Введите текст для поиска
Расширенный поиск каналов

Data Science by ODS.ai 🦜

@opendatascience
Гео и язык канала: не указан, Английский
Категория: Технологии

First Telegram Data Science channel. Covering all technical and popular staff about anything related to Data Science: AI, Big Data, Machine Learning, Statistics, general Math and the applications of former. To reach editors contact: @haarrp

Связанные каналы
Гео и язык канала
не указан, Английский
Категория
Технологии
Статистика
Это ваш канал? Подтвердить История канала
Фильтр публикаций

Data Science by ODS.ai 🦜

18 Apr, 20:44

Открыть в Telegram Поделиться Пожаловаться
Репост из: Machinelearning
Видео недоступно для предпросмотра
Смотреть в Telegram
👑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
1.8k 0 29 18
Data Science by ODS.ai 🦜

16 Apr, 16:50

Открыть в Telegram Поделиться Пожаловаться
Видео недоступно для предпросмотра
Смотреть в Telegram
⚡️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
3.9k 0 16 1 12
Data Science by ODS.ai 🦜

12 Apr, 11:17

Открыть в Telegram Поделиться Пожаловаться
🔥 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
7.4k 2 47 1 22
Data Science by ODS.ai 🦜

10 Apr, 09:35

Открыть в Telegram Поделиться Пожаловаться
🥔 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
Your creative AI assistant to generate ART from textual descriptions
7.9k 1 31 6 44
Data Science by ODS.ai 🦜

9 Apr, 11:06

Открыть в Telegram Поделиться Пожаловаться
⚡️ 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
9.4k 3 135 3 41
Data Science by ODS.ai 🦜

6 Apr, 19:01

Открыть в Telegram Поделиться Пожаловаться
Репост из: Machinelearning
⚡️ 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
8.2k 0 49 4 19
Data Science by ODS.ai 🦜

5 Apr, 11:26

Открыть в Telegram Поделиться Пожаловаться
8.8k 0 46 2 18
Data Science by ODS.ai 🦜

2 Apr, 16:01

Открыть в Telegram Поделиться Пожаловаться
Let’s get back to posting 😌
9.7k 0 2 4 26
Data Science by ODS.ai 🦜

2 Apr, 16:00

Открыть в Telegram Поделиться Пожаловаться
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.
10.2k 0 14 1 47
Data Science by ODS.ai 🦜

10 Mar, 09:34

Открыть в Telegram Поделиться Пожаловаться
LLM models are in their childhood years

@yannlecun/post/C4TONRKrCgx/?xmt=AQGzgyqvMeJEC2KowLslWxsAN6dSxycXtm1O-gfJ9FPLlQ' rel='nofollow'>Source.
19.8k 1 49 6 80
Data Science by ODS.ai 🦜

1 Feb, 23:54

Открыть в Telegram Поделиться Пожаловаться
35.1k 0 40 28 111
Data Science by ODS.ai 🦜

2 Oct 2023, 08:25

Открыть в Telegram Поделиться Пожаловаться
Well, AI can learn that humans might be deceiving.

Upd: as our readers noted, post originally was written by Denis here.
But then Yudkowski retweeted and it was spread on X.
70.8k 0 195 31 274
Data Science by ODS.ai 🦜

27 Sep 2023, 13:50

Открыть в Telegram Поделиться Пожаловаться
59.3k 0 35 2 44
Data Science by ODS.ai 🦜

22 Sep 2023, 18:27

Открыть в Telegram Поделиться Пожаловаться
Hey, please boost our channel to allow us to post stories.

We solemnly swear to post only memes there.

https://t.me/opendatascience?boost
49.4k 0 13 2 89
Data Science by ODS.ai 🦜

14 Sep 2023, 20:22

Открыть в Telegram Поделиться Пожаловаться
Репост из: Machinelearning
🔥 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
34.9k 0 64 2 75
Data Science by ODS.ai 🦜

14 Sep 2023, 07:44

Открыть в Telegram Поделиться Пожаловаться
​​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
34.2k 1 91 8 35
Data Science by ODS.ai 🦜

13 Sep 2023, 17:17

Открыть в Telegram Поделиться Пожаловаться
Репост из: Machinelearning
Видео недоступно для предпросмотра
Смотреть в Telegram
📹 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
25.2k 0 69 35
Data Science by ODS.ai 🦜

12 Sep 2023, 19:57

Открыть в Telegram Поделиться Пожаловаться
Репост из: ml4se
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
23.3k 0 22 4 8
Data Science by ODS.ai 🦜

11 Sep 2023, 08:11

Открыть в Telegram Поделиться Пожаловаться
Репост из: Data, Stories and Languages
​​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
24.3k 0 45 4 28
Data Science by ODS.ai 🦜

7 Sep 2023, 08:58

Открыть в Telegram Поделиться Пожаловаться
Репост из: Data, Stories and Languages
​​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
31.5k 0 42 3 24
Показано 20 последних публикаций.