ML Research Hub – Telegram
ML Research Hub
32.7K subscribers
4.03K photos
230 videos
23 files
4.34K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🤖🧠 Kimi Linear: The Future of Efficient Attention in Large Language Models

🗓️ 08 Nov 2025
📚 AI News & Trends

The rapid evolution of large language models (LLMs) has unlocked new capabilities in natural language understanding, reasoning, coding and multimodal tasks. However, as models grow more advanced, one major challenge persists: computational efficiency. Traditional full-attention architectures struggle to scale efficiently, especially when handling long context windows and real-time inference workloads. The increasing demand for agent-like ...

#KimiLinear #EfficientAttention #LargeLanguageModels #LLM #ComputationalEfficiency #AIInnovation
🤖🧠 Meilisearch: The Lightning-Fast, AI-Ready Search Engine for Modern Applications

🗓️ 08 Nov 2025
📚 AI News & Trends

Search is no longer a luxury feature. Today’s users expect instant, relevant results across e-commerce platforms, SaaS tools, media libraries and knowledge systems. With AI-powered experiences becoming the new standard, developers need search infrastructure that is fast, flexible, developer-friendly and ready for hybrid semantic search. This is where Meilisearch stands out. Meilisearch is an open-source, ...

#Meilisearch #AIReadySearch #LightningFast #SearchEngine #ModernApplications #OpenSource
🤖🧠 Pixeltable: The Future of Declarative Data Infrastructure for Multimodal AI Workloads

🗓️ 08 Nov 2025
📚 AI News & Trends

In the rapidly evolving AI landscape, building intelligent applications is no longer just about having powerful models. The real challenge lies in handling complex data pipelines, integrating multiple systems and scaling multimodal workloads efficiently. Traditional AI app development stacks involve databases, vector stores, ETL pipelines, model serving layers, orchestration tools, caching systems and lineage tracking ...

#Pixeltable #DeclarativeDataInfrastructure #MultimodalAI #AIDevelopment #DataPipelines #AIWorkloads
🤖🧠 Chandra OCR: The Future of Document Understanding and Layout-Aware Text Extraction

🗓️ 08 Nov 2025
📚 AI News & Trends

Optical Character Recognition (OCR) has evolved far beyond simply converting scanned text into digital characters. With the rise of artificial intelligence and large language models, the industry is shifting toward intelligent document understanding where structure, context and visual elements matter as much as the text itself. In this landscape, Chandra emerges as a breakthrough solution. ...

#ChandraOCR #DocumentUnderstanding #LayoutAwareText #OpticalCharacterRecognition #AIDocumentProcessing #IntelligentOCR
🤖🧠 LMCache: Accelerating LLM Inference With Next-Generation KV Cache Technology

🗓️ 08 Nov 2025
📚 AI News & Trends

As large language models (LLMs) continue to scale in size and complexity, organizations face an increasingly critical challenge: serving models efficiently in real-world applications. While LLM capabilities are rapidly evolving, the bottleneck of inference performance remains a major limitation especially when dealing with long-context workloads or high-traffic enterprise environments. This is where LMCache steps in. ...

#LMCache #LLMInference #KVCache #LargeLanguageModels #AIAcceleration #NextGenTechnology
🤖🧠 Dify: A Powerful #1 Production-Ready Platform for Building Advanced LLM Applications

🗓️ 08 Nov 2025
📚 AI News & Trends

The rapid growth of AI has made large language models (LLMs) an essential component for automation, content creation, data intelligence and workflow optimization. But moving AI concepts from prototype to production has traditionally required significant engineering effort, infrastructure planning and model-orchestration expertise. Dify changes that entirely. Dify is an open-source platform designed to help developers, ...

#Dify #LLMApplications #ProductionReady #AIPower #LargeLanguageModels #OpenSourcePlatform
JoyAgent-JDGenie: Technical Report on the GAIA

📝 Summary:
This paper introduces JoyAgent-JDGenie, a generalist AI agent architecture. It integrates multi-agent planning, hierarchical memory, and advanced tools to achieve superior performance across diverse tasks, outperforming baselines and approaching proprietary systems.

🔹 Publication Date: Published on Oct 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.00510
• PDF: https://arxiv.org/pdf/2510.00510
• Github: https://github.com/jd-opensource/joyagent-jdgenie

==================================

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

#AIAgent #GeneralistAI #MultiAgentSystems #AIResearch #MachineLearning
nature papers: 2000$

Q1 and  Q2 papers    1000$

Q3 and Q4 papers   500$

Doctoral thesis (complete)    700$

M.S thesis         300$

paper simulation   200$

Contact me @husseinsheikho
🤖🧠 Open WebUI: The Most Powerful Self-Hosted AI Platform for Local and Private LLMs

🗓️ 09 Nov 2025
📚 AI News & Trends

In the rapidly evolving landscape of artificial intelligence, the ability to run large language models securely and efficiently has become a major priority for developers, enterprises and privacy-focused users. While cloud-based AI services are convenient, they rely heavily on remote servers, internet access and third-party control. This is where Open WebUI stands out as a ...

#OpenWebUI #SelfHostedAI #PrivateLLMs #LocalAI #AISecurity #OpenSourcePlatform
🤖🧠 Generative AI for Beginners: A Complete Guide to Microsoft’s Free Course

🗓️ 09 Nov 2025
📚 AI News & Trends

Generative AI has rapidly shifted from an emerging technology to a foundation of modern digital innovation. From automated writing assistants and AI chatbots to image generators and intelligent search engines, generative AI is transforming industries and shaping the future of work. Whether you are a student, a budding developer or a technology enthusiast, learning generative ...

#GenerativeAI #BeginnersGuide #MicrosoftAI #FreeCourse #AIEducation #DigitalInnovation
Media is too big
VIEW IN TELEGRAM
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development

📝 Summary:
ComfyUI-Copilot is an LLM and multi-agent system that enhances ComfyUI's usability. It provides intelligent recommendations and automated one-click workflow construction, lowering entry barriers for beginners and boosting efficiency for experienced users.

🔹 Publication Date: Published on Jun 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2506.05010
• PDF: https://arxiv.org/pdf/2506.05010
• Project Page: https://x.com/wangly0229/status/1923515826713526583
• Github: https://github.com/AIDC-AI/ComfyUI-Copilot

==================================

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

#LLM #MultiAgent #ComfyUI #AI #WorkflowAutomation
OpenVoice: Versatile Instant Voice Cloning

📝 Summary:
OpenVoice is a versatile voice cloning method using a short audio clip. It provides flexible control over voice styles and achieves zero-shot cross-lingual cloning for new languages without extensive training data. It is also highly efficient.

🔹 Publication Date: Published on Dec 3, 2023

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2312.01479
• PDF: https://arxiv.org/pdf/2312.01479
• Github: https://github.com/myshell-ai/openvoice

🔹 Models citing this paper:
https://huggingface.co/rsxdalv/OpenVoiceV2
https://huggingface.co/ameerazam08/Udiff
https://huggingface.co/flopml/OpenVoice-v2

Datasets citing this paper:
https://huggingface.co/datasets/tsinghua-ee/QualiSpeech
https://huggingface.co/datasets/dlxjj/Openvoice
https://huggingface.co/datasets/Pendrokar/open_tts_tracker

Spaces citing this paper:
https://huggingface.co/spaces/Russell1123213123/testOpenVoice
https://huggingface.co/spaces/gauthamk28/gauthamk28_voice
https://huggingface.co/spaces/blayks07/OpenVoice-main

==================================

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

#VoiceCloning #AIResearch #SpeechSynthesis #ZeroShotLearning #CrossLingualAI
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

📝 Summary:
LLMs struggle to authentically role-play villains due to safety alignment, showing a monotonic decline in fidelity as character morality decreases. The Moral RolePlay benchmark reveals models struggle with traits like deceit and manipulation, highlighting a tension between model safety and creati...

🔹 Publication Date: Published on Nov 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.04962
• PDF: https://arxiv.org/pdf/2511.04962
• Github: https://github.com/Tencent/DigitalHuman/tree/main/RolePlay_Villain

==================================

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

#LLM #AI #AISafety #RolePlaying #NLP
Visual Spatial Tuning

📝 Summary:
Visual Spatial Tuning VST is a framework that progressively trains Vision-Language Models VLMs using specialized datasets VST-P for spatial perception and VST-R for reasoning. VST achieves state-of-the-art results on spatial benchmarks without harming general VLM capabilities, leading to more phy...

🔹 Publication Date: Published on Nov 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05491
• PDF: https://arxiv.org/pdf/2511.05491
• Project Page: https://yangr116.github.io/vst_project/
• Github: https://github.com/Yangr116/VST

==================================

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

#VisionLanguageModels #SpatialAI #ComputerVision #DeepLearning #AIResearch
Dense Motion Captioning

📝 Summary:
The paper introduces Dense Motion Captioning, a new task for 3D human motion understanding. It presents CompMo, a large dataset with complex, temporally annotated motions, and DEMO, a model combining a language model with a motion adapter to generate detailed, grounded captions.

🔹 Publication Date: Published on Nov 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05369
• PDF: https://arxiv.org/pdf/2511.05369
• Project Page: https://xusy2333.com/demo/
• Github: https://github.com/41xu/DEMO

==================================

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

#MotionCaptioning #3DMotion #ComputerVision #LanguageModels #AIResearch
DeepEyesV2: Toward Agentic Multimodal Model

📝 Summary:
DeepEyesV2 is an agentic multimodal model that uses a two-stage training pipeline for robust tool integration. This method, combining a cold-start stage and reinforcement learning, effectively enables task-adaptive tool invocation for real-world reasoning tasks.

🔹 Publication Date: Published on Nov 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05271
• PDF: https://arxiv.org/pdf/2511.05271
• Project Page: https://visual-agent.github.io/
• Github: https://github.com/Visual-Agent/DeepEyes

==================================

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

#MultimodalAI #AgenticAI #ReinforcementLearning #DeepLearning #AIResearch
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

📝 Summary:
Large Vision-Language Models suffer from language bias leading to hallucinations. Our method refines textual embeddings by integrating average-pooled visual features. This simple approach improves visual grounding and reduces hallucinations.

🔹 Publication Date: Published on Nov 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05017
• PDF: https://arxiv.org/pdf/2511.05017

==================================

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

#VisionLanguageModels #AIHallucinations #VisualGrounding #DeepLearning #NLP
Jailbreaking in the Haystack

📝 Summary:
NINJA is a new jailbreak method for long-context LMs. It appends benign content to harmful goals, exploiting goal positioning. This significantly increases attack success rates, revealing fundamental vulnerabilities in modern models.

🔹 Publication Date: Published on Nov 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.04707
• PDF: https://arxiv.org/pdf/2511.04707
• Project Page: https://ar-forum.github.io/ninjaattackweb/
• Github: https://github.com/AR-FORUM/NINJA_Attack

==================================

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

#LLM #Jailbreaking #AISafety #AI #Cybersecurity