23171
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
https://arxiv.org/abs/2602.24286
@LLM_learning
با عرض سلام این مقاله فقط ۳ نویسنده خواهد داشت و زمان تقریبی سابمیت ۲ هفته خواهد بود...!
@Raminmousa
⚡️Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds
HF: https://huggingface.co/papers/2511.08892
Peoject: https://www.lumine-ai.org/
Paper: https://arxiv.org/abs/2511.08892
@Machine_learn
🔥 Efficient Guided Generation for Large Language Models
💡 The paper presents an efficient method for guiding large language model text generation using regular expressions and context-free grammars. The problem addressed is that guided generation can be impractical due to significant overhead. The authors propose an approach that adds minimal overhead to the token sequence generation process. This method makes guided generation feasible in practice. The approach is implemented in the open source Python library Outlines, providing a practical solution for efficient guided generation. The results indicate that the method is effective, allowing for guided generation with little to no overhead, which is a significant contribution to the field of natural language processing.
📅 Published on Jul 19, 2023
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2307.09702
• PDF: https://arxiv.org/pdf/2307.09702
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
📃 Current Bioinformatics Tools in Precision Oncology
📎 Study paper
@Machine_learn
🎬 ساخت ویدیو
• Sora
• Kling
• Veo
• Seedance
• Lumalabs
🎨 ساخت تصویر
• Google Flow
• Qwen Image
• NanoBanana
• ChatGPT Image
• Grok
🎤 تقلید صدا
• ElevenLabs
• Fish Audio
• Minimax
• Descript
• Respeecher
🧠 تحقیق و کاوش
• ChatGPT
• Gemini
• Perplexity
• NotebookLM
• Deepseek
🗣 ساخت کاراکتر سخنگو
• Heygen
• Synthesia
• D-ID
• Hedra
━━━━━━━━━━━━━━━
🔗 لینک ابزارها:
• ChatGPT → https://chatgpt.com
• Gemini → https://gemini.google.com
• Perplexity → https://perplexity.ai
• Deepseek → https://deepseek.com
• NotebookLM → https://notebooklm.google.com
• Kling → https://klingai.com
• Veo → https://deepmind.google/technologies/veo
• Lumalabs → https://lumalabs.ai
• Sora → https://openai.com/sora
• ElevenLabs → https://elevenlabs.io
• Fish Audio → https://fish.audio
• Descript → https://descript.com
• Heygen → https://heygen.com
• Synthesia → https://synthesia.io
• D-ID → https://d-id.com
/channel/Machine_learn
با عرض سلام یکی از مقالاتمون در حوزه ی wound image classification در ژورنال nature scientific reports ریوایزد خورده و جایگاه های ۲، ۴ و ۵ اش قابل اضافه شدن می باشد. دوستانی که نیاز دارن می تونن جهت ثبت اسم به ایدی بنده پیام بدن
Price
2: 300$
4: 200$
5:150$
@Raminmousa
@Paper4money
@Machine_learn
Follow the Machine Learning with Python channel on WhatsApp: https://whatsapp.com/channel/0029VaC7Weq29753hpcggW2A
Читать полностью…
با عرض سلام
دوستان اوضاع اصلا جالب نیست و کلا اینترنت نداریم. امیدوارم حالتون خوب باشه و اوضاع بهتر بشه.
🖤
فقط نفرات ۲ و ۳ از این مقاله باقی موندن...!
Читать полностью…
با عرض سلام مي خواهيم مقاله كنفرانسي با عنوان زير بنويسيم
Complex Sig: Complex deep model for signal classification
Abstract: The ability to classify signals is an important task that provides the opportunity for many different applications. In the early research for signal classification, they had to
decompose the signal using FT (Fourier transform), SIFT, MFCC or other manual methods using statistical modulation features, then classify these signals by a traditional machine learning approach. In the last few years, the process of learning deep models that lead to the automatic extraction of features has positively affected classification. Different deep-learning models with di erent depths have been proposed in the literature.
This article proposes different approaches to classify signals in different SNR conditions. ResNet-based approaches perform well for high SNRs but poorly when dealing with low SNRs. Therefore, TRansforme-based approaches were proposed for classification, reaching an average accuracy of 0.7056 in low SNR and an average of 0.9089 in high SNR.
نتايج اوليه خوب بوده و قابل مقايسه با ساير مقالات تو اين حوزه ميباشد. نياز به ٢ يا سه نفر داريم كه مشاركت كنند.
Price:
2: 300$
3:200$
4:100$
@Raminmousa
@paper4money
@Machine_learn
🔹 Title: Predicting the Order of Upcoming Tokens Improves Language Modeling
🔹 Publication Date: Published on Aug 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19228
• PDF: https://arxiv.org/pdf/2508.19228
• Github: https://github.com/zaydzuhri/token-order-prediction
@Machine_learn
رمضان الکریم ❤️
@Machine_learn
How we made Python's packaging library 3x faster
📚 Read
@Machine_learn
🔹 Title: Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents
🔹 Publication Date: Published on Aug 27
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19493
• PDF: https://arxiv.org/pdf/2508.19493
• Project Page: https://zhixin-l.github.io/SAPA-Bench
• Github: https://github.com/Zhixin-L/SAPA-Bench
@Machine_learn
🔥 Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild
💡 The paper presents Lift4D, a test-time optimization framework for reconstructing dynamic non-rigid objects from monocular video. The problem addressed is the difficulty in reconstructing 4D representations of dynamic objects from single-view video due to the scarcity of 4D training data and the limitations of prior approaches that either directly predict 4D representations or initialize a 3D representation and refine it based on video evidence.
The method involves adapting a single-view 3D reconstruction model to yield temporally consistent per-frame predictions, which provides a coherent initialization for a deformable 3D Gaussian Splatting representation. This representation is then optimized to match the input video through an occlusion-aware optimization that recovers visible surface details and completes unobserved regions using a view-conditioned diffusion prior.
The results show that Lift4D improves over prior 4D reconstruction methods, particularly on challenging in-the-wild sequences with severe occlusions and non-rigid motion. The framework effectively handles complex scenarios by integrating visual cues from direct observations with data-driven priors over geometry and appearance, making it a significant contribution to the field of 4D reconstruction from monocular video.
📅 Published on Jun 22
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.23688
• PDF: https://arxiv.org/pdf/2606.23688
• Project Page: https://lift4d.github.io/
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
Title: A Multi-Task Framework Unifying Classification and Regression for Microgrid Power (kWh) Forecasting: Modified FEDformer
Abstract:........
Keywords: Microgrid Power forecasting; Transformer; FedFormer; Regression; Classification
Price:
2: 500$
3: 400$
Journal: IEEE Power & Energy Society
@Raminmousa
@Paper4money
@Machine_learn
🔥 World Action Models: A Survey
💡 The paper World Action Models A Survey provides a comprehensive overview of World Action Models, which are predictive action systems that generate future states for decision making. These models balance representational richness against computational constraints, and recent developments have led to a blurring of boundaries among various related models. The survey aims to clarify these boundaries and provide a common account of the field.
The authors organize existing works into two complementary views. The first view examines what each method is required to generate, including rendered futures, latent futures, and video generation free action reasoning. The second view decomposes each method into its predictive substrate, backbone, action coupling, and deployment regime. This anatomy allows for a unified discussion of key aspects such as interactability, causality, persistence, physical plausibility, and generalization.
The survey reveals a consistent design pattern in World Action Models, where design choices trade representational richness against compute, memory, latency, and action label cost. The authors find that the field is moving towards methods that generate less of the future while preserving what is required for control. The survey provides a clear and unified account of the field, covering data, evaluation, and open challenges, and provides a foundation for future research in World Action Models.
The main contributions of the paper are to clarify the boundaries and definitions of World Action Models, to provide a comprehensive overview of existing works, and to identify a consistent design pattern in the field. The survey also highlights the key challenges and open issues in World Action Models, including the need for more efficient and effective methods that balance representational richness against computational constraints. Overall, the paper provides a valuable resource for researchers and practitioners in the field of World Action Models, and helps to advance the state of the art in predictive action systems.
