23171
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
22 Feb 2024 · Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, Monica S. Lam ·
We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages. This underexplored problem poses new challenges at the pre-writing stage, including how to research the topic and prepare an outline prior to writing. We propose STORM, a writing system for the Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking. STORM models the pre-writing stage by (1) discovering diverse perspectives in researching the given topic, (2) simulating conversations where writers carrying different perspectives pose questions to a topic expert grounded on trusted Internet sources, (3) curating the collected information to create an outline. For evaluation, we curate FreshWiki, a dataset of recent high-quality Wikipedia articles, and formulate outline assessments to evaluate the pre-writing stage. We further gather feedback from experienced Wikipedia editors. Compared to articles generated by an outline-driven retrieval-augmented baseline, more of STORM's articles are deemed to be organized (by a 25% absolute increase) and broad in coverage (by 10%). The expert feedback also helps identify new challenges for generating grounded long articles, such as source bias transfer and over-association of unrelated facts.
Paper: https://arxiv.org/pdf/2402.14207v2.pdf
Codes:
https://github.com/assafelovic/gpt-researcher
https://github.com/stanford-oval/storm
@Machine_learn
DATA SCIENCE AND DATA
ANALYTICS OPPORTUNITIES AND CHALLENGES
Edited by
Amit Kumar Tyagi
#Book
@Machine_learn
دوستانی که مایل به شرکت در این مقاله می باشند اخرین فرصت تا فردا شب...!
Читать полностью…
Efficient Reasoning with Hidden Thinking
Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities in Multimodal Large Language Models (MLLMs). However, the verbose nature of textual reasoning introduces significant inefficiencies. In this work, we propose
(as hidden llama), an efficient reasoning framework that leverages reasoning CoTs at hidden latent space. We design the Heima Encoder to condense each intermediate CoT into a compact, higher-level hidden representation using a single thinking token, effectively minimizing verbosity and reducing the overall number of tokens required during the reasoning process. Meanwhile, we design corresponding Heima Decoder with traditional Large Language Models (LLMs) to adaptively interpret the hidden representations into variable-length textual sequence, reconstructing reasoning processes that closely resemble the original CoTs. Experimental results across diverse reasoning MLLM benchmarks demonstrate that Heima model achieves higher generation efficiency while maintaining or even better zero-shot task accuracy. Moreover, the effective reconstruction of multimodal reasoning processes with Heima Decoder validates both the robustness and interpretability of our approach.
Paper: https://arxiv.org/pdf/2501.19201v1.pdf
Code: https://github.com/shawnricecake/heima
Datasets: MMBench - MM-Vet - MathVista - MMStar - HallusionBench
@Machine_learn
📃 Cheet Sheet for Machine Learning
@Machine_learn
با عرض سلام بسیاری از دوستان که می خواهند مقاله شروع کنند نیاز به نقش راهی برای شروع دارند. از این رو سعی داریم جهت مشاوره در موضوعات زیر همکاری داشته باشیم. انتخاب موضوع، انتخاب ایده، بررسی ساختار کلی مقاله و انتخاب ژورنال با بنده خواهد بود و هر هفته یک جلسه جهت بررسی کارهای انجام شده خواهیم داشت. هزینه مشاوره در هر موضوع ۵ تومن می باشد.
💠Medical Image
1-alzheimer disease classification
2-Wound image classification
3- skin cancer classification
4- breast cancer segmentation
💠Time series:
1- crypro market price prediction: High dimensional features
2-crypto market illiquidity prediction: High dimensional features
3-Air quality prediction
4-Network traffic prediction
5-Malware detection
💠Text mining
1-Large languge model: systmatic survey
2-multi-domain sentiment analysis
3- Extracting psychiatric stressors for suicide from twitter
جهت مشارکت می تونین با ایدی بنده در ارتباط باشین.
