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: Memory Retrieval and Consolidation in Large Language Models through Function Tokens

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08203
• PDF: https://arxiv.org/pdf/2510.08203

🔹 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: Fidelity-Aware Data Composition for Robust Robot Generalization

🔹 Publication Date: Published on Sep 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.24797
• PDF: https://arxiv.org/pdf/2509.24797

🔹 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: Beyond Outliers: A Study of Optimizers Under Quantization

🔹 Publication Date: Published on Sep 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.23500
• PDF: https://arxiv.org/pdf/2509.23500

🔹 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: Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction

🔹 Publication Date: Published on Oct 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.03117
• PDF: https://arxiv.org/pdf/2510.03117
• Project Page: https://bridgedit-t2sv.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
1
🔹 Title: Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07048
• PDF: https://arxiv.org/pdf/2510.07048
• Github: https://github.com/ytgui/Search-R3

🔹 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: GCPO: When Contrast Fails, Go Gold

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07790
• PDF: https://arxiv.org/pdf/2510.07790
• Github: https://github.com/AchoWu/GCPO

🔹 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: SViM3D: Stable Video Material Diffusion for Single Image 3D Generation

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08271
• PDF: https://arxiv.org/pdf/2510.08271

🔹 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: GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07314
• PDF: https://arxiv.org/pdf/2510.07314

🔹 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: Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models

🔹 Publication Date: Published on Oct 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06209
• PDF: https://arxiv.org/pdf/2510.06209

🔹 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: OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26633
• PDF: https://arxiv.org/pdf/2509.26633
• Project Page: https://omniretarget.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: DreamOmni2: Multimodal Instruction-based Editing and Generation

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06679
• PDF: https://arxiv.org/pdf/2510.06679
• Project Page: https://pbihao.github.io/projects/DreamOmni2/index.html
• Github: https://github.com/dvlab-research/DreamOmni2

🔹 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: Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning

🔹 Publication Date: Published on Oct 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.02590
• PDF: https://arxiv.org/pdf/2510.02590

🔹 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: OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07743
• PDF: https://arxiv.org/pdf/2510.07743

🔹 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
🤖🧠 Join the 5-Day AI Agents Intensive Course with Google

🗓️ 07 Oct 2025
📚 AI News & Trends

Artificial Intelligence is rapidly evolving beyond chatbots and text generation. The next frontier is AI agents — intelligent, autonomous systems that can reason, take action and collaborate with tools and other agents. To help developers and practitioners build these next-generation systems, Google is launching the 5-Day AI Agents Intensive, a no-cost, online program running from ...

#aiagents #dayai #googleartificial #agentsintelligent #ai #evolvingchatbots
1
🤖🧠 Cognee: Powerful Memory for AI Agents in Just 6 Lines of Code

🗓️ 07 Oct 2025
📚 AI News & Trends

Artificial Intelligence is evolving rapidly, but one of the biggest challenges for developers is building agents that remember, reason and adapt. Traditional RAG (Retrieval-Augmented Generation) systems often fall short when handling context, scalability and precision. That’s where Cognee comes in. It is an open-source framework designed to provide AI agents with memory using a unique ...

#AI #Memory #AIAgents #OpenSource #RAG #ArtificialIntelligence
4
🤖🧠 ROMA: The Ultimate AI Framework That Lets You Build High-Performance Agents in Minutes

🗓️ 11 Oct 2025
📚 AI News & Trends

Artificial Intelligence continues to evolve at an unprecedented pace, with agent-based frameworks becoming increasingly important for tackling complex problems. ROMA (Recursive Open Meta-Agents) represents a significant leap forward in this space, providing developers and researchers with a hierarchical, flexible, and high-performance framework for building multi-agent AI systems. This article explores ROMA’s architecture, technical capabilities, practical ...

#AI #MachineLearning #MultiAgentSystems #ArtificialIntelligence #HighPerformance #ROMA
2👍1
🤖🧠 15+ Gemini AI Photo Editing Prompts for Boys: Create Stunning Styles & Expressions in 2025

🗓️ 11 Oct 2025
📚 AI News & Trends

Are you looking to take your portraits to the next level? With Gemini AI Photo Editing Prompts, boys can now turn ordinary photos into ultra-realistic, cinematic or high-fashion images effortlessly. These prompts are specifically designed to work with uploaded images, allowing you to enhance your existing photos while keeping the subject intact. Whether you’re curating ...

#GeminiAI #PhotoEditing #PortraitPhotography #AIart #BoysFashion #2025Trends
2
🤖🧠 DeepEval: The Ultimate LLM Evaluation Framework for AI Developers

🗓️ 07 Oct 2025
📚 AI News & Trends

In today’s AI-driven world, large language models (LLMs) have become central to modern applications from chatbots to intelligent AI agents. However, ensuring the accuracy, reliability and safety of these models is a significant challenge. Even small errors, biases or hallucinations can result in misleading information, frustrated users or business setbacks. This is where DeepEval, an ...

#DeepEval #LLM #AIDevelopment #LanguageModels #ModelEvaluation #ArtificialIntelligence
2
🤖🧠 The Little Book of Deep Learning – A Complete Summary and Chapter-Wise Overview

🗓️ 08 Oct 2025
📚 AI News & Trends

In the ever-evolving world of Artificial Intelligence, deep learning continues to be the driving force behind breakthroughs in computer vision, speech recognition and natural language processing. For those seeking a clear, structured and accessible guide to understanding how deep learning really works, “The Little Book of Deep Learning” by François Fleuret is a gem. This ...

#DeepLearning #ArtificialIntelligence #MachineLearning #NeuralNetworks #AIGuides # FrancoisFleuret
1
🤖🧠 Build a Large Language Model From Scratch: A Step-by-Step Guide to Understanding and Creating LLMs

🗓️ 08 Oct 2025
📚 AI News & Trends

In recent years, Large Language Models (LLMs) have revolutionized the world of Artificial Intelligence (AI). From ChatGPT and Claude to Llama and Mistral, these models power the conversational systems, copilots, and generative tools that dominate today’s AI landscape. However, for most developers and learners, the inner workings of these systems remain a mystery until now. ...

#LargeLanguageModels #LLM #ArtificialIntelligence #DeepLearning #MachineLearning #AIGuides
2👍1
🤖🧠 OpenAI’s AgentKit: Transforming How Developers Build and Deploy AI Agents

🗓️ 08 Oct 2025
📚 AI News & Trends

OpenAI continues to redefine the frontiers of artificial intelligence with the introduction of AgentKit a powerful all-in-one toolkit designed to simplify and accelerate how developers build and deploy AI agents. Unveiled during OpenAI’s Dev Day on October 6, 2025, AgentKit marks a transformative leap in agentic AI technology giving developers and organizations the ability to ...

#OpenAI #AgentKit #AIAgents #ArtificialIntelligence #DeveloperTools #AIInnovation
1