پژوهشگرای ComputerVision توجه کنند:

April 5 2023: Meta AI released Segment Anything Model , Meta AI SAM video for Image Segmentation. This model consisted of a Vision Transformer to generate image embeddings and a Prompt encoder mask decoder model to create segmentation masks from prompts. These prompts could be points, bounding box or text description.Since its advent, SAM has attracted significant attention for multiple reasons. First, it is the first to show that vision can follow NLP to pursue a path that combines foundation model with prompt engineering. Second, it is the first to perform label-free segmentation.Moreover, this fundamental task makes SAM compatible with other models to realize advanced vision applications, like text-guided segmentation and image editing with fine-grained control.

21 June 2023 : Then Fast SAM, Video FastSAM came up with using YOLO v8 for instance segmentation instead of Vision Transformer and custom prompt guided selection for detecting segmentation masks. This sped up segmentation process by 50 X.

25 June 20233 : Now Mobile SAM, VideoSam The authors distill the knowledge from the image encoder ViT-H in the original SAM to a lightweight image encoder, which can be automatically compatible with the mask decoder in the original SAM. The training can be completed on a single GPU within less than one day, and the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM. For inference speed, MobileSAM runs around 10ms per image: 8ms on the image encoder and 2ms on the mask decoder. With superior performance and a higher versatility, MobileSAM is 7 times smaller and 4 times faster than the concurrent FastSAM, making it more suitable for mobile applications

Rapid developments due to Meta AI making their code open source and releasing their datasets.

#مقاله #ایده_جذاب #بینایی_کامپیوتر #هوش_مصنوعی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

اطلاعاتی که برنامه Threads متعلق به شرکت متا زحمت میکشه و میدزده

Reference: Link

#App
#News
#DataLeaks

@VulnerHunters

LLM Powered Autonomous Agents

This is an incredible overview of LLM-powered autonomous agent systems. Includes case studies and proof-of-concept examples.
https://lilianweng.github.io/posts/2023-06-23-agent/

منابع رایگان GenerativeAI

1) Intro to Generative #AI: goo.gle/3NGqBjE

2) Intro to #LLMs Large Language Models: goo.gle/43kbKku

3) Transformer Models: goo.gle/3rjsY4k

4) Intro to Image Generation: goo.gle/3rljB47

#پیشرفته #منابع #هوش_مصنوعی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

فقط برای ریسرچ.
اگر دنبال موضوع، استاد، دانشجو برای پوزیشن خاص، نویسنده همکار، سوال در زمینه ژورنال و کنفرانس و ... هستید عضو بشید.

هرگونه بی احترامی باعث ریمو‌میشه.
پروژه درسی سفارش ندید و نگیرید باعث ریمو‌ شدنتان میشود.

با تشکر.

لینک گروه:
https://yangx.top/researcher_people

قسمت اول لیست کنفرانس های #هوش_مصنوعی

🔸 CVPR : Conference on Computer Vision and Pattern Recognition
🔸 ICLR : International Conference on Learning Representations
🔸 NeurIPS: Neural Information Processing Systems
🔸 ICCV : International Conference on Computer Vision
🔸 ICML: International Conference on Machine Learning
🔸 ECCV : European Conference on Computer Vision
🔸 ACL : Annual Meeting of the Association for Computational Linguistics
🔸 AAAI : Association for the Advancement of Artificial Intelligence
🔸 EMNLP : Conference on Empirical Methods in Natural Language Processing
🔸 IJCAI : International Joint Conference on Artificial Intelligence
🔸 ICRA: International Conference on Robotics and Automation
🔸 SIGKDD : ACM SIGKDD International Conference on Knowledge discovery and data mining
🔸 NAACL : North American Chapter of the Association for Computational Linguistics
🔸 ICASSP : International Conference on Acoustics, Speech and Signal Processing
🔸 INTERSPEECH : Conference of the International Speech Communication Association
🔸 WWW : International World Wide Web Conferences
🔸 IROS: International Conference on Intelligent Robots and Systems
🔸 ACMMM : ACM Multimedia
🔸 SIGIR: International ACM SIGIR Conference on Research and Development in Information Retrieval
🔸 BMVC : British Machine Vision Conference
🔸 AISTATS : International Conference on Artificial Intelligence and Statistics
🔸 CIKM : ACM International Conference on Information and Knowledge Management
🔸 COLT: Conference on Learning Theory
🔸 WACV : Winter Conference on Applications of Computer Vision

#کنفرانس

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

قسمت دوم لیست کنفرانس های #هوش_مصنوعی

🔸 ICIP : International Conference on Image Processing
🔸 RSS : Robotics: Science and Systems
🔸 COLING: International Conference on Computational Linguistics
🔸 IJCNN: International Joint Conference on Neural Networks
🔸 AAMAS: International Conference on Autonomous Agents and Multiagent Systems
🔸 CoNLL: Conference on Computational Natural Language Learning
🔸 GECCO: Genetic and Evolutionary Computation Conference
🔸 ICPR: International Conference on Pattern Recognition
🔸 UAI: Conference on Uncertainty in Artificial Intelligence
🔸 CoRL: Conference on Robot Learning
🔸 ACCV: Asian Conference on Computer Vision
🔸 ECMLPKDD : European Conference on Machine learning and knowledge discovery in databases
🔸 ICMR : ACM International Conference on Multimedia Retrieval Newark
🔸 ICME: International Conference on Multimedia and Expo
🔸 ICMLA : International Conference On Machine Learning And Applications
🔸 ICAPS: International Conference on Automated Planning and Scheduling
🔸 ICIAP : International Conference on Image Analysis and Processing
🔸 PAKDD: Pacific-Asia Conference on Knowledge Discovery and Data Mining
🔸 ICONIP: International Conference on Neural Information Processing
🔸 KR : International Conference on Principles of Knowledge Representation and Reasoning
🔸 ICTAI: International Conference on Tools with Artificial Intelligence
🔸 ICANN: International Conference on Artificial Neural Networks
🔸 ECAI : European Conference on Artificial Intelligence
🔸 ACML : Asian Conference on Machine Learning
🔸 ALT : International Conference on Algorithmic Learning
🔸 PRICAI: Pacific Rim International Conference on Artificial Intelligence
🔸 SIGGRAPH : ACM SIGGRAPH Annual Conference
🔸 ICDM : International Conference on Data Mining
🔸 CoG : IEEE Conference on Games
🔸 MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention

#کنفرانس

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

کورس تابستانی دانشگاه Heinrich Heine یک دوره Representation Learning ارائه داده که جای این دوره خیلی خالی بود این کورس کلاسی خیلی مفیده علاقمندان این فیلد دنبال کنند.
- Visual self-supervised learning methods
- Natural language representation
- Contrastive learning
- Vision transformers & knowledge distillation
- Self-distillation
- Masked-based visual learning
- Multimodal representation learning
- Emerging topics in representation learning
- Scaling laws ...

🔸 Course

#منابع #الگوریتمها #پیشرفته

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

گرافیک کتاب جبرخطی دکتر گیلبرت استرانگ مناسب برای همه مقاطع تحصیلی هستش منبع آموزشی

🔸 Linear Algebra for Everyone

#کتاب #منابع #ریاضی #مبتدی


🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

من تیر خوردم شما ادامه بدید 😕
میگه فشرده سازی تو برخی موارد از ترنسفرمر هم بهتره، مخصوصا دسته بندی !
https://aclanthology.org/2023.findings-acl.426/

دکتر Jeremy Howard یک آموزش جامع برای مبتدیان NLP تهیه کرده که یکی از بهترینها هستش علاقمندید به این فیلد دنبال ‌کنید

🔸 NLP for absolute beginners

#مبتدی #پردازش_زبان_طبیعی #منابع

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

دیپ فیک اواتار خودتون بسازین
https://github.com/sensity-ai/dot

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

سه دوره رایگان علم داده و هوش مصنوعی از شرکت مایکروسافت از اینجا دنبال کنید

1. AI for Beginners

- Terminologies
- Basics of NLP
- Basics of Computer Vision

2. Data Science for Beginners

- Data Science Basics & Ethics
- Statistics
- SQL & NOSQL
- Data Preparation & Visualization
- Data Analysis
- Complete Data Science Lifecycle

3. Machine Learning for Beginners

- Various ML Techniques
- Building your first ML Project right from data collection to create a web app for a trained model
- NLP Techniques
- Times Series
- Reinforcement Learning

#منابع #مقدماتی #پیشرفته #علم_داده #یادگیری_ماشین #هوش_مصنوعی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

آموزشی کاربردی و مفید از مدلهای LLM از کارایی و چگونگی تهیه اونها و... صحبت میکنند.

Large Language Models: Application through Production

🔸 Notebooks & slides
🔸 Video

#پردازش_زبان_طبیعی #منابع #پیشرفته #مقدماتی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

محققین مدلهای LLM وقتی هم نمیدانند هم میدانند!

🔸 Robots That Ask For Help: Uncertainty Alignment for Large Language Model
🔸 Code for Large Language Model

-Builds on theory of conformal prediction
-Selects subset of LLM generated possible actions
-Eval across settings & embodiments validates ability to provide levels of success & reduce amount of help asked for

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

یکی از مقالات جالبی که تازه منتشر شده
Secrets of RLHF in Large Language Models Part I: PPO
https://huggingface.co/papers/2307.04964

#ایده_جذاب #مقاله

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

خفن‌ترین هوش مصنوعی مکالمه‌ای جهان به بازی اومد!
Air
این هوش مصنوعی می‌تونه تا 50 دقیقه با یک مشتری صحبت کنه و صداش با انسان مو نمی‌زنه. گفته می‌شه این هوش در یک شرکت می‌تونه به جای 100 هزار پشتیبان تلفنی انسانی مشغول به کار بشه.
توی این پست لینکدین می‌تونید یک دمو ازش به عنوان پشتیبان تلفنی شرکت تسلا رو ببینید.

این هم آدرس وب‌سایتش:
https://www.air.ai
#پردازش_زبان_طبیعی #ابزار

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

متا ورژن دوم Llama 2 خود را منتشر کرد.

🔸 Paper

🔸 Project

پ.ن : اینجا هم ایده های مرتبط دیگه منتشر شده ازش .

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

معرفی برخی از کتاب ها در زمینه دیتاساینس، پایتون و ماشین لرنینگ

How is ChatGPT’s behavior changing over time?

If you are developing with LLMs or in this case GPT-3.5 or GPT-4, it's definitely worth taking a look at this report.

There is suspicion in the AI community that models like GPT-4 are changing/degrading in performance and behavior.

The paper "finds that the performance and behavior of both GPT-3.5 and GPT-4 vary significantly across these two releases and that their performance on some tasks have gotten substantially worse over time."

There are no official reports on this matter but it highlights the importance of things like continuous monitoring of LLM output quality.

https://arxiv.org/abs/2307.09009
https://github.com/lchen001/LLMDrift

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind