Machine learning books and papers
前往频道在 Telegram
📈 Telegram 频道 Machine learning books and papers 的分析概览
频道 Machine learning books and papers (@machine_learn) 英语 语言赛道中的 是活跃参与者。目前社区聚集了 24 125 名订阅者，在 教育 类别中位列第 8 267，并在 伊朗 地区排名第 14 567 位。
📊 受众指标与增长动态
自 невідомо 创建以来，项目保持高速增长，吸引了 24 125 名订阅者。
根据 25 十月, 2026 的最新数据，频道保持稳定运转。过去 30 天订阅人数变化为 -172，过去 24 小时变化为 -2，整体触达仍然可观。
- 认证状态： 未认证
- 互动率 (ER)： 平均受众互动率为 6.51%。内容发布后 24 小时内通常能获得 1.93% 的反应，占订阅者总量。
- 帖子覆盖： 每篇帖子平均可获得 1 570 次浏览，首日通常累积 466 次浏览。
- 互动与反馈： 受众积极参与，单帖平均反应数为 2。
- 主题关注点： 内容集中在 disorder, psy, مقاله, framework, graph 等核心主题上。
📝 描述与内容策略
作者将该频道定位为表达主观观点的平台：
“Admin: @Raminmousa1
ID: @Machine_learn
link: https://t.me/Machine_learn”
凭借高频更新（最新数据采集于 26 十月, 2026），频道始终保持新鲜度与高覆盖。分析显示受众积极互动，使其成为 教育 类别中的关键影响点。
24 125
订阅者
-224 小时
-537 天
-17230 天
正在加载数据
相似频道
标签云
进出提及
---
---
---
---
---
---
吸引订阅者
十月 '2610月 '26
十月 '26
+11
在1个频道中
九月 '26
+13
在2个频道中
Get PRO
八月 '26
+76
在1个频道中
Get PRO
七月 '26
+83
在2个频道中
Get PRO
六月 '26
+44
在1个频道中
Get PRO
五月 '26
+45
在2个频道中
Get PRO
四月 '26
+45
在0个频道中
Get PRO
三月 '26
+2
在0个频道中
Get PRO
二月 '26
+14
在1个频道中
Get PRO
一月 '26
+10
在1个频道中
Get PRO
十二月 '25
+251
在2个频道中
Get PRO
十一月 '25
+522
在11个频道中
Get PRO
十月 '25
+1 065
在2个频道中
Get PRO
九月 '25
+794
在2个频道中
Get PRO
八月 '25
+941
在11个频道中
Get PRO
七月 '25
+835
在3个频道中
Get PRO
六月 '25
+734
在3个频道中
Get PRO
五月 '25
+956
在2个频道中
Get PRO
四月 '25
+1 898
在4个频道中
Get PRO
三月 '25
+658
在7个频道中
Get PRO
二月 '25
+44
在4个频道中
Get PRO
一月 '25
+92
在8个频道中
Get PRO
十二月 '24
+134
在5个频道中
Get PRO
十一月 '24
+394
在13个频道中
Get PRO
十月 '24
+463
在6个频道中
Get PRO
九月 '24
+249
在4个频道中
Get PRO
八月 '24
+387
在3个频道中
Get PRO
七月 '24
+220
在1个频道中
Get PRO
六月 '24
+228
在11个频道中
Get PRO
五月 '24
+422
在2个频道中
Get PRO
四月 '24
+611
在11个频道中
Get PRO
三月 '24
+731
在4个频道中
Get PRO
二月 '24
+1 021
在1个频道中
Get PRO
一月 '24
+1 100
在13个频道中
Get PRO
十二月 '23
+628
在0个频道中
Get PRO
十一月 '23
+409
在11个频道中
Get PRO
十月 '23
+296
在9个频道中
Get PRO
九月 '23
+365
在0个频道中
Get PRO
八月 '23
+467
在0个频道中
Get PRO
七月 '23
+715
在0个频道中
Get PRO
六月 '23
+268
在0个频道中
Get PRO
五月 '23
+107
在0个频道中
Get PRO
四月 '23
+107
在0个频道中
Get PRO
三月 '23
+249
在0个频道中
Get PRO
二月 '23
+110
在0个频道中
Get PRO
一月 '23
+163
在0个频道中
Get PRO
十二月 '22
+118
在0个频道中
Get PRO
十一月 '22
+165
在0个频道中
Get PRO
十月 '22
+101
在0个频道中
Get PRO
九月 '22
+177
在0个频道中
Get PRO
八月 '22
+220
在0个频道中
Get PRO
七月 '22
+229
在0个频道中
Get PRO
六月 '22
+56
在0个频道中
Get PRO
五月 '22
+296
在0个频道中
Get PRO
四月 '22
+411
在0个频道中
Get PRO
三月 '22
+47
在0个频道中
Get PRO
二月 '22
+34
在0个频道中
Get PRO
一月 '22
+44
在0个频道中
Get PRO
十二月 '21
+59
在0个频道中
Get PRO
十一月 '21
+59
在0个频道中
Get PRO
十月 '21
+109
在0个频道中
Get PRO
九月 '21
+454
在0个频道中
Get PRO
八月 '21
+251
在0个频道中
Get PRO
七月 '21
+84
在0个频道中
Get PRO
六月 '21
+183
在0个频道中
Get PRO
五月 '21
+126
在0个频道中
Get PRO
四月 '21
+116
在0个频道中
Get PRO
三月 '21
+101
在0个频道中
Get PRO
二月 '21
+601
在0个频道中
Get PRO
一月 '21
+167
在0个频道中
Get PRO
十二月 '20
+8 834
在0个频道中
| 日期 | 订阅者增长 | 提及 | 频道 | |
| 27 十月 | 0 | |||
| 26 十月 | 0 | |||
| 25 十月 | 0 | |||
| 24 十月 | 0 | |||
| 23 十月 | 0 | |||
| 22 十月 | 0 | |||
| 21 十月 | 0 | |||
| 20 十月 | 0 | |||
| 19 十月 | 0 | |||
| 18 十月 | 0 | |||
| 17 十月 | 0 | |||
| 16 十月 | 0 | |||
| 15 十月 | 0 | |||
| 14 十月 | 0 | |||
| 13 十月 | +6 | |||
| 12 十月 | 0 | |||
| 11 十月 | +2 | |||
| 10 十月 | 0 | |||
| 09 十月 | +1 | |||
| 08 十月 | 0 | |||
| 07 十月 | +1 | |||
| 06 十月 | 0 | |||
| 05 十月 | 0 | |||
| 04 十月 | +1 | |||
| 03 十月 | 0 | |||
| 02 十月 | 0 | |||
| 01 十月 | 0 |
频道帖子
سلام
فقط دو روز تا سابمیت نهایی این مقاله باقی مونده دوستانی که نیاز دارن بهم پیام بدن.
@Raminmousa1
| 2 |  🔥 OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
💡 Summary
🔗 Links:
GitHub: https://github.com/huggingface
arXiv: https://arxiv.org/abs/2609.39490
PDF: https://arxiv.org/pdf/2609.39490
Project Page: https://pku-value-lab.github.io/OmniReasoning-Homepage/
📊 Datasets citing this paper:
https://huggingface.co/datasets/mjuicem/OmniReasoning-131K
https://huggingface.co/datasets/mjuicem/OmniReasoningBench
@Machine_learn | 910 |
| 3 |  با عرض سلام این مقاله نفرات ۲ و ۳ رو میخواییم اسم بنویسم. هزینه به ترتیب ۳۰۰ و ۲۰۰ دلار. اگه کسی نیاز داشت به ایدیم پیام بده.
@Raminmousa1 | 445 |
| 4 | با عرض سلام این مقاله نفرات ۲ و ۳ رو میخواییم اسم بنویسم. هزینه به ترتیب ۳۰۰ و ۲۰۰ دلار. اگه کسی نیاز داشت به ایدیم پیام بده.
@Raminmousa1 | 1 723 |
| 5 | preprints202504.2464.v1.pdf | 1 892 |
| 6 |  🔥 Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training
🔗 Links:
GitHub: https://github.com/huggingface
arXiv: https://arxiv.org/abs/2610.05416
PDF: https://arxiv.org/pdf/2610.05416
Project Page: https://francis-rings.github.io/Prism/
🤖 Models citing this paper:
https://huggingface.co/FrancisRing/Prism
🚀 Spaces citing this paper:
https://huggingface.co/spaces/bibibi12345/Prism
https://huggingface.co/spaces/tardellirs/model-pulse
@Machine_learn | 1 892 |
| 7 |  🔥 Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
🔗 Links:
GitHub: https://github.com/huggingface
arXiv: https://arxiv.org/abs/2610.02521
PDF: https://arxiv.org/pdf/2610.02521
Project Page: https://spatial-memory-intelligence.github.io/
@Machine_learn | 1 684 |
| 8 | High-Impact Research Paper – MedicalRec / GROKRec
Title: MedicalRec
Price: $1,000 USD
Looking for a ready-to-publish, novel research paper in medical AI and sustainable deep learning?
