¡Ya disponible! Investigación de Telegram 2025 — los principales insights del año 
Machine learning books and papers
Ir al canal en Telegram
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Mostrar más📈 Análisis del canal de Telegram Machine learning books and papers
El canal Machine learning books and papers (@machine_learn) en el segmento lingüístico de Inglés es un actor destacado. Actualmente la comunidad reúne a 24 518 suscriptores, ocupando la posición 8 048 en la categoría Educación y el puesto 13 749 en la región Irán.
📊 Métricas de audiencia y dinámica
Desde su creación el невідомо, el proyecto ha mostrado un crecimiento acelerado, reuniendo a 24 518 suscriptores.
Según los últimos datos del 25 junio, 2026, el canal mantiene una actividad estable. En los últimos 30 días la variación de miembros fue de -164, y en las últimas 24 horas de -1, conservando un alto alcance.
- Estado de verificación: No verificado
- Tasa de interacción (ER): El promedio de interacción de la audiencia es 7.13%. Durante las primeras 24 horas tras publicar, el contenido suele obtener 1.90% de reacciones respecto al total de suscriptores.
- Alcance de las publicaciones: Cada publicación recibe en promedio 1 748 visualizaciones. En el primer día suele acumular 465 visualizaciones.
- Reacciones e interacción: La audiencia responde de forma activa: el promedio de reacciones por publicación es 1.
- Intereses temáticos: El contenido se centra en temas clave como disorder, psy, مقاله, framework, graph.
📝 Descripción y política de contenido
El autor describe el recurso como un espacio para expresar opiniones subjetivas:
“Admin: @Raminmousa
ID: @Machine_learn
link: https://t.me/Machine_learn”
Gracias a la alta frecuencia de actualizaciones (últimos datos recibidos el 26 junio, 2026), el canal mantiene la vigencia y un amplio alcance. La analítica demuestra que la audiencia interactúa activamente con el contenido, lo que lo convierte en un punto de referencia dentro de la categoría Educación.
24 518
Suscriptores
-124 horas
-407 días
-16430 días
Archivo de publicaciones
Constrained Diffusion Implicit Models!
We use diffusion models to solve noisy inverse problems like inpainting, sparse-recovery, and colorization. 10-50x faster than previous methods!
Paper: arxiv.org/pdf/2411.00359
Demo: https://t.co/m6o9GLnnZF
@Machine_learn
Smol TTS models are here! OuteTTS-0.1-350M - Zero shot voice cloning, built on LLaMa architecture, CC-BY license! 🔥
> Pure language modeling approach to TTS
> Zero-shot voice cloning
> LLaMa architecture w/ Audio tokens (WavTokenizer)
> BONUS: Works on-device w/ llama.cpp ⚡
Three-step approach to TTS:
> Audio tokenization using WavTokenizer (75 tok per second).
> CTC forced alignment for word-to-audio token mapping.
> Structured prompt creation w/ transcription, duration, audio tokens.
https://huggingface.co/OuteAI/OuteTTS-0.1-350M
@Machine_learn
📕 Machine Learning for Absolute Beginners
▪️Link
@Machine_learn
Machine Learning with PyTorch and Scikit-Learn Book
📚 book
@Machine_learn
AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent
🖥 Github: https://github.com/thudm/autowebglm
📕 Paper: https://arxiv.org/abs/2404.03648v1
🔥Dataset: https://paperswithcode.com/dataset/mind2web
@Machine_learn
❤️ اکستنشن ChatGPT Search برای مرورگرهای کرومیوم منتشر شد
از طریق این لینک میتونید این افزونه رو دانلود کنید
@Machine_learn
Conformal prediction under ambiguous ground truth
Paper: https://arxiv.org/pdf/2307.09302v2.pdf
Codes:
https://github.com/google-deepmind/uncertain_ground_truth
https://github.com/alaalab/webcp
Dataset: Dermatology ddx dataset
@Machine_learn
Repost from Papers
الحمدالله تو اين بازه ٣ ماه تونستيم مقالات مشاركتي رو تحت وظايف زير انجام بديم:
🔹ثبت ٤ مقاله در حوزه Multi-modal wond classification
🔹ارائه ی دو مقاله در حوزه ی breast cancer segmentation
🔹 ارائه ی سه مقاله در حوزه ی cancer detection
که ۸۰٪ مراحل این مقالات هم تموم شده.
به زودی پس از اتمام این مقالات لیستی از مقالات مشارکتی رو خواهیم داشت .
https://t.me/+SP9l58Ta_zZmYmY0
👩💻 Python Notes for Professionals book
🔗 Book
@Machine_learn
Repost from Github LLMs
📖 LLM-Agent-Paper-List is a repository of papers on the topic of agents based on large language models (LLM)! The papers are divided into categories such as LLM agent architectures, autonomous LLM agents, reinforcement learning (RL), natural language processing methods, multimodal approaches and tools for developing LLM agents, and more.
🖥 Github
https://t.me/deep_learning_proj
💠Title:BERTCaps: BERT Capsule for persian Multi-domain Sentiment Analysis.
🔺Abstract:
Sentiment classification is widely known as a domain-dependent problem. In order to learn an accurate domain-specific sentiment classifier, a large number of labeled samples are needed, which are expensive and time-consuming to annotate. Multi-domain sentiment analysis based on multi-task learning can leverage labeled samples in each single domain, which can alleviate the need for large amount of labeled data in all domains. In this article, the purpose is BERTCaps to provide a multi-domain classifier. In this model, BERT was used for Instance Representation and Capsule was used for instance learning. In the evaluation dataset, the model was able to achieve an accuracy of 0.9712 in polarity classification and an accuracy of 0.8509 in domain classification.
journal: https://www.sciencedirect.com/journal/array
If:2.3
جايگاه ٢ و ٤ اين مقاله رو نياز داريم.
دوستاني كه مايل به شركت هستن مي تونن به ايدي بنده پيام بدن.
@Raminmousa
@Paper4money
@Machine_learn
📑A Survey of Deep Learning Methods for Estimating the Accuracy of Protein Quaternary Structure Models
📎 Study the paper
@Machine_learn
Ms - SmolLM2 1.7B - beats Qwen 2.5 1.5B & Llama 3.21B, Apache 2.0 licensed, trained on 11 Trillion tokens 🔥
> 135M, 360M, 1.7B parameter model
> Trained on FineWeb-Edu, DCLM, The Stack, along w/ new mathematics and coding datasets
> Specialises in Text rewriting, Summarization & Function Calling
> Integrated with transformers & model on the hub!
You can run the 1.7B in less than 2GB VRAM on a Q4 👑
Fine-tune, run inference, test, train, repeat - intelligence is just 5 lines of code away!
https://huggingface.co/collections/HuggingFaceTB/smollm2-6723884218bcda64b34d7db9
@Machine_learn
Repost from Papers
💠Title:BERTCaps: BERT Capsule for persian Multi-domain Sentiment Analysis.
🔺Abstract:
Sentiment classification is widely known as a domain-dependent problem. In order to learn an accurate domain-specific sentiment classifier, a large number of labeled samples are needed, which are expensive and time-consuming to annotate. Multi-domain sentiment analysis based on multi-task learning can leverage labeled samples in each single domain, which can alleviate the need for large amount of labeled data in all domains. In this article, the purpose is BERTCaps to provide a multi-domain classifier. In this model, BERT was used for Instance Representation and Capsule was used for instance learning. In the evaluation dataset, the model was able to achieve an accuracy of 0.9712 in polarity classification and an accuracy of 0.8509 in domain classification.
journal: https://www.sciencedirect.com/journal/array
If:2.3
جايگاه ٢ و ٤ اين مقاله رو نياز داريم.
دوستاني كه مايل به شركت هستن مي تونن به ايدي بنده پيام بدن.
@Raminmousa
@Paper4money
@Machine_learn
تخفيف ٥٠٪🔹
دو پكيچ كدنويسي پايه يادگيري ماشين و يادگيري عميق به همراه ٣٦ بروژه عملي با پشتيباني ٢ ماهه .
جهت سفارش به ايدي بنده پيام بدين.
🔺
هزینه هر دو پک با تخفيف ۱۵۰۰ هزار ميباشد.
@Raminmousa
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
🖥 Github: https://github.com/mark12ding/sam2long
📕 Paper: https://arxiv.org/abs/2410.16268v1
🤗 HF: https://huggingface.co/papers/2410.16268
@Machine_learn
🌟 Aya Expanse
🟢Aya Expanse 32B
🟢Aya Expanse 8B
🟠Aya Expanse 32B-GGUF
🟠Aya Expanse 8B-GGUF
Expanse 8B Transformers :
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "CohereForAI/aya-expanse-8b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Format the message with the chat template
messages = [{"role": "user", "content": " %prompt% "}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>%prompt%<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
gen_tokens = model.generate(
input_ids,
max_new_tokens=100,
do_sample=True,
temperature=0.3,
)
gen_text = tokenizer.decode(gen_tokens[0])
print(gen_text)
🟡GGUF 32B
🟡GGUF 8B
🟡Demo
@Machine_learn