Available now! Telegram Research 2025 — the year's key insights 
Machine learning books and papers
Open in Telegram
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Show more📈 Analytical overview of Telegram channel Machine learning books and papers
Channel Machine learning books and papers (@machine_learn) in the English language segment is an active participant. Currently, the community unites 24 518 subscribers, ranking 8 048 in the Education category and 13 749 in the Iran region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 24 518 subscribers.
According to the latest data from 25 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by -164 over the last 30 days and by -1 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 7.13%. Within the first 24 hours after publication, content typically collects 1.90% reactions from the total number of subscribers.
- Post reach: On average, each post receives 1 748 views. Within the first day, a publication typically gains 465 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 1.
- Thematic interests: Content is focused on key topics such as disorder, psy, مقاله, framework, graph.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“Admin: @Raminmousa
ID: @Machine_learn
link: https://t.me/Machine_learn”
Thanks to the high frequency of updates (latest data received on 26 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Education category.
24 518
Subscribers
-124 hours
-407 days
-16430 days
Posts Archive
Repost from Papers
يكي از بهترين موضوعات در طبقه بندي متن؛ تحليل احساس چند دامنه اي مي باشد. براي اين منظور مدلي تحت عنوان
Title: TRCAPS: The Transformer-based Capsule Approach for Persian Multi-
Domain Sentiment Analysis
طراحي كرديم كه نتايج خيلي بهتري نسبت به IndCaps داشته است.
دوستاني كه نياز به مقاله تو حوزه NLP دارن مي تونن تا اخر اين هفته داخل اين مقاله شركت كنند.
ژورنال هدف Array elsevier مي باشد.
شركت كنندگان داخل اين مقاله نياز به انجام تسك هايي نيز مي باشند.
@Raminmousa
@Machine_learn
@Paper4money
📄 Advances of Artificial Intelligence in Anti-Cancer Drug Design: A Review of the Past Decade
📎 Study the paper
@Machine_learn
🌟 Zamba2-Instruct
🟢Zamba2-1.2B-instruct;
🟠Zamba2-2.7B-instruct.
# Clone repo
git clone https://github.com/Zyphra/transformers_zamba2.git
cd transformers_zamba2
# Install the repository & accelerate:
pip install -e .
pip install accelerate
# Inference:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)
user_turn_1 = "user_prompt1."
assistant_turn_1 = "assistant_prompt."
user_turn_2 = "user_prompt2."
sample = [{'role': 'user', 'content': user_turn_1}, {'role': 'assistant', 'content': assistant_turn_1}, {'role': 'user', 'content': user_turn_2}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))
🖥GitHub
@Machine_learn
Prompt Engineering Techniques: Comprehensive Repository for Development and Implementation 🖋️
📓 Github
@Machine_learn
Repost from Github LLMs
🔥 NVIDIA silently release a Llama 3.1 70B fine-tune that outperforms
GPT-4o and Claude Sonnet 3.5
Llama 3.1 Nemotron 70B Instruct a further RLHFed model on
huggingface
https://huggingface.co/collections/nvidia/llama-31-nemotron-70b-670e93cd366feea16abc13d8
✅https://t.me/deep_learning_proj
✔️ LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
New pipeline for selecting high-quality long-take videos and generating temporally dense captions.
Dataset with four key features essential for training long video generation models: (1) long videos covering at least 10 seconds, (2) long-take videos without cuts, (3) large motion and diverse contents, and (4) temporally dense captions.
🖥 Github: https://github.com/silentview/lvd-2m
📕 Paper: https://arxiv.org/abs/2410.10816v1
🖥 Dataset: https://paperswithcode.com/dataset/howto100m
🔸@Machine_learn
Repost from Papers
با عرض سلام در يكي از مقالاتمون با موضوع
multimodal capsule fusion with self-attention approach for alzheimer disease classification
نياز به نفر دوم هستيم. تسك ها به صورت مشخص شده براي نفر دوم در نظر گرفته شده است. دوستاني كه ميخوان مشاركت كنن به بنده
پيام بدن با تشكر.
@Raminmousa
@Machine_learn
@Paper4money
📃Network Modeling and Control of Dynamic Disease Pathways, Review and Perspectives
📎 Study the paper
@Machine_learn
پروژه های بیشتر شبیه این ریپورت داخل این پک قرار داره. دوستانی که نیاز دارن می تونن به ایدی بنده مراجعه کنن.
@Raminmousa
Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts
💻 Github: https://github.com/freedomintelligence/apollomoe
🔖 Paper: https://arxiv.org/abs/2410.10626v1
🤗 Dataset: https://paperswithcode.com/dataset/mmlu
✅@Machine_learn
با عرض سلام خيلي از دوستان در رابطي با طراحي صفر تا صد پروژه هاي ديپ از بنده سوال پرسيدن داخل پك زير ٣٦ پروژه رو با جزئيات شرح دادم:
1-Deep Learning Basic
-01_Introduction
--01_How_TensorFlow_Works
2-Classification apparel
-Classification apparel double capsule
-Classification apparel double cnn
3-ALZHEIMERS USING CNN(ResNet)
4-Fake News (Covid-19 dataset)
-Multi-channel
-3DCNN model
-Base line+ Char CNN
-Fake News Covid CapsuleNet
5-3DCNN Fake News
6-recommender systems
-GRU+LSTM MovieLens
7-Multi-Domain Sentiment Analysis
-Dranziera CapsuleNet
-Dranziera CNN Multi-channel
-Dranziera LSTM
8-Persian Multi-Domain SA
-Bi-GRU Capsule Net
-Multi-CNN
9-Recommendation system
-Factorization Recommender, Ranking Factorization Recommender, Item Similarity Recommender (turicreate)
-SVD, SVD++, NMF, Slope One, k-NN, Centered k-NN, k-NN Baseline, Co-Clustering(surprise)
10-NihX-Ray
-optimized CNN on FullDataset Nih-Xray
-MobileNet
-Transfer learning
-Capsule Network on FullDataset Nih-Xray
دوستاني كه نياز به اين پروژه ها دارن ميتونن با بنده در ارتباط باشن.
@Raminmousa
@Machine_learn