This paper introduces GROKRec, an innovative recommender framework that uses embedding vectors from the Grok language model combined with numerical features to recommend the best deep learning model for any medical image classification task — without the need to train dozens of models on the target dataset.
Key Highlights:
Addresses major real-world problems: high computational cost, energy consumption, carbon emissions, and e-waste caused by training large DL models.
Built on a newly curated public dataset MedicalRec-Bench II containing 3,500 research papers and over 6,000 model evaluation records across diverse medical imaging tasks.
Evaluated under four feature configurations (MedicalRec I) using 13 different models.
Achieves strong performance with HitRate@100 ranging from 72.43% to 77.08% — the highest among compared approaches.
Uses composite loss functions and regularization techniques for accurate recommendations.
Fully eliminates the trial-and-error process of training multiple models, significantly reducing carbon footprint.
This is a complete, self-contained research contribution with a novel dataset and a practical, environmentally conscious solution for the medical AI community.
Ideal for: Researchers, academic publishers, journals, or institutions looking for high-quality, ready-to-use work in medical image analysis, recommender systems, and green AI.
Price: $1,000 USD (one-time transfer of ownership/rights as agreed).
Interested? Contact me for the full manuscript, dataset details, or to discuss terms.
@Raminmousa1 | 2 030 |
| 9 |  🔥 FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
🔗 Links:
GitHub: https://github.com/huggingface
arXiv: https://arxiv.org/abs/2609.38839
PDF: https://arxiv.org/pdf/2609.38839
Project Page: https://yinbo0927.github.io/FrameMorrow/
@Machine_learn | 1 559 |
| 10 |  🔥 TAPNext: Tracking Any Point (TAP) as Next Token Prediction
🔗 Links:
GitHub: https://github.com/huggingface
arXiv: https://arxiv.org/abs/2504.05579
PDF: https://arxiv.org/pdf/2504.05579
Project Page: https://tap-next.github.io/
@machine_learn | 1 557 |
| 11 |  ☁️ ابرک ویراک را 24 ساعت رایگان تست کنید!
قبل از خرید، سرویس ابری VirakCloud را با شرایط واقعی امتحان کنید:
🎁 24 ساعت تست رایگان
🚀 پهنای باند اختصاصی با ترافیک نامحدود
⏱️ پرداخت ساعتی؛ فقط به اندازه مصرفتان هزینه کنید
بدون نیاز به تعهد بلندمدت، ابرک خودتان را بسازید، عملکرد سرویس را بررسی کنید و بعد تصمیم بگیرید.
برای دریافت کد تست رایگان، کلمه «تست» را به آیدی زیر ارسال کنید:
https://t.me/cloud_virak
👇 سپس وارد پنل VirakCloud شوید، کد را وارد کنید و ابرک خود را بسازید:
🔗 https://B2n.ir/qy4432
☎️ 02191555530
🌐 virakcloud.com | 417 |
| 12 |  📖 "A Little Book on the Fundamentals of Generative AI" - an intuitive introduction to the mathematics:
arxiv.org/pdf/2605.29713
#GenerativeAI #Mathematics #DeepLearning #AIResearch #MachineLearning #arXiv
✨ Join Best TG Channels https://t.me/addlist/0f6vfFbEMdAwODBk
@Machine_learn | 1 839 |
| 13 |  🔎 #وبینار عملی ریشه‌یابی خطا با Sentry
🔮 در وبینار «از گزارش خطای کاربر تا ریشه‌یابی مشکل با Sentry» با یک سناریوی عملی، مسیر رسیدن از گزارش یک مشکل به سرنخ‌های لازم برای ریشه‌یابی آن را دنبال می‌کنیم.
در این وبینار:
• #سنتری را راه‌اندازی می‌کنیم و به یک اپلیکیشن متصل می‌شویم
• یک خطا را ثبت می‌کنیم و با اطلاعاتی که Sentry در اختیارمان می‌گذارد، علت آن را بررسی می‌کنیم
• با Session Replay اتفاقات پیش از بروز خطا را از دید کاربر بازبینی می‌کنیم
• با Trace و Span مسیر اجرای عملیات را دنبال و گلوگاه‌های عملکردی اپلیکیشن را پیدا می‌کنیم.
📣 ارائه‌دهنده: علیرضا بانشی | SaaS Team Lead در هم‌روش
📅 سه‌شنبه ۲۱ مهر ساعت ۱۹
🔗 ثبت‌نام رایگان:
https://hmrv.sh/EdN7gd
☁️@hamravesh | 540 |
| 14 |  با عرض سلام این مقاله به صورت کامل واگذار میشه به همراه پیاده سازی مجموعه داده و قالب latex. هزینه کار ۱۰۰۰ دلار
@Raminmousa1 | 1 911 |
| 15 |  Understanding Attention
From Q, K, V to Modern Transformer Attention
https://drive.google.com/file/d/1fCHQ5xCQJ6jZszAYf-qP3VIySbzFIEDv/view
@Machine_learn | 2 060 |
| 16 |  Uniface
Automate face detection, recognition, and analysis of key facial landmarks with the Uniface Python library.
https://github.com/yakhyo/uniface
@Machine_learn | 1 868 |
| 17 | For Sale: High-Impact Research Paper – MedicalRec / GROKRec
Title: MedicalRec
Price: $1,000 USD
Looking for a ready-to-publish, novel research paper in medical AI and sustainable deep learning?
This paper introduces GROKRec, an innovative recommender framework that uses embedding vectors from the Grok language model combined with numerical features to recommend the best deep learning model for any medical image classification task — without the need to train dozens of models on the target dataset.
Key Highlights:
Addresses major real-world problems: high computational cost, energy consumption, carbon emissions, and e-waste caused by training large DL models.
Built on a newly curated public dataset MedicalRec-Bench II containing 3,500 research papers and over 6,000 model evaluation records across diverse medical imaging tasks.
Evaluated under four feature configurations (MedicalRec I) using 13 different models.
Achieves strong performance with HitRate@100 ranging from 72.43% to 77.08% — the highest among compared approaches.
Uses composite loss functions and regularization techniques for accurate recommendations.
Fully eliminates the trial-and-error process of training multiple models, significantly reducing carbon footprint.
This is a complete, self-contained research contribution with a novel dataset and a practical, environmentally conscious solution for the medical AI community.
Ideal for: Researchers, academic publishers, journals, or institutions looking for high-quality, ready-to-use work in medical image analysis, recommender systems, and green AI.
Price: $1,000 USD (one-time transfer of ownership/rights as agreed).
Interested? Contact me for the full manuscript, dataset details, or to discuss terms.
@Raminmousa1 | 2 127 |
| 18 | For Sale: High-Impact Research Paper – MedicalRec / GROKRec
Title: MedicalRec
Price: $1,000 USD
Looking for a ready-to-publish, novel research paper in medical AI and sustainable deep learning?
This paper introduces GROKRec, an innovative recommender framework that uses embedding vectors from the Grok language model combined with numerical features to recommend the best deep learning model for any medical image classification task — without the need to train dozens of models on the target dataset.
Key Highlights:
Addresses major real-world problems: high computational cost, energy consumption, carbon emissions, and e-waste caused by training large DL models.
Built on a newly curated public dataset MedicalRec-Bench II containing 3,500 research papers and over 6,000 model evaluation records across diverse medical imaging tasks.
Evaluated under four feature configurations (MedicalRec I) using 13 different models.
Achieves strong performance with HitRate@100 ranging from 72.43% to 77.08% — the highest among compared approaches.
Uses composite loss functions and regularization techniques for accurate recommendations.
Fully eliminates the trial-and-error process of training multiple models, significantly reducing carbon footprint.
This is a complete, self-contained research contribution with a novel dataset and a practical, environmentally conscious solution for the medical AI community.
Ideal for: Researchers, academic publishers, journals, or institutions looking for high-quality, ready-to-use work in medical image analysis, recommender systems, and green AI.
Price: $1,000 USD (one-time transfer of ownership/rights as agreed).
Interested? Contact me for the full manuscript, dataset details, or to discuss terms.
@Raminmousa1 | 1 |
| 19 | #for_sell
@Raminmousa1 | 1 579 |
| 20 |  ❇️ MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning 🔥
Source code: https://github.com/xiaomi-mlab/Minddrive
@Machine_learn | 2 410 |
