Machine learning books and papers

Graph Theory and Additive Combinatorics Exploring Structure and Randomness 📚 link @Machine_learn

Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement 🖥 Github: https://github.com/dvlab-research/Seg-Zero 📕 Paper: https://arxiv.org/abs/2503.06520v1 🌟 Dataset: https://paperswithcode.com/dataset/refcoco 📌 Model: https://huggingface.co/Ricky06662/Seg-Zero-7B @Machine_learn

با عرض سلام در ادامه ی کار تحقیقاتی یک مقاله مروری در حوزه پاتولوژی رو می خواهیم بنویسیم. دوستانی که مایل هستن نفرات ۲ و ٣ این موضوع رو می تونن شرکت کنن. ✅زمان تقریبی شروع ۲۰ فروردین. Journal: scientific reports https://www.nature.com/srep/ Price: 2: 400$ 3: 300$ توضیحات کامل و نحوه نگارش هر بخش رو خودم کمک میکنم. @Raminmousa @Machine_learn @Paper4money

تنها نفر ۲ و ۳ از این باقی موندن....!

٥ رزرو شد...!

با عرض سلام در ادامه ی کار تحقیقاتی یک مقاله مروری در حوزه پاتولوژی رو می خواهیم بنویسیم. دوستانی که مایل هستن نفرات ۲ تا ۵ این موضوع رو می تونن شرکت کنن. ✅زمان تقریبی شروع ۲۰ فروردین. Journal: scientific reports https://www.nature.com/srep/ Price: 2: 400$ 3: 300$ 4: 200$ 5: 150$ توضیحات کامل و نحوه نگارش هر بخش رو خودم کمک میکنم. @Raminmousa @Machine_learn @Paper4money

Introduction to Graph Neural Networks: A Starting Point for Machine Learning Engineers 📓 Paper @Machine_learn

با عرض سلام در ادامه ی کار تحقیقاتی یک مقاله مروری در حوزه پاتولوژی رو می خواهیم بنویسیم. دوستانی که مایل هستن نفرات ۲ تا ۵ این موضوع رو می تونن شرکت کنن. ✅زمان تقریبی شروع ۲۰ فروردین. Journal: Nature ( Modern Phatology) Price: 2: 400$ 3: 300$ 4: 200$ 5: 150$ توضیحات کامل و نحوه نگارش هر بخش رو خودم کمک میکنم. @Raminmousa @Machine_learn @Paper4money

PiEEG kit - bioscience Lab in home for your Brain and Body 🖥 Github: https://github.com/pieeg-club/PiEEG_Kit 📕 Paper: https://arxiv.org/abs/2503.13482 🌟 Methods: https://paperswithcode.com/task/eeg-1 @Machine_learn

Executable Code Actions Elicit Better LLM Agents 1 Feb 2024 · Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges. LLM agents are typically prompted to produce actions by generating #JSON or text in a pre-defined format, which is usually limited by constrained action space (e.g., the scope of pre-defined tools) and restricted flexibility (e.g., inability to compose multiple tools). This work proposes to use executable Python code to consolidate LLM agents' actions into a unified action space (CodeAct). Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. Our extensive analysis of 17 LLMs on API-Bank and a newly curated benchmark shows that CodeAct outperforms widely used alternatives (up to 20% higher success rate). The encouraging performance of CodeAct motivates us to build an open-source #LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language. To this end, we collect an instruction-tuning dataset CodeActInstruct that consists of 7k multi-turn interactions using CodeAct. We show that it can be used with existing data to improve models in agent-oriented tasks without compromising their general capability. CodeActAgent, finetuned from Llama2 and Mistral, is integrated with #Python interpreter and uniquely tailored to perform sophisticated tasks (e.g., model training) using existing libraries and autonomously self-debug. Paper: https://arxiv.org/pdf/2402.01030v4.pdf Codes: https://github.com/epfllm/megatron-llm https://github.com/xingyaoww/code-act Datasets: MMLU - GSM8K - HumanEval - MATH @Machine_learn

Jointly announcing EAGLE-3 with SGLang: Setting a new record in LLM inference acceleration! - 5x🚀than vanilla (on HF) - 1.4x🚀than EAGLE-2 (on HF) - A record of ~400 TPS on LLama 3.1 8B with a single H100 (on SGLang) - 1.65x🚀in latency even for large bs=64 (on SGLang) - A new scaling law: more training data, better speedup - Apache 2.0 Paper: https://arxiv.org/abs/2503.01840 Code: https://github.com/SafeAILab/EAGLE SGLang version: https://github.com/sgl-project/sglang/pull/4247 @Machine_learn

مقاله ی طبقه بندی زخم چند وجهی که در یکی از بهترین ژورنال های Elsevier به چاپ رسوندیم. Multi-modal wound classification using wound image and location by Swin Transformer and Transformer ✅Accepted ✅ Author: Ramin Mousa, Behnaz Rezaei, Laya Mahmoudi, Jafar Abdollahi If: 7.5 Journal: https://www.sciencedirect.com/journal/expert-systems-with-applications Paper: Link @Machine_learn

مقاله ی طبقه بندی زخم چند وجهی که در یکی از بهترین ژورنال های Elsevier به چاپ رسوندیم. Multi-modal wound classification using wound image and location by Swin Transformer and Transformer ✅Accepted ✅ Author: Ramin Mousa, Behnaz Rezaei, Laya Mahmoudi, Jafar Abdollahi If: 7.5 Journal: https://www.sciencedirect.com/journal/expert-systems-with-applications Link @Machine_learn

📃 Biological Multi-Layer and Single Cell Network-Based Multiomics Models - a Review 📎 Study the paper @Machine_learn

You don't need to buy a GPU for machine learning work! There are other alternatives. Here are some: 1. Google Colab 2. Kaggle 3. Deepnote 4. AWS SageMaker 5. GCP Notebooks 6. Azure Notebooks 7. Cocalc 8. Binder 9. Saturncloud 10. Datablore 11. IBM Notebooks 12. Ola kutrim @Machine_learn

🎁 جشنواره نوروزی آکادمی همراه اول آغاز شد! ❗️ یکبار برای یک سال 🎉 به مناسبت عید نوروز طرح ویژه «اشتراک آموزشی» ارائه شد. با خرید این اشتراک می‌تونی به صورت نامحدود به همه دوره‌های آموزشی دسترسی داشته باشی! و نیازی نیست که برای خرید هر دوره هزینه جداگانه‌ای انجام بدی. برخی از مزایای طرح اشتراک آموزشی: 🔸دسترسی نامحدود به ۲۰۰۰ ساعت محتوای آموزشی متنوع 🔸 بهره‌گیری از برترین اساتید صنعت و دانشگاه 🔸 آموزش‌های کاربردی شغل محور 🔸گواهینامه معتبر آموزشی ⚠️مهلت خرید: فقط تا ۱۵ فروردین ۱۴۰۴ 🚫(ظرفیت محدود) 🌐 جهت ثبت‌نام و مشاهده طرح‌های پیشنهادی به لینک زیر مراجعه کنید. https://link.hamrah.academy/yob @hamrah_academy | آکادمی همراه

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL 10 Mar 2025 · Yingzhe Peng, Gongrui Zhang, Miaosen Zhang, Zhiyuan You, Jie Liu, Qipeng Zhu, Kai Yang, Xingzhong Xu, Xin Geng, Xu Yang Enhancing reasoning in Large Multimodal Models (#LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B-parameter architectures where architectural constraints limit reasoning capacity and modality alignment. While rule-based reinforcement learning (RL) excels in text-only domains, its multimodal extension confronts two critical barriers: (1) data limitations due to ambiguous answers and scarce complex reasoning examples, and (2) degraded foundational reasoning induced by multimodal pretraining. To address these challenges, we propose \textbf{\method}, a two-stage framework adapting rule-based RL for multimodal reasoning through \textbf{Foundational Reasoning Enhancement (FRE)} followed by \textbf{Multimodal Generalization Training (MGT)}. The FRE stage first strengthens reasoning abilities using text-only data with rule-based RL, then the MGT stage generalizes these reasoning capabilities to multimodal domains. Experiments on Qwen2.5-VL-Instruct-3B demonstrate that \method achieves 4.83\% and 4.5\% average improvements over baselines in multimodal and text-only benchmarks, respectively, with a 3.63\% gain in complex Football Game tasks. These results validate that text-based reasoning enhancement enables effective multimodal generalization, offering a data-efficient paradigm that bypasses costly high-quality multimodal training data. Paper: https://arxiv.org/pdf/2503.07536v1.pdf code: https://github.com/tidedra/lmm-r1 @Machine_learn