Artificial Intelligence
16.9K subscribers
1.13K photos
17 videos
1 file
2K links
Artificial Intelligence

admin - @haarrp

@itchannels_telegram - πŸ”₯ best it channels

@ai_machinelearning_big_data - Machine learning channel

@pythonl - Our Python channel

@pythonlbooks- python ΠΊΠ½ΠΈΠ³ΠΈπŸ“š

@datascienceiot - ml πŸ“š

РКН: clck.ru/3FmwZw
Download Telegram
πŸš€ Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset


πŸ–₯ Github: https://github.com/liamlian0727/usis10k

πŸ“•Paper: https://arxiv.org/abs/2406.06039v1

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘4❀2
TSI-Bench: Benchmarking Time Series Imputation

πŸ–₯ Github: https://github.com/WenjieDu/Awesome_Imputation

πŸ“• Paper: https://arxiv.org/pdf/2406.12747v1.pdf

πŸ”₯Dataset: https://github.com/WenjieDu/TSDB

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5❀3πŸ”₯2
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘4πŸ”₯3❀2
LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments

πŸ–₯ Github: https://github.com/bigai-nlco/langsuite

πŸ“• Paper: https://arxiv.org/abs/2406.16294v1

πŸ”₯Dataset: https://paperswithcode.com/dataset/ai2-thor

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ”₯7πŸ‘2❀1
Point-SAM: Promptable 3D Segmentation Model for Point Clouds

πŸ–₯ Github: https://github.com/zyc00/point-sam

πŸ“• Paper: https://arxiv.org/abs/2406.17741v1

πŸ”₯Dataset: https://paperswithcode.com/dataset/shapenet

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘2πŸ”₯2❀1
πŸ₯ MedMNIST-C: benchmark dataset based on the MedMNIST+ collection covering 12 2D datasets and 9 imaging modalities.

pip install medmnistc

πŸ–₯ Github: https://github.com/francescodisalvo05/medmnistc-api

πŸ“• Paper: https://arxiv.org/abs/2406.17536v2

πŸ”₯Dataset: https://paperswithcode.com/dataset/imagenet-c

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘3❀2
New open model alert by Shanghai AI Laboratory 🚨

Welcome Internal 2.5
πŸ”₯Very high quality 7B model
πŸš€Up to 1 million context window
πŸ”§Tool usage capabilities

Looking forward to playing with it

https://huggingface.co/collections/internlm/internlm25-66853f32717072d17581bc13

@ArtificialIntelligencedl
❀2πŸ”₯2πŸ‘1
βš‘οΈΠ›ΡƒΡ‡ΡˆΠΈΠΉ способ ΠΏΠΎΠ»ΡƒΡ‡Π°Ρ‚ΡŒ свСТиС обновлСния ΠΈ ΡΠ»Π΅Π΄ΠΈΡ‚ΡŒ Π·Π° Ρ‚Ρ€Π΅Π½Π΄Π°ΠΌΠΈ Π² Ρ€Π°Π·Ρ€Π°Π±ΠΎΡ‚ΠΊΠ΅ Π½Π° вашСм языкС. НаходитС свой стСк ΠΈ ΠΏΠΎΠ΄ΠΏΠΈΡΡ‹Π²Π°ΠΉΡ‚Π΅ΡΡŒ:

C++ t.me/cpluspluc
Devops: t.me/devOPSitsec
МашинноС ΠΎΠ±ΡƒΡ‡Π΅Π½ΠΈΠ΅: t.me/ai_machinelearning_big_data
ΠΠΠΠ›Π˜Π— Π”Π°Π½Π½Ρ‹Ρ…: t.me/data_analysis_ml
Π₯Π°ΠΊΠΈΠ½Π³: t.me/linuxkalii
Linux: t.me/linuxacademiya
Π‘Π°Π·Ρ‹ Π΄Π°Π½Π½Ρ‹Ρ…: t.me/sqlhub
C#: t.me/csharp_ci
Golang: t.me/Golang_google
Java: t.me/javatg
React: t.me/react_tg
Javascript: t.me/javascriptv
Мобильная Ρ€Π°Π·Ρ€Π°Π±ΠΎΡ‚ΠΊΠ°: t.me/mobdevelop
Docker: t.me/+0WdB4uvOwCY0Mjdi
Python: t.me/pythonl
Rust: t.me/rust_code
PHP: t.me/phpshka
Android: t.me/android_its
Big Data: t.me/bigdatai
БобСсСдования ΠœΠ›: t.me/machinelearning_interview
Python ΠΏΠΎΠ΄Π³ΠΎΡ‚ΠