MiniCPM-V: A GPT-4V Level MLLM on Your Phone
The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of #AI research and industry, shedding light on a promising path toward the next AI milestone. However, significant challenges remain preventing MLLMs from being practical in real-world applications. The most notable challenge comes from the huge cost of running an MLLM with a massive number of parameters and extensive computation. As a result, most MLLMs need to be deployed on high-performing cloud servers, which greatly limits their application scopes such as mobile, offline, energy-sensitive, and privacy-protective scenarios. In this work, we present MiniCPM-V, a series of efficient #MLLMs deployable on end-side devices. By integrating the latest MLLM techniques in architecture, pretraining and alignment, the latest MiniCPM-Llama3-V 2.5 has several notable features: (1) Strong performance, outperforming GPT-4V-1106, Gemini Pro and Claude 3 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, (2) strong #OCR capability and 1.8M pixel high-resolution #image perception at any aspect ratio, (3) trustworthy behavior with low hallucination rates, (4) multilingual support for 30+ languages, and (5) efficient deployment on mobile phones. More importantly, MiniCPM-V can be viewed as a representative example of a promising trend: The model sizes for achieving usable (e.g., GPT-4V) level performance are rapidly decreasing, along with the fast growth of end-side computation capacity. This jointly shows that GPT-4V level MLLMs deployed on end devices are becoming increasingly possible, unlocking a wider spectrum of real-world AI applications in the near future.
Paper: https://arxiv.org/pdf/2408.01800v1.pdf
Codes:
https://github.com/OpenBMB/MiniCPM-o
https://github.com/openbmb/minicpm-v
Datasets: Video-MME
@Machine_learn
The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of #AI research and industry, shedding light on a promising path toward the next AI milestone. However, significant challenges remain preventing MLLMs from being practical in real-world applications. The most notable challenge comes from the huge cost of running an MLLM with a massive number of parameters and extensive computation. As a result, most MLLMs need to be deployed on high-performing cloud servers, which greatly limits their application scopes such as mobile, offline, energy-sensitive, and privacy-protective scenarios. In this work, we present MiniCPM-V, a series of efficient #MLLMs deployable on end-side devices. By integrating the latest MLLM techniques in architecture, pretraining and alignment, the latest MiniCPM-Llama3-V 2.5 has several notable features: (1) Strong performance, outperforming GPT-4V-1106, Gemini Pro and Claude 3 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, (2) strong #OCR capability and 1.8M pixel high-resolution #image perception at any aspect ratio, (3) trustworthy behavior with low hallucination rates, (4) multilingual support for 30+ languages, and (5) efficient deployment on mobile phones. More importantly, MiniCPM-V can be viewed as a representative example of a promising trend: The model sizes for achieving usable (e.g., GPT-4V) level performance are rapidly decreasing, along with the fast growth of end-side computation capacity. This jointly shows that GPT-4V level MLLMs deployed on end devices are becoming increasingly possible, unlocking a wider spectrum of real-world AI applications in the near future.
