379K subscribers
4.38K photos
835 videos
17 files
4.86K links
Погружаемся в машинное обучение и Data Science

Показываем как запускать любые LLm на пальцах.

По всем вопросам - @haarrp

@itchannels_telegram -🔥best channels

Реестр РКН: clck.ru/3Fmqri
Download Telegram
Register for the International Data Analysis Olympiad (IDAO-2021)! The registration continues until March 12.

This year, HSE Faculty of Computer Science and Yandex are holding the Olympiad for the fourth time. This year's Platinum Partner is ‘Otkritie’ Bank. The Olympiad is organised by leading data analysts for their future colleagues, early career analysts and scientists.

The online tour will focus on the search for dark matter - one of the few remaining mysteries of fundamental physics. Dark matter cannot be seen because it does not interact with light and interacts very weakly with ordinary matter. The task of IDAO participants is to build a model that recognises some known observation processes, so that they can be excluded from the search for dark matter.

Details and registration https://idao.world
Precise Multi-Neuron Abstractions for Neural Network Certification

Github : https://github.com/eth-sri/eran

Paper: https://arxiv.org/abs/2103.03638v1

@ai_machinelearning_big_data
👔 Virtual Try-on via Distilling Appearance Flows, CVPR 2021

Github: https://github.com/geyuying/PF-AFN

Paper: https://arxiv.org/abs/2103.04559

@ai_machinelearning_big_data
Involution: Inverting the Inherence of Convolution for Visual Recognition

Github: https://github.com/d-li14/involution

Paper: https://arxiv.org/abs/2103.06255

OpenMMLab: https://openmmlab.com/

@ai_machinelearning_big_data
This media is not supported in your browser
VIEW IN TELEGRAM
Strawberry Fields is a full-stack Python library for designing, simulating, and optimizing continuous-variable quantum optical circuits.

Github: https://github.com/XanaduAI/strawberryfields

Paper: https://arxiv.org/pdf/2103.05530v1.pdf

@ai_machinelearning_big_data
This media is not supported in your browser
VIEW IN TELEGRAM
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

Github: https://github.com/hkchengrex/MiVOS

Paper: https://arxiv.org/pdf/2103.07941v1.pdf

@ai_machinelearning_big_data
Probabilistic two-stage detection

Two-stage object detectors that use class-agnostic one-stage detectors as the proposal network.

Github: https://github.com/xingyizhou/CenterNet2

Paper: https://arxiv.org/abs/2103.07461v1


@ai_machinelearning_big_data
Large Scale Image Completion via Co-Modulated Generative Adversarial Networks, ICLR 2021 (Spotlight)

Gitub: https://github.com/zsyzzsoft/co-mod-gan

Paper: https://openreview.net/pdf?id=sSjqmfsk95O

Demo: http://comodgan.ml/

@ai_machinelearning_big_data