Data Science by ODS.ai 🦜

24 May 2024 13:03

🚀🎉Another exciting day for Multimodal AI! The MiniCPM-V repository by is trending on GitHub.

🤯 Impressive Results:
👉MiniCPM-Llama3-V 2.5 (8B) surpasses GPT-4V, Gemini Pro, & Claude 3
👉MiniCPM-V 2.0 (2B) surpasses Yi-VL 34B, CogVLM-Chat 17B, & Qwen-VL-Chat 10B

MiniCPM-V is efficiently deployable on end-side devices🤖📱 Read more: https://github.com/OpenBMB/MiniCPM-V

🚀MiniCPM-V is building with Gradio to showcase framework's flexibility for creating powerful AI Vision apps. Local Gradio demo: https://github.com/OpenBMB/MiniCPM-V?tab=readme-ov-file#webui-demo

@opendatascience

Data Science by ODS.ai 🦜

21 May 2024 17:22

Images that Sound: Composing Images and Sounds on a Single Canvas

abs: https://arxiv.org/abs/2405.12221
project page: https://ificl.github.io/images-that-sound/
code: https://github.com/IFICL/images-that-sound

This paper introduces an inference-time procedure that generates images that are also spectrograms corresponding to the prompt. It uses a latent image and audio diffusion model with same latent space (Stable Diffusion v1.5 and Auffusion) and denoise the same latent with both.

@opendatascience

Data Science by ODS.ai 🦜

08 May 2024 21:54

🧬 AlphaFold 3 predicts the structure and interactions of all of life’s molecules

Google DeepMind представили Alpha Fold3, новую модель искусственного интеллекта, которая предсказывает структуру и взаимодействия молекул.

Благодаря точному прогнозированию структуры белков, ДНК, РНК и многого другого, а также того, как они взаимодействуют, наше понимание биологического мира может выйти на новый уровень, а в практическом применение поможет разработке новых лекарств.

Эта революционная модель, может предсказывать структуру и взаимодействия всех молекул жизни с беспрецедентной точностью.

На основе входного списка молекул Alpha Fold3 генерирует их общую трехмерную структуру, показывая, как они сочетаются друг с другом. Программа моделирует крупные биомолекулы, такие как белки, ДНК и РНК, а также небольшие молекулы, также известные как лиганды.

Кроме того, Alpha Fold3 может моделировать химические модификации этих молекул, которые контролируют здоровое функционирование клеток, нарушение которых может привести к различным заболеваниям.

Теперь для учёные со всего мира могут работать с AlphaFold 3 совершенно бесплатно.

▪Blog: https://blog.google/technology/ai/google-deepmind-isomorphic-alphafold-3-ai-model/
▪Nature: https://www.nature.com/articles/s41586-024-07487-w
▪Two Minute Papers: https://www.youtube.com/watch?v=Mz7Qp73lj9o

@ai_machinelearning_big_data

Data Science by ODS.ai 🦜

04 May 2024 09:11

This is what we started with and results still look good for 2021. Back in a day we used neural networks for generation of the logo for the channel and it saved us quite some time on communication with designers.

Data Science by ODS.ai 🦜

27 Apr 2024 07:12

Discover, download, and run local LLMs

LM Studio allows to run #LLM model of your choice locally

Link: https://lmstudio.ai/

Data Science by ODS.ai 🦜

16 Apr 2024 15:50

⚡️Map-relative Pose Regression🔥(#CVPR2024 highlight)

For years absolute pose regression did not work. There was some success by massively synthesising scene-specific data. We train scene-agnostic APR and it works.

▪Paper: https://arxiv.org/abs/2404.09884
▪Page: https://nianticlabs.github.io/marepo


@opendatascience

Data Science by ODS.ai 🦜

10 Apr 2024 08:35

🥔 YaART: Yet Another ART Rendering Technology

💚 This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF).

💜 During the development of YaART, Yandex especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before.

💖 In particular, researchers comprehensively analyze how these choices affect both the efficiency of the training process and the quality of the generated images, which are highly important in practice.

▪Paper page - https://ya.ru/ai/art/paper-yaart-v1
▪Arxiv - https://arxiv.org/abs/2404.05666
▪Habr - https://habr.com/ru/companies/yandex/articles/805745/

@opendatascience

Data Science by ODS.ai 🦜

06 Apr 2024 18:01

⚡️ Awesome CVPR 2024 Papers, Workshops, Challenges, and Tutorials!

На конференцию 2024 года по компьютерному зрению и распознаванию образов (CVPR) поступило 11 532 статей, из которых только 2 719 были приняты, что составляет около 23,6% от общего числа.

Ниже приведен список лучших докладов, гайдов, статей, семинаров и датасетов с CVPR 2024.

▪Github

@ai_machinelearning_big_data

Data Science by ODS.ai 🦜

02 Apr 2024 15:01

Let’s get back to posting 😌

Data Science by ODS.ai 🦜

10 Mar 2024 07:34

LLM models are in their childhood years

yannlecun/post/C4TONRKrCgx/?xmt=AQGzgyqvMeJEC2KowLslWxsAN6dSxycXtm1O-gfJ9FPLlQ">Source.

Data Science by ODS.ai 🦜

27 Sep 2023 12:50

Here is very interesting notes about how behaves generation of stable diffusion trained on different datasets with the same noise. Seems very contrintuitive!

https://twitter.com/mokadyron/status/1706618451664474148

Data Science by ODS.ai 🦜

14 Sep 2023 19:22

🔥 Introducing Würstchen: Fast Diffusion for Image Generation

Diffusion model, whose text-conditional component works in a highly compressed latent space of images

Würstchen - это диффузионная модель, которой работает в сильно сжатом латентном пространстве изображений.

Почему это важно? Сжатие данных позволяет на порядки снизить вычислительные затраты как на обучение, так и на вывод модели.

Обучение на 1024×1024 изображениях гораздо затратное, чем на 32×32. Обычно в других моделях используется сравнительно небольшое сжатие, в пределах 4x - 8x пространственного сжатия.

Благодаря новой архитектуре достигается 42-кратное пространственное сжатие!

🤗 HF: https://huggingface.co/blog/wuertschen

📝 Paper: https://arxiv.org/abs/2306.00637

📕 Docs: hhttps://huggingface.co/docs/diffusers/main/en/api/pipelines/wuerstchen

🚀 Demo: https://huggingface.co/spaces/warp-ai/Wuerstchen

ai_machinelearning_big_data

Data Science by ODS.ai 🦜

13 Sep 2023 16:17

📹 DEVA: Tracking Anything with Decoupled Video Segmentation

Decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation.

Новая модель сегментации видео для "отслеживания чего угодно" без обучения по видео для любой отдельной задачи.

🖥 Github: https://github.com/hkchengrex/Tracking-Anything-with-DEVA

🖥 Colab: https://colab.research.google.com/drive/1OsyNVoV_7ETD1zIE8UWxL3NXxu12m_YZ?usp=sharing

⏩ Project: https://hkchengrex.github.io/Tracking-Anything-with-DEVA/

📕 Paper: https://arxiv.org/abs/2309.03903v1

⭐️ Docs: https://paperswithcode.com/dataset/burst

ai_machinelearning_big_data

Data Science by ODS.ai 🦜

11 Sep 2023 07:11

​​Explaining grokking through circuit efficiency

The paper explores the phenomenon of "grokking" in neural networks, where a network that initially performs poorly on new data eventually excels without any change in training setup. According to the authors, grokking occurs when two conditions are present: a memorizing solution and a generalizing solution. The generalizing solution takes longer to learn but is more efficient in terms of computational resources. The authors propose a "critical dataset size" at which the efficiencies of memorizing and generalizing are equal, providing a pivot point for the network to switch from memorization to generalization.

Furthermore, the paper introduces two new behaviors: "ungrokking" and "semi-grokking." Ungrokking describes a situation where a well-performing network reverts to poor performance when trained on a smaller dataset. Semi-grokking refers to a scenario where the network, instead of achieving full generalization, reaches a state of partial but improved performance.

Paper link: https://arxiv.org/abs/2309.02390

My overview of the paper:
https://andlukyane.com/blog/paper-review-un-semi-grokking
https://artgor.medium.com/paper-review-explaining-grokking-through-circuit-efficiency-1f420d6aea5f

#paperreview

Data Science by ODS.ai 🦜

04 Sep 2023 06:38

​​RecMind: Large Language Model Powered Agent For Recommendation

Recent advancements have significantly improved the capabilities of Large Language Models (LLMs) in various tasks, yet their potential in the realm of personalized recommendations has been relatively unexplored. To address this gap, a new LLM-powered autonomous recommender agent called RecMind has been developed. RecMind is designed to provide highly personalized recommendations by leveraging planning algorithms, tapping into external data sources, and using individualized data.

One standout feature of RecMind is its novel "Self-Inspiring" algorithm, which enhances the model's planning abilities. During each step of planning, the algorithm encourages the model to consider all its past actions, thereby improving its understanding and use of historical data. The performance of RecMind has been evaluated across multiple recommendation tasks like rating prediction, sequential and direct recommendation, explanation generation, and review summarization. The results show that RecMind outperforms existing LLM-based methods in these tasks and is competitive with the specialized P5 model.

Paper link: https://arxiv.org/abs/2308.14296

A detailed unofficial overview of the paper:
https://andlukyane.com/blog/paper-review-recmind

#deeplearning #nlp #llm #recommender

Data Science by ODS.ai 🦜

24 May 2024 10:47

Если вас интересует аналитика или вы уже развиваетесь в этой сфере и хотите существенно улучшить свои скиллы, запишитесь на курс "Аналитик PRO" от Changellenge Education.

Changellenge Education – специализированная школа аналитики, которая уже выпустила 3 500 специалистов. Их выпускники работают в Яндексе, VK, Газпроме и других крупных компаниях.

"Аналитик PRO" – самый полный курс аналитики на рынке. Он подойдет вам, если вы хотите прокачаться как аналитик данных, бизнес-аналитик, финансовый аналитик. В курсе собрано всё, что нужно для роста в любом направлении аналитики.

На 12 месячной программе вы прокачаете ключевые навыки, необходимые аналитику — работа с данными:
🔵Python, SQL, Excel,
а также визуализация данных:
🔵Tableau, PPT, и с помощью Python.

Вы научитесь строить финансовые модели, погрузитесь в продуктовую и маркетинговую аналитику.

Больше 2/3 курса — это практические задачи и реальные бизнес-проекты от реальных компаний уровня Тинькофф.

Эти проекты можно будет сразу указать в резюме и портфолио, чтобы выделиться на фоне других кандидатов. Благодаря набору востребованных навыков, пулу проектов и после выпуска вы сможете претендовать на интересные офферы с достойной зарплатой на старте.

Это реально важно, конкуренция джунов сейчас большая, работодателям нужна практика и опыт работы и в Changellenge Education это учитывают.

По промокоду ODS10 вас ждет скидка в 10 000 рублей от нашего канала. Скидка действует 48 часов. Оставьте заявку по ссылке и начните свою карьеру в аналитике уже сегодня. Успехов!

Реклама. ООО «Высшая школа аналитики и стратегии». ИНН:7716917009 erid: 2Vtzqv6zrVR

Data Science by ODS.ai 🦜

21 May 2024 14:14

Блокчейн TON ищет талантливых разработчиков!

Стартует масштабный хакатон “The Open League Hackathon” с призовым пулом $2,000,000 от команды блокчейна TON.

В поддержку хакатона все Web3-энтузиасты приглашаются на трёхдневные оффлайн встречи для нетворкинга в 13 городах мира:

📍Прага, Берлин, Киев, Варшава, Тбилиси, Белград, Сеул, Тайбэй (Тайвань), Гуруграм (Индия), Гонг-Конг, Минск, Москва и Санкт-Петербург.

Первые встречи начнутся уже 24 мая. Ищи свой город и регистрируйся здесь 👈 тык

Что вас ждет:

— 3 дня нетворка, лекций, конкурсов и работы над собственными проектами с поддержкой представителей TON Foundation и команд экосистемы TON

— Призовые $5.000 для трех лучших проектов на каждом оффлайн ивенте + много мерча и других бонусов

Не упусти возможность представить свое приложение 900 миллионам активных пользователей Telegram вместе с TON.

Регистрируйся — https://society.ton.org/activities/open-league

Data Science by ODS.ai 🦜

04 May 2024 09:11

We followed on developing theme in Novemeber 2022. And it looks like we might have another attempt to renew our avatar, what do you think?

Data Science by ODS.ai 🦜

03 May 2024 18:58

🔥 Say Goodbye to LoRA, Hello to DoRA 🤩🤩

DoRA consistently outperforms LoRA with various tasks (LLM, LVLM, etc.) and backbones (LLaMA, LLaVA, etc.)

[Paper] https://arxiv.org/abs/2402.09353
[Code] https://github.com/NVlabs/DoRA

#Nvidia
#icml #PEFT #lora #ML #ai

@opendatascience

Data Science by ODS.ai 🦜

18 Apr 2024 19:44

👑Llama 3 is here, with a brand new tokenizer! 🦙

Вышла Llama 3

Meta выпустила новую SOTA Llama 3 в двух версиях на 8B и 70B параметров.

Длина контекста 8К, поддержка 30 языков.

•HF: https://huggingface.co/spaces/ysharma/Chat_with_Meta_llama3_8b
•Blog: https://ai.meta.com/blog/meta-llama-3/

Вы можете потестить 🦙 MetaLlama 3 70B и 🦙 Meta Llama 3 8B с помощью 🔥 бесплатного интерфейса: https://llama3.replicate.dev/

@ai_machinelearning_big_data

Data Science by ODS.ai 🦜

12 Apr 2024 10:17

🔥 ControlNet++: Improving Conditional Controls
with Efficient Consistency Feedback

Proposes an approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency

proj: https://liming-ai.github.io/ControlNet_Plus_Plus/
abs: https://arxiv.org/abs/2404.07987

@opendatascience

Data Science by ODS.ai 🦜

09 Apr 2024 10:06

⚡️ PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models

Significantly improved finetuned perf by simply changing the initialization of LoRA's AB matrix from Gaussian/zero to principal components.

On GSM8K, Mistral-7B fine-tuned with PiSSA achieves an accuracy of 72.86%, outperforming LoRA’s 67.7% by 5.16%.

▪Github: https://github.com/GraphPKU/PiSSA
▪Paper: https://arxiv.org/abs/2404.02948

@opendatascience

Data Science by ODS.ai 🦜

05 Apr 2024 10:26

Objective-Driven AI: Towards AI systems that can learn, remember, reason, and plan

A presentation by Yann Lecun on the #SOTA in #DL

YouTube: https://www.youtube.com/watch?v=MiqLoAZFRSE
Slides: Google Doc
Paper: Open Review

P.S. Stole the post from @chillhousetech

Data Science by ODS.ai 🦜

02 Apr 2024 15:00

Position: Analyst/Researcher for AI Team at Cyber.fund

About Cyber.fund:
Cyber.fund is a pioneering $100mm research-driven fund specializing in the realm of web3, decentralized AI, autonomous agents, and self-sovereign identity. Our legacy is built upon being the architects behind monumental projects such as Lido, p2p.org, =nil; foundation, Neutron, NEON, and early investments in groundbreaking technologies like Solana, Ethereum, EigenLayer among 150+ others. We are committed to advancing the frontiers of Fully Homomorphic Encryption (FHE) for Machine Learning, privacy-first ML (Large Language Models), AI aggregations, and routing platforms alongside decentralized AI solutions.

Who Are We Looking For?
A dynamic individual who straddles the worlds of business acumen and academic rigor with:
- A robust theoretical foundation in Computer Science and a must-have specialization in Machine Learning.
- An educational background from a technical university, with a preference for PhD holders from prestigious institutions like MIT or МФТИ.
- A track record of publications in the Machine Learning domain, ideally at the level of NeuroIPS.
- Experience working in startups or major tech companies, ideally coupled with a background in angel investing.
- A profound understanding of algorithms, techniques, and models in ML, with an exceptional ability to translate these into innovative products.
- Fluent English, intellectual curiosity, and a fervent passion for keeping abreast of the latest developments in AI/ML.

Responsibilities:
1) Investment Due Diligence: Conduct technical, product, and business analysis of potential AI/ML investments. This includes market analysis, engaging with founders and technical teams, and evaluating the scalability, reliability, risks, and limitations of products.

2) Portcos Support: Provide strategic and technical support to portfolio companies in AI/ML. Assist in crafting technological strategies, hiring, industry networking, identifying potential project challenges, and devising solutions.

3) Market and Technology Research: Stay at the forefront of ML/DL/AI trends (e.g., synthetic data, flash attention, 1bit LLM, FHE for ML, JEPA, etc.). Write publications, whitepapers, and potentially host X spaces/streams/podcasts on these subjects (in English). Identify promising companies and projects for investment opportunities.

How to Apply?
If you find yourself aligning with our requirements and are excited by the opportunity to contribute to our vision, please send your CV to sg@cyber.fund. Including a cover letter, links to publications, open-source contributions, and other achievements will be advantageous.

Location:
Location is flexible, but the candidate should be within the time zones ranging from EET to EST (Eastern Europe to the East Coast of the USA).

This is not just a job opportunity; it's a call to be part of a visionary journey reshaping the landscape of AI and decentralized technology. Join us at Cyber.fund and be at the forefront of the technological revolution.

Data Science by ODS.ai 🦜

02 Oct 2023 07:25

Well, AI can learn that humans might be deceiving.

Data Science by ODS.ai 🦜

22 Sep 2023 17:27

Hey, please boost our channel to allow us to post stories.

We solemnly swear to post only memes there.

/channel/opendatascience?boost

Data Science by ODS.ai 🦜

14 Sep 2023 06:44

​​TSMixer: An All-MLP Architecture for Time Series Forecasting

Time-series datasets in real-world scenarios are inherently multivariate and riddled with intricate dynamics. While recurrent or attention-based deep learning models have been the go-to solution to address these complexities, recent discoveries have shown that even basic univariate linear models can surpass them in performance on standard academic benchmarks. As an extension of this revelation, the paper introduces the Time-Series Mixer TSMixer. This innovative design, crafted by layering multi-layer perceptrons, hinges on mixing operations across both time and feature axes, ensuring an efficient extraction of data nuances.

Upon application, TSMixer has shown promising results. Not only does it hold its ground against specialized state-of-the-art models on well-known benchmarks, but it also trumps leading alternatives in the challenging M5 benchmark, a dataset that mirrors the intricacies of retail realities. The paper's outcomes emphasize the pivotal role of cross-variate and auxiliary data in refining time series forecasting.

Paper link: https://arxiv.org/abs/2303.06053
Code link: https://github.com/google-research/google-research/tree/master/tsmixer

A detailed unofficial overview of the paper:
https://andlukyane.com/blog/paper-review-tsmixer

#paperreview #deeplearning #timeseries #mlp

Data Science by ODS.ai 🦜

12 Sep 2023 18:57

Releasing Persimmon-8B

Permisimmon-8B is open-source, fully permissive model. It is trained from scratch using a context size of 16K. The model has 70k unused embeddings for multimodal extensions, and has sparse activations. The inference code combines the speed of C++ implementations (e.g. FasterTransformer) with the flexibility of naive Python inference.

Hidden Size 4096
Heads 64
Layers 36
Batch Size 120
Sequence Length 16384
Training Iterations 375K
Tokens Seen 737B

Code and weights: https://github.com/persimmon-ai-labs/adept-inference

Data Science by ODS.ai 🦜

07 Sep 2023 07:58

​​Contrastive Feature Masking Open-Vocabulary Vision Transformer

Contrastive Feature Masking Vision Transformer (CFM-ViT): a new approach for image-text pretraining that is optimized for open-vocabulary object detection. Unlike traditional masked autoencoders, which typically operate in the pixel space, CFM-ViT uses a joint image-text embedding space for reconstruction. This approach enhances the model's ability to learn region-level semantics. Additionally, the model features a Positional Embedding Dropout to better handle scale variations that occur when transitioning from image-text pretraining to detection finetuning. PED also enables the model to use a "frozen" ViT backbone as a region classifier without loss of performance.

In terms of results, CFM-ViT sets a new benchmark in open-vocabulary object detection with a 33.9 APr score on the LVIS dataset, outperforming the closest competitor by 7.6 points. The model also demonstrates strong capabilities in zero-shot detection transfer. Beyond object detection, it excels in image-text retrieval, outperforming the state of the art on 8 out of 12 key metrics. These features and results position CFM-ViT as a significant advancement in the field of computer vision and machine learning.

Paper link: https://arxiv.org/abs/2309.00775

My overview of the paper:
https://andlukyane.com/blog/paper-review-cfmvit
https://artgor.medium.com/paper-review-contrastive-feature-masking-open-vocabulary-vision-transformer-4639d1bf7043

#paperreview

Data Science by ODS.ai 🦜

02 Sep 2023 14:30

SAM-Med2D ➕

SAM-Med2D, the most comprehensive studies on applying SAM to medical 2D images.

🏆 Самая большая на сегодняшний день база данных по сегментации медицинских изображений (4,6 млн. изображений и 19,7 млн. масок) для обучения моделей.
🏆 Модель файнтюнинга Segment Anything Model (SAM).
🏆 Бенчмарк SAM-Med2D на крупномасштабных наборах данных.

🖥 Github: https://github.com/uni-medical/sam-med2d

🖥 Colab: https://colab.research.google.com/github/uni-medical/SAM-Med2D/blob/main/predictor_example.ipynb

📕 Paper: https://arxiv.org/abs/2308.16184

⭐️ Dataset: https://paperswithcode.com/dataset/sa-1b

ai_machinelearning_big_data