Machine learning books and papers

ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents 25 Feb 2025 · Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie, Feng Zhao · Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning. Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness. To address these challenges, we propose #ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents. ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multi-modal retrieval. To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains. Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach. Notably, ViDoRAG outperforms existing methods by over 10% on the competitive #ViDoSeek benchmark. Paper: https://arxiv.org/pdf/2502.18017v1.pdf Code: https://github.com/Alibaba-NLP/ViDoRAG @Machine_learn

📄The role and application of bioinformatics techniques and tools in drug discovery 📎 Study the paper @Machine_learn

با عرض سلام این مقاله امشب فرایند سابمیتش دوشتانی که نیاز به مشارکت دارن می تونن شرکت کنند. @Raminmousa

DeepSeek-V3/R1 Inference System Overview 📚 Read @Machine_learn

people : Ai is so smart AI :

با عرض سلام نفر سوم از مقاله زير را نياز داريم. Title: Wavelet transform and deep average model for price and illiquidity prediction cryptocurrencies using high-dimensional features 🔸🔸🔸🔸🔸🔸🔸🔸 abstarct: Cryptocurrencies are alternative payment methods that are created using encrypted algorithms. Encryption technologies mean that cryptocurrencies act as both a currency and a virtual accounting system. The global crypto market value is \$2.9 trillion. Hence, it requires high investment requirements. One of the challenging issues in cryptocurrencies is illiquidity. Due to behavioural chaos in the market, some currencies have severe dumps and pumps, which cause concerns for investors. This paper deals with price prediction and illiquidity prediction (converting one asset to another while maintaining its value). The proposed Wavelet Deep average model uses a combination of Wavelet transform and average deep learning models for the final prediction. This model uses the hash rate information of currencies as the main inputs. Then, it achieves the selection of a subset of features using a Random Forest(RF). The selected features are designed by a Wavelet and are considered as the input to the deep network. Four currencies, BTC, Dogecoin, Ethereum(ETH), and Bitcoin Cash(BCH), were considered for model evaluation. In Bitcoin prediction, the lowest MAE for price prediction and illiquidity was achieved, which was 1.19 and 1.49, respectively. Also, the proposed model achieved MAE of 1.99, 3.69, and 2.99 for the illiquidity of three currencies Dogecoin, ETH, and BCH. The implementation codes are available in https://github.com/Ramin1Mousa/. Journal: Neural computing and application (springer) @Raminmousa

📃 A review on federated learning in computational pathology 📎 Study the paper @Machine_learn

Hawk: Learning to Understand Open-World Video Anomalies 27 May 2024 · Jiaqi Tang, Hao Lu, Ruizheng Wu, Xiaogang Xu, Ke Ma, Cheng Fang, Bin Guo, Jiangbo Lu, Qifeng Chen, Ying-Cong Chen · Video Anomaly Detection (#VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (#VLM) to interpret video anomalies precisely. Recognizing the difference in motion information between abnormal and normal videos, Hawk explicitly integrates motion modality to enhance anomaly identification. To reinforce motion attention, we construct an auxiliary consistency loss within the motion and video space, guiding the video branch to focus on the motion modality. Moreover, to improve the interpretation of motion-to-language, we establish a clear supervisory relationship between motion and its linguistic representation. Furthermore, we have annotated over 8,000 anomaly videos with language descriptions, enabling effective training across diverse open-world scenarios, and also created 8,000 question-answering pairs for users' open-world questions. The final results demonstrate that #Hawk achieves SOTA performance, surpassing existing baselines in both video description generation and question-answering. Our codes/dataset/demo will be released at https://github.com/jqtangust/hawk. Paper: https://arxiv.org/pdf/2405.16886v1.pdf Code: https://github.com/jqtangust/hawk Dataset: Hawk Annotation Dataset @Machine_learn

با عرض سلام برای یکی از کارهای سری‌زمانی با استفاده از Whighted Deep Neural Network و Wavelet نیاز به نویسنده مسول داریم. نفر ۴ ام از مقاله خواهند بود. هزینه این مشارکت 250 دلار و دوستانی که نیاز دارند جهت بررسی جزئیات بیشتر به ایدی بنده پیام بدن. @Raminmousa

From System 1 to System 2: A Survey of Reasoning Large Language Models 24 Feb 2025 · Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhijiang Guo, Le Song, Cheng-Lin Liu · Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning #LLMs, analyzing their features, the core methods enabling advanced reasoning, and the evolution of various reasoning LLMs. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time \href{https://github.com/zzli2022/Awesome-Slow-Reason-System}{GitHub Repository} to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field. Paper: https://arxiv.org/pdf/2502.17419v1.pdf Code: https://github.com/zzli2022/awesome-slow-reason-system Datasets: GSM8K - MedQA - MathVista - GPQA - MMLU-Pro - PGPS9K 💠https://t.me/deep_learning_proj