@Raminmousa
CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive Learning
🖥 Github: https://github.com/chumingqian/CycleGuardian
📕 Paper: https://arxiv.org/abs/2502.00734v1
🌟 Dataset: https://paperswithcode.com/dataset/icbhi-respiratory-sound-database
@Machine_learn
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
13 Dec 2024 · Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao Liu, Wen Liu, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, Xin Xie, Yuxiang You, Kai Dong, Xingkai Yu, Haowei Zhang, Liang Zhao, Yisong Wang, Chong Ruan ·
We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades. For the vision component, we incorporate a dynamic tiling vision encoding strategy designed for processing high-resolution images with different aspect ratios. For the language component, we leverage #DeepSeekMoE models with the Multi-head Latent Attention mechanism, which compresses Key-Value cache into latent vectors, to enable efficient inference and high throughput. Trained on an improved vision-language dataset, DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, #DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models. Codes and pre-trained models are publicly accessible at https://github.com/deepseek-ai/DeepSeek-VL2.
Paper: https://arxiv.org/pdf/2412.10302v1.pdf
Code: https://github.com/deepseek-ai/deepseek-vl2
Datasets: RefCOCO TextVQA MMBench
DocVQA
💠
/channel/deep_learning_proj
با عرض سلام
تخفیف ۵۰٪ دو پکیچ یادگیری ماشین و یادگیری عمیق که شامل ۳۶ پروژه عملی در بحث پردازش تصویر و پردازش متن می باشند رو در نظر گرفتیم. دوستانی که نیاز به این دو پک دارند می تونن به بنده پیام بدن. ۱ ماه مشاوره ریکان راجع به این پروژه ها هم خواهیم داشت.
🟥🟥🟥🟥🟥🟥
@Raminmousa
Introduction to Python for Computational Science and Engineering
📚 book
@Machine_learn
CoSTI: Consistency Models for (a faster) Spatio-Temporal Imputation
31 Jan 2025 · Javier Solís-García, Belén Vega-Márquez, Juan A. Nepomuceno, Isabel A. Nepomuceno-Chamorro ·
Multivariate Time Series Imputation (MTSI) is crucial for many applications, such as healthcare monitoring and traffic management, where incomplete data can compromise decision-making. Existing state-of-the-art methods, like Denoising Diffusion Probabilistic Models (DDPMs), achieve high imputation accuracy; however, they suffer from significant computational costs and are notably time-consuming due to their iterative nature. In this work, we propose CoSTI, an innovative adaptation of Consistency Models (CMs) for the MTSI domain. CoSTI employs Consistency Training to achieve comparable imputation quality to DDPMs while drastically reducing inference times, making it more suitable for real-time applications. We evaluate CoSTI across multiple datasets and missing data scenarios, demonstrating up to a 98% reduction in imputation time with performance on par with diffusion-based models. This work bridges the gap between efficiency and accuracy in generative imputation tasks, providing a scalable solution for handling missing data in critical spatio-temporal systems.
Paper: https://arxiv.org/pdf/2501.19364v1.pdf
Code: https://github.com/javiersgjavi/costi
@Machine_learn
نفر ۵ از این پروژه همچنان خالی هست...!
@Raminmousa
Free Certification Courses to Learn Data Analytics in 2025:
1. Python
🔗 https://imp.i384100.net/5gmXXo
2. SQL
🔗 https://edx.org/learn/relational-databases/stanford-university-databases-relational-databases-and-sql
3. Statistics and R
🔗 https://edx.org/learn/r-programming/harvard-university-statistics-and-r
4. Data Science: R Basics
🔗https://edx.org/learn/r-programming/harvard-university-data-science-r-basics
5. Excel and PowerBI
🔗 https://learn.microsoft.com/en-gb/training/paths/modern-analytics/
6. Data Science: Visualization
🔗https://edx.org/learn/data-visualization/harvard-university-data-science-visualization
7. Data Science: Machine Learning
🔗https://edx.org/learn/machine-learning/harvard-university-data-science-machine-learning
8. R
🔗https://imp.i384100.net/rQqomy
9. Tableau
🔗https://imp.i384100.net/MmW9b3
10. PowerBI
🔗 https://lnkd.in/dpmnthEA
11. Data Science: Productivity Tools
🔗 https://lnkd.in/dGhPYg6N
12. Data Science: Probability
🔗https://mygreatlearning.com/academy/learn-for-free/courses/probability-for-data-science
13. Mathematics
🔗http://matlabacademy.mathworks.com
14. Statistics
🔗 https://lnkd.in/df6qksMB
15. Data Visualization
🔗https://imp.i384100.net/k0X6vx
16. Machine Learning
🔗 https://imp.i384100.net/nLbkN9
17. Deep Learning
🔗 https://imp.i384100.net/R5aPOR
18. Data Science: Linear Regression
🔗https://pll.harvard.edu/course/data-science-linear-regression/2023-10
19. Data Science: Wrangling
🔗https://edx.org/learn/data-science/harvard-university-data-science-wrangling
20. Linear Algebra
🔗 https://pll.harvard.edu/course/data-analysis-life-sciences-2-introduction-linear-models-and-matrix-algebra
21. Probability
🔗 https://pll.harvard.edu/course/data-science-probability
22. Introduction to Linear Models and Matrix Algebra
🔗https://edx.org/learn/linear-algebra/harvard-university-introduction-to-linear-models-and-matrix-algebra
23. Data Science: Capstone
🔗 https://edx.org/learn/data-science/harvard-university-data-science-capstone
24. Data Analysis
🔗 https://pll.harvard.edu/course/data-analysis-life-sciences-4-high-dimensional-data-analysis
25. IBM Data Science Professional Certificate
https://imp.i384100.net/9gxbbY
26. Neural Networks and Deep Learning
https://imp.i384100.net/DKrLn2
27. Supervised Machine Learning: Regression and Classification
https://imp.i384100.net/g1KJEA
@Machine_learn
LLMs can see and hear without any training
30 Jan 2025 · Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar ·
We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ability to perform multi-step reasoning, MILS prompts the LLM to generate candidate outputs, each of which are scored and fed back iteratively, eventually generating a solution to the task. This enables various applications that typically require training specialized models on task-specific data. In particular, we establish a new state-of-the-art on emergent zero-shot image, video and audio captioning. MILS seamlessly applies to media generation as well, discovering prompt rewrites to improve text-to-image generation, and even edit prompts for style transfer! Finally, being a gradient-free optimization approach, MILS can invert multimodal embeddings into text, enabling applications like cross-modal arithmetic.
Paper: https://arxiv.org/pdf/2501.18096v1.pdf
Code: https://github.com/facebookresearch/mils
✅
/channel/deep_learning_proj
📄 New methods for drug synergy prediction: A mini-review
📎 Study the paper
@Machine_learn
BashBook
📚 Book
@Machine_learn
با عرض سلام برای یکی از مقالاتمون نفر دوم رو لازم داریم زمان سابمیت امشب تا فردا شب
Time-series Forecasting of Bitcoin Prices and Illiquidity
using High-dimensional Features: XGBoostLSTM
Approach
Corresponding author: Ramin Mousa
Abstract Liquidity is the ease of converting an asset into cash or another asset
without loss, and is shown by the relationship between the time scale and the
price scale of an investment. This article examines the relationship between
Bitcoin’s price prediction and illiquidity. Bitcoin Hash Rate information was col-
lected in three different intervals, and three techniques of feature selection (FS)
Filter, Wrapper, and Embedded were used. Considering the regression nature of
illiquidity prediction, an approach based on LSTM network and XGBoost was
proposed. LSTM was used to extract time series features, and XGBoost was used
to learn these features. The proposed LSTMXGBoost approach was evaluated in
two modes: price prediction and illiquidity prediction. This approach achieved
MAE 1.60 in the next-day forecast and MAE 3.46 in the next-day illiquidity
forecast. In the cross-validation of the proposed approach on the FS approaches,
the best result was obtained in the prediction by the filter approach and in
the classification by the wrapper approach. These obtained results indicate that
the presented models outperform the existing models in the literature. Examin-
ing the confusion matrices indicates that the two tasks of price prediction and
illiquidity prediction have no correlation and harm each other.
Keywords: illiquidity prediction, Bitcoin hash rate, hybrid model, price pre-
diction, LSTMXGBoost
ژورنال سابمیت
Journal : Finanace innovation(springer)
If: 6.5
دوستانی که در سری زمانی کار می کنن می تونن در این مقاله شرکت کنن.