Paper: https://arxiv.org/pdf/2408.01800v1.pdf
Codes:
https://github.com/OpenBMB/MiniCPM-o
https://github.com/openbmb/minicpm-v
Datasets: Video-MME
@Machine_learn
👍4
Transformers 2: Self-adaptive LLMs
Paper: https://arxiv.org/pdf/2501.06252v2.pdf
Code:
https://github.com/SakanaAI/self-adaptive-llms
https://github.com/codelion/adaptive-classifier
Datasets: GSM8K - HumanEval - MATH
MBPP - TextVQA - OK-VQA - ARC (AI2 Reasoning Challenge)
@Machine_learn
Paper: https://arxiv.org/pdf/2501.06252v2.pdf
Code:
https://github.com/SakanaAI/self-adaptive-llms
https://github.com/codelion/adaptive-classifier
Datasets: GSM8K - HumanEval - MATH
MBPP - TextVQA - OK-VQA - ARC (AI2 Reasoning Challenge)
@Machine_learn
❤2
🧑🍳 New Cookbook guide: How to use the Usage API and Cost API to monitor your OpenAI usage
📚 Book
@Machine_learn
📚 Book
@Machine_learn
👍1
This media is not supported in your browser
VIEW IN TELEGRAM
git clone https://github.com/DepthAnything/Video-Depth-Anything
cd Video-Depth-Anything
pip install -r requirements.txt▪GitHub
▪Paper
▪Model Small
▪Model Large
▪Demo
@Machine_learn
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥2
Mathematics of Machine Learning.pdf
3.9 MB
📚 Mathematics of Machine Learning
👨🏻🏫 Philipp Christian Petersen
📝 Table of Contents:
● Language of Machine Learning
● ML Mathematical Framework
● Rademacher Complexities
● Rademacher Complexities Applications
●The Mysterious Machine
● Lower Bounds on Learning
● Model Selection
● Regression and Regularization
● Freezing Fritz
● Support Vector Machines
● Kernel Methods
● Nearest Neighbour
● Neural Networks
● Boosting
● Clustering
● Dimensionality Reduction
@Machine_learn
👨🏻🏫 Philipp Christian Petersen
📝 Table of Contents:
● Language of Machine Learning
● ML Mathematical Framework
● Rademacher Complexities
● Rademacher Complexities Applications
●The Mysterious Machine
● Lower Bounds on Learning
● Model Selection
● Regression and Regularization
● Freezing Fritz
● Support Vector Machines
● Kernel Methods
● Nearest Neighbour
● Neural Networks
● Boosting
● Clustering
● Dimensionality Reduction
@Machine_learn
👍2
با عرض سلام پروژه جدیدمون شروع شد.
هدف اصلی این پروژه اموزش یک مدل پیشنهاد دهنده ی مدل برای مسائله طبقه بندی تصاویر پزشکی میباشد که از اموزش مجدد مدل ها جلوگیری میکند. این مسائله با جنبه جلوگیری از مصرف انرژی اموزشی و زمان اموزش مدل ها ارائه می شود. برای این منظور ۵۰۰۰ مقاله در این زمینه جمع اوری شده است. جزئیات بیشتر در لینک گیت قرار دارد.
Project Title: MedRec: Medical recommender system for image classification without retraining
Github: https://github.com/Ramin1Mousa/MedicalRec
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
Impact factor: 20.8
۷ نفر دیگر امکان اضافه شدن به این پروژه رو دارند. هر شخص نیاز هست که حدودا داده های ۴۰۰ مقاله رو بررسی کند. زمان تقریبی هر مقاله ۵-۱۰ دقیقه می باشد. هزینه مشارکت در مقاله:
🔹 2- 600$
🔺 3- 500$
💠 4- 400$
🔺 5- 300$
🔹 6- 200$
🔸 7- 200$
جهت مشارکت می تونید به ایدی بنده پیام بدین.
🔹 شنبه شروع این پروژه هست🔹
@Raminmousa
هدف اصلی این پروژه اموزش یک مدل پیشنهاد دهنده ی مدل برای مسائله طبقه بندی تصاویر پزشکی میباشد که از اموزش مجدد مدل ها جلوگیری میکند. این مسائله با جنبه جلوگیری از مصرف انرژی اموزشی و زمان اموزش مدل ها ارائه می شود. برای این منظور ۵۰۰۰ مقاله در این زمینه جمع اوری شده است. جزئیات بیشتر در لینک گیت قرار دارد.
Project Title: MedRec: Medical recommender system for image classification without retraining
Github: https://github.com/Ramin1Mousa/MedicalRec
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
Impact factor: 20.8
۷ نفر دیگر امکان اضافه شدن به این پروژه رو دارند. هر شخص نیاز هست که حدودا داده های ۴۰۰ مقاله رو بررسی کند. زمان تقریبی هر مقاله ۵-۱۰ دقیقه می باشد. هزینه مشارکت در مقاله:
جهت مشارکت می تونید به ایدی بنده پیام بدین.
@Raminmousa
Please open Telegram to view this post
VIEW IN TELEGRAM
👍2
List of 500+AI Agent projects/UseCases
https://github.com/DataSpoof/500-AI-Agents-Projects
@Machine_learn
https://github.com/DataSpoof/500-AI-Agents-Projects
@Machine_learn
❤1🔥1
Forecasting of Bitcoin Prices Using Hashrate Features: Wavelet and Deep Stacking Approach
✅ NEW PAPER
Link: https://arxiv.org/abs/2501.13136
Abstract: Digital currencies have become popular in the last decade due to their non-dependency and decentralized nature. The price of these currencies has seen a lot of fluctuations at times, which has increased the need for prediction. As their most popular, Bitcoin(BTC) has become a research hotspot. The main challenge and trend of digital currencies, especially BTC, is price fluctuations, which require studying the basic price prediction model. This research presents a classification and regression model based on stack deep learning that uses a wavelet to remove noise to predict movements and prices of BTC at different time intervals. The proposed model based on the stacking technique uses models based on deep learning, especially neural networks and transformers, for one, seven, thirty and ninety-day forecasting. Three feature selection models, Chi2, RFE and Embedded, were also applied to the data in the pre-processing stage. The classification model achieved 63\% accuracy for predicting the next day and 64\%, 67\% and 82\% for predicting the seventh, thirty and ninety days, respectively. For daily price forecasting, the percentage error was reduced to 0.58, while the error ranged from 2.72\% to 2.85\% for seven- to ninety-day horizons. These results show that the proposed model performed better than other models in the literature.
@Machine_learn
Link: https://arxiv.org/abs/2501.13136
Abstract: Digital currencies have become popular in the last decade due to their non-dependency and decentralized nature. The price of these currencies has seen a lot of fluctuations at times, which has increased the need for prediction. As their most popular, Bitcoin(BTC) has become a research hotspot. The main challenge and trend of digital currencies, especially BTC, is price fluctuations, which require studying the basic price prediction model. This research presents a classification and regression model based on stack deep learning that uses a wavelet to remove noise to predict movements and prices of BTC at different time intervals. The proposed model based on the stacking technique uses models based on deep learning, especially neural networks and transformers, for one, seven, thirty and ninety-day forecasting. Three feature selection models, Chi2, RFE and Embedded, were also applied to the data in the pre-processing stage. The classification model achieved 63\% accuracy for predicting the next day and 64\%, 67\% and 82\% for predicting the seventh, thirty and ninety days, respectively. For daily price forecasting, the percentage error was reduced to 0.58, while the error ranged from 2.72\% to 2.85\% for seven- to ninety-day horizons. These results show that the proposed model performed better than other models in the literature.
@Machine_learn
Please open Telegram to view this post
VIEW IN TELEGRAM
arXiv.org
Forecasting of Bitcoin Prices Using Hashrate Features: Wavelet and...
Digital currencies have become popular in the last decade due to their non-dependency and decentralized nature. The price of these currencies has seen a lot of fluctuations at times, which has...
👍2❤1🔥1
📃 Demystifying the black box: A survey on explainable artificial intelligence (XAI) in bioinformatics
📎 Study the paper
@Machine_learn
📎 Study the paper
@Machine_learn
❤3👍2
Physics IQ Benchmark: Do generative video models learn physical principles from watching videos
Book
@Machine_learn
Book
@Machine_learn
❤3
This channels is for Programmers, Coders, Software Engineers.
0️⃣ Python
1️⃣ Data Science
2️⃣ Machine Learning
3️⃣ Data Visualization
4️⃣ Artificial Intelligence
5️⃣ Data Analysis
6️⃣ Statistics
7️⃣ Deep Learning
8️⃣ programming Languages
✅ https://t.iss.one/addlist/8_rRW2scgfRhOTc0
✅ https://t.iss.one/codeprogrammer
Please open Telegram to view this post
VIEW IN TELEGRAM
Telegram
Data science
You’ve been invited to add the folder “Data science”, which includes 16 chats.
👍1
Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systems
Surround-View System (SVS) is an essential component in Advanced Driver Assistance System (ADAS) and requires precise calibrations.
Paper: https://arxiv.org/pdf/2501.01557v2.pdf
Code: https://github.com/lwangvaleo/click_calib
Dataset: WoodScape
@Machine_learn
Surround-View System (SVS) is an essential component in Advanced Driver Assistance System (ADAS) and requires precise calibrations.
Paper: https://arxiv.org/pdf/2501.01557v2.pdf
Code: https://github.com/lwangvaleo/click_calib
Dataset: WoodScape
@Machine_learn
👍3