📅 Published on Jun 18
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.20781
• PDF: https://arxiv.org/pdf/2606.20781
• Project Page: https://world-action-models.github.io/
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
با عرض سلام یکی از مقالاتمون در حوزه ی wound image classification در ژورنال nature scientific reports ریوایزد خورده و جایگاه های ۲ و ۵ اش قابل اضافه شدن می باشد. دوستانی که نیاز دارن می تونن جهت ثبت اسم به ایدی بنده پیام بدن
Price
2: 300$
5:150$
@Raminmousa
@Paper4money
@Machine_learn
با عرض سلام مقاله MedicalRec توسط بنده و دوستان ارائه شد. این مقاله جهت ارائه ی سیستم پیشنهاد دهنده مدل طبقه بندی برای تصاویر پزشکی میباشد. در ادامه ما می خواهیم MedicalRec2 را توسعه دهیم که یک مدل پیشنهاد دهنده طبقه بند و تقسیم بند در حوزه ی پزشکی می باشد. از این رو نفرات ۲ تا ۶ این مقاله را جهت مشارکت در نظر داریم. هزینه ها از قرار زیر می باشند.
2: 500$
3: 400$
4: 300$
5: 250$
6: 200$
جهت مشارکت با ایدی بنده در ارتباط باشین.
@Raminmousa
@Paper4money
تنها ۳ روز تا سابمیت این مقاله باقی مونده....!
Читать полностью…
با عرض سلام یکی از مقالاتمون در حوزه ی wound image classification در ژورنال nature scientific reports ریوایزد خورده و جایگاه های ۲، ۴ و ۵ اش قابل اضافه شدن می باشد. دوستانی که نیاز دارن می تونن جهت ثبت اسم به ایدی بنده پیام بدن
Price
2: 300$
4: 200$
3:150$
@Raminmousa
@Paper4money
@Machine_learn
🔥 Awesome open-source project to learn more about Transformer Models! 🤖✨
We found this interactive website that shows you visually how transformer models work. 🌐📊
Transformer Explainer:
https://poloclub.github.io/transformer-explainer/
@Machine_learn
Fri, 27 Feb 2026 (showing first 50 of 206 entries )
[1] arXiv:2602.23352 [pdf, html, other]
Stark localization of interacting particles
Wojciech De Roeck, Amirali Hannani, Alessio Lerose, Nathan Vandenbosch
Subjects: Mathematical Physics (math-ph); Disordered Systems and Neural Networks (cond-mat.dis-nn)
[2] arXiv:2602.23350 [pdf, html, other]
A strengthening of the dimensional Brunn-Minkowski conjecture implies the (B)-Conjecture
Sotiris Armeniakos, Jacopo Ulivelli
Comments: Comments are welcome!
Subjects: Functional Analysis (math.FA); Metric Geometry (math.MG)
[3] arXiv:2602.23343 [pdf, html, other]
Cyclic sieving for a class of rectangular domino tableaux
Laura Colmenarejo, Bridget Eileen Tenner, Camryn E. Thompson
Comments: 17 pages
Subjects: Combinatorics (math.CO)
[4] arXiv:2602.23340 [pdf, html, other]
Combinatorial Properties of the Raisonnier Filter
Spyridon Dialiatsis, Yurii Khomskii
Subjects: Logic (math.LO)
[5] arXiv:2602.23326 [pdf, html, other]
Spin Glass Concepts in Computer Science, Statistics, and Learning
Andrea Montanari
Comments: 33 pages; 2 pdf figures
Subjects: Probability (math.PR); Disordered Systems and Neural Networks (cond-mat.dis-nn)
[6] arXiv:2602.23325 [pdf, html, other]
Spanning tight components in 4-uniform hypergraphs
Francesco Di Braccio, Brian Hearn, Joanna Lada, Mihir Neve, Lu-Ming Zhang
Comments: 24 pages, 4 figures
Subjects: Combinatorics (math.CO)
[7] arXiv:2602.23323 [pdf, html, other]
Modeling Large-Scale Adversarial Swarm Engagements using Optimal Control
Claire Walton, Isaac Kaminer, Qi Gong, Abram H. Clark, Theodoros Tsatsanifos
Comments: arXiv admin note: substantial text overlap with arXiv:2108.02311. substantial text overlap with arXiv:2108.02311
Subjects: Optimization and Control (math.OC)
@Machine_learn
✨RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning
📝 Summary:
RoboCurate enhances synthetic robot learning data by evaluating action quality through simulator replay consistency. It also augments observation diversity via image editing and video transfer techniques. This leads to substantial improvements in robot task success rates compared to using real da...
🔹 Publication Date: Published on Feb 21
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.18742
• PDF: https://arxiv.org/pdf/2602.18742
• Project Page: https://seungkukim.github.io/robocurate/
@Machine_learn
هر ثانیه توقف، یعنی از دست رفتن زمان، هزینه و فرصت…
پایداری دیگر یک انتخاب نیست؛ یک ضرورت است.
🚀 ایرانGPU؛جایی که پروژه‌ها متوقف نمی‌شوند.
🏛 تنها و اولین شرکت بورسی هوش مصنوعی ایران
🕒 بیش از ۵ سال سابقه فعالیت حرفه‌ای
🌐 شبکه‌ای از ۲۰+ دیتاسنتر غیرمتمرکز در سراسر کشور
🧠 مناسب تیم‌ها، پژوهشگران و سازمان‌های حرفه‌ای AI
🛟 پشتیبانی ۲۴ ساعته، ۷ روز هفته
📈 تضمین SLA با دسترس‌پذیری 99.9٪ و ارائه سرور داخل ایران
📩 ثبت درخواست مشاوره | شروع مسیر هوشمندانه
https://b2n.ir/qk8423
🔹 Title: CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
🔹 Publication Date: Published on Aug 27
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.20096
• PDF: https://arxiv.org/pdf/2508.20096
• Project Page: https://github.com/OpenIXCLab/CODA
• Github: https://github.com/OpenIXCLab/CODA
@Machine_learn
Dataset Name: Gallstone Dataset (UCI)
Basic Description: Gallstone Dataset (UCI Machine Learning Repository)
📥 DATASET DOWNLOAD INFORMATION
==================================
🔴 Dataset Size: Download dataset as zip (81 kB)
🔰 Direct dataset download link:
URL not found
📊 Additional information:
==================================
File count not found
Views: 1,128
Downloads: 246
📚 RELATED NOTEBOOKS:
==================================
1. Heart Attack Risk Prediction Dataset | Upvotes: 274
URL: https://www.kaggle.com/datasets/iamsouravbanerjee/heart-attack-prediction-dataset
@Machine_learn
با عرض سلام برای مقاله زیر نیاز به نفرات ۲ و ۳ داریم.
KG-Psy: A Knowledge-Graph and GPT-5 Based Framework for Personalized Clinical Decision Support in Bipolar Disorder and Borderline Personality Disorder
Abstract: Accurate diagnosis and personalized treatment planning for complex psychiatric disorders such as Bipolar Disorder (BD) and Borderline Personality Disorder (BPD) remain major challenges due to overlapping symptoms, fluctuating mood patterns, and heterogeneous clinical presentations. To address these challenges, we introduce KG-Psy, a hybrid neuro-symbolic framework that combines a domain-specific psychiatric Knowledge Graph (KG) with the advanced reasoning capabilities of GPT-5.
KG-Psy constructs multi-layer psychiatric knowledge graphs encoding symptom trajectories, neural correlates, pharmacological mechanisms, therapeutic guidelines, comorbidities, and behavioral patterns extracted from large-scale clinical literature. GPT-5 is employed to extract clinical entities, infer latent symptom-neural relationships, assess diagnostic likelihoods, and generate patient-specific treatment recommendations. The integration of structured KG reasoning with LLM-based inference allows KG-Psy to produce interpretable, evidence-supported, and clinically actionable outputs.
We evaluated KG-Psy on 310 de-identified psychiatric case reports and 12 expert-validated benchmark scenarios. The framework achieved 91.5% F1-score in distinguishing BD from BPD and an average pathway confidence of 86.9%, indicating robust multi-step inference. In personalized treatment recommendation tasks, KG-Psy achieved 88.7% accuracy, outperforming LLM-only and KG-only baselines by 23% and 31%, respectively.
....
Keywords: Bipolar Disorder, Borderline Personality Disorder, Knowledge Graph, GPT-5, Personalized Treatment
2 :20 milion
3 :15 milion
@Raminmousa
@Machine_learn
@paper4money
🔹 Title: Self-Rewarding Vision-Language Model via Reasoning Decomposition
🔹 Publication Date: Published on Aug 27
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19652
• PDF: https://arxiv.org/pdf/2508.19652
@Machine_learn