision-Language-Action Model

๐Ÿ”น Publication Date: Published on Oct 22

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.19430
โ€ข PDF: https://arxiv.org/pdf/2510.19430
โ€ข Project Page: https://gigabrain0.github.io/
โ€ข Github: https://github.com/open-gigaai/giga-brain-0

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: From Charts to Code: A Hierarchical Benchmark for Multimodal Models

๐Ÿ”น Publication Date: Published on Oct 20

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.17932
โ€ข PDF: https://arxiv.org/pdf/2510.17932
โ€ข Project Page: https://csu-jpg.github.io/Chart2Code.github.io/
โ€ข Github: https://github.com/CSU-JPG/Chart2Code

๐Ÿ”น Datasets citing this paper:
โ€ข https://huggingface.co/datasets/CSU-JPG/Chart2Code

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: Attention Sinks in Diffusion Language Models

๐Ÿ”น Publication Date: Published on Oct 17

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.15731
โ€ข PDF: https://arxiv.org/pdf/2510.15731

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: Directional Reasoning Injection for Fine-Tuning MLLMs

๐Ÿ”น Publication Date: Published on Oct 16

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.15050
โ€ข PDF: https://arxiv.org/pdf/2510.15050
โ€ข Github: https://github.com/WikiChao/DRIFT

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: See the Text: From Tokenization to Visual Reading

๐Ÿ”น Publication Date: Published on Oct 21

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.18840
โ€ข PDF: https://arxiv.org/pdf/2510.18840

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
โค1
๐Ÿ”น Title: DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

๐Ÿ”น Publication Date: Published on Oct 16

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.15015
โ€ข PDF: https://arxiv.org/pdf/2510.15015

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿ”น Title: Language Models are Injective and Hence Invertible

๐Ÿ”น Publication Date: Published on Oct 17

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.15511
โ€ข PDF: https://arxiv.org/pdf/2510.15511

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
โค1
๐Ÿ”น Title: Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

๐Ÿ”น Publication Date: Published on Oct 22

๐Ÿ”น Paper Links:
โ€ข arXiv Page: https://arxiv.org/abs/2510.19592
โ€ข PDF: https://arxiv.org/pdf/2510.19592
โ€ข Project Page: https://www.jshyun.me/projects/decaf
โ€ข Github: https://github.com/HYUNJS/DecAF

๐Ÿ”น Datasets citing this paper:
No datasets found

๐Ÿ”น Spaces citing this paper:
No spaces found
==================================

For more data science resources:
โœ“ https://t.me/DataScienceT
๐Ÿค–๐Ÿง  LangGraph by LangChain-AI: The Framework Powering Stateful, Long-Running AI Agents

๐Ÿ—“๏ธ 23 Oct 2025
๐Ÿ“š 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. Thatโ€™s where LangGraph from LangChain-AI steps in. Trusted by ...

#LangGraph #LangChainAI #AIAgents #StatefulAI #LongRunningAgents #ArtificialIntelligence
๐Ÿค–๐Ÿง  Master Machine Learning: Explore the Ultimate โ€œMachine-Learning-Tutorialsโ€ Repository

๐Ÿ—“๏ธ 23 Oct 2025
๐Ÿ“š AI News & Trends

In todayโ€™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 isnโ€™t just about coding, it requires a structured understanding of algorithms, statistics, optimization techniques and real-world problem-solving. Thatโ€™s where Ujjwal Karnโ€™s Machine-Learning-Tutorials GitHub repository stands out. This open-source, topic-wise ...

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