@Raminmousa
با عرض سلام
نفر سوم و چهارم از مقاله زیر رو جهت ثبت اسم نیاز داریم. این مقاله ۸ ماه داریم روش کار میکنیم.
Title: Gaussian Mixture latent for Recurrent Neural Networks Basic deficiencies
The problem of time series prediction analyzes patterns in past data to predict the future. Traditional machine learning algorithms, despite achieving impressive results, require manual feature selection. Automatic feature selection along with the addition of time concept in deep recurrent networks has led to the provision of more suitable solutions. The selection of feature order in deep recurrent networks leads to the provision of different results due to the use of Back-propagation. The problem of selecting feature order is an NP-complete problem. In this research, the aim is to provide a solution to improve this problem.......!
Jouranl: Expert system with application
هزینه نفر سوم ۵۰۰ دلار و هزینه نفر چهارم ۴۰۰ دلار می باشد. جهت ثبت اسم با ایدی بنده در ارتباط باشین.
@Raminmousa
@Machine_learn
Detecting Backdoor Samples in Contrastive Language Image Pretraining
3 Feb 2025 · Hanxun Huang, Sarah Erfani, Yige Li, Xingjun Ma, James Bailey ·
Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training dataset. This raises security concerns on the current practice of pretraining large-scale models on unscrutinized web data using CLIP. In this work, we analyze the representations of backdoor-poisoned samples learned by CLIP models and find that they exhibit unique characteristics in their local subspace, i.e., their local neighborhoods are far more sparse than that of clean samples. Based on this finding, we conduct a systematic study on detecting CLIP backdoor attacks and show that these attacks can be easily and efficiently detected by traditional density ratio-based local outlier detectors, whereas existing backdoor sample detection methods fail. Our experiments also reveal that an unintentional backdoor already exists in the original CC3M dataset and has been trained into a popular open-source model released by OpenCLIP. Based on our detector, one can clean up a million-scale web dataset (e.g., CC3M) efficiently within 15 minutes using 4 Nvidia A100 GPUs.
Paper: https://arxiv.org/pdf/2502.01385v1.pdf
Code: https://github.com/HanxunH/Detect-CLIP-Backdoor-Samples
Datasets: Conceptual Captions CC12M RedCaps
@Machine_learn
📚 Linear Algebra for Computer Vision,
Robotics, and Machine Learning
👉 Book
@Machine_learn
Mathematical Foundations of Reinforcement Learning
📚 Link
@Machine_learn
با عرض سلام
نفر سوم از مقاله زیر رو جهت همکاری نیاز داریم. این مقاله ۸ ماه داریم روش کار میکنیم.
Title: Gaussian Mixture latent for Recurrent Neural Networks Basic deficiencies
The problem of time series prediction analyzes patterns in past data to predict the future. Traditional machine learning algorithms, despite achieving impressive results, require manual feature selection. Automatic feature selection along with the addition of time concept in deep recurrent networks has led to the provision of more suitable solutions. The selection of feature order in deep recurrent networks leads to the provision of different results due to the use of Back-propagation. The problem of selecting feature order is an NP-complete problem. In this research, the aim is to provide a solution to improve this problem.......!
هزینه مشارکت نفر سوم این مقاله ۱۰۰۰$ و ژورنال هدف Expert system میباشد.
@Raminmousa
@Machine_learn
Microsoft just updated their blog with 300 examples of real-world AI use cases.
📕 Article
@Machine_learn
Practical Statistics for Data Scientists
50+ Essential Concepts Using R and Python
#Python #Book
@Machine_learn
Demystifying Long Chain-of-Thought Reasoning in LLMs
🖥 paper
🧠 code
@Machine_learn
Awesome-LLM-as-a-judge Survey
▪ Github
🔸/channel/deep_learning_proj
RIGNO: A Graph-based framework for robust and accurate operator learning for PDEs on arbitrary domains
Paper: https://arxiv.org/pdf/2501.19205v1.pdf
Code: https://github.com/camlab-ethz/rigno
@Machine_learn
A Little Bit of Reinforcement Learning
from Human Feedback
📓 Book
@Machine_learn
20% از کارهای این مقاله انجام شده و این اخرین فرصت برای جوین شدن به پروژست.
@Raminmousa