Competitive Programming with Large Reasoning Models OpenAI∗ ▪ Link @Machine_learn

ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs 📚 'Read @Machine_learn

The Hundred-Page Language Models Book 📕 Book @Machine_learn

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement 🖥 Github: https://github.com/thu-coai/AISafetyLab 📕 Paper: https://arxiv.org/abs/2502.16776v1 🌟 Dataset: https://paperswithcode.com/dataset/gptfuzzer @Machine_learn

🎨 Can AI design truly novel concepts like humans? Check SYNTHIA, a breakthrough in T2I generation! 🤖 SYNTHIA composes affordances to create visually novel & functionally coherent designs. 📄 https://arxiv.org/pdf/2502.17793 💻 https://github.com/HyeonjeongHa/SYNTHIA 🎥 https://youtube.com/watch?v=KvsOx44WdzM @Machine_learn

با عرض سلام نياز به نفر سوم در مقاله زير داريم. وضعيت: ريوايزد🔥 💠Advancements in Deep Learning for predicting Drug-Lipid interactions in liposomal drug delivery     🔹Abstract   Liposomal drug delivery systems have improved cancer therapeutics by enhancing drug stability, allowing selective tissue targeting, and reducing off-target effects. One of the main problems, however, is how to maximize drug-lipid interaction as well as develop personalized treatment alternatives. Traditional methods in computational biology, such as molecular dynamics simulations, are useful but have challenges in their scalability and cost of computation. This study focuses on the use of deep learning algorithms, Graph Neural Networks (GNNs), Attention Mechanisms, and Physics-Informed Neural Networks (PINNs) for the prediction and optimization of drug-lipid interactions in liposomal formulations. These models are much more advanced, can handle complex datasets with simplified models, and recognize complicated interaction patterns while adhering to the necessary physics involved in the problem. We highlight the practicality of these models in predicting encapsulation efficiency, drug release kinetics, and developing controlled drug delivery systems for cancer treatment through several case studies. Also, the application of transfer learning and meta-learning improves model transferability in different drug-lipid matrices, which is a step towards personalized medicine. Our results highlight that the combination of deep learning with experimental and clinical evidence enhances predictive performance and expands scope, thereby facilitating the formulation of more exact and individualized treatment modalities. Such an interdisciplinary approach can greatly improve treatment efficacy and expand the horizons of precision medicine in the field of nanomedicine.     Keywords: Liposomal drug delivery, Deep Learning models, Drug-Lipid interactions, Physics-Informed Neural Networks (PINNs), Encapsulation efficiency, Personalized medicine, Nanomedicine.    Journal:https://link.springer.com/journal/11831 If: 9.9 جهت ثبت سفارش به ايدي بنده پيام بدين. @Raminmousa @Paper4money @Machine_learn

یکی از ابزارهای خوبی که بنده تونستم توسعه بدم ابزار Stock Ai می باشد. در این ابزار از ۳۶۰ اندیکاتور استفاده کردم. گزارشات back test این ابزار در ویدیو های زیر موجود می باشد. May 2024 : https://youtu.be/aSS99lynMFQ?si=QSk8VVKhLqO_2Qi3 July 2014: https://youtu.be/ThyZ0mZwsGk?si=FKPK7Hkz-mRx-752&t=209 از این رو سعی میکنیم مقاله ای این کار رو بنویسیم. شروع مقاله ی این کار ۲۰ اسفند خواهد بود. دوستانی که می تونن به هر نحوی کمک کنند تا شروع مقاله می تونن نام نویسی کنند. نفرات ٣ و ٥ اين كار باقي مونده. @Raminmousa @Machine_learn @Paper4money

Slamming: Training a Speech Language Model on One GPU in a Day 19 Feb 2025 · Gallil Maimon, Avishai Elmakies, Yossi Adi · We introduce Slam, a recipe for training high-quality Speech Language Models (SLMs) on a single academic GPU in 24 hours. We do so through empirical analysis of model initialisation and architecture, synthetic training data, preference optimisation with synthetic data and tweaking all other components. We empirically demonstrate that this training recipe also scales well with more compute getting results on par with leading SLMs in a fraction of the compute cost. We hope these insights will make SLM training and research more accessible. In the context of SLM scaling laws, our results far outperform predicted compute optimal performance, giving an optimistic view to #SLM feasibility. See code, data, models, samples at - https://pages.cs.huji.ac.il/adiyoss-lab/slamming . Paper: https://arxiv.org/pdf/2502.15814v1.pdf Code: https://github.com/slp-rl/slamkit https://t.me/deep_learning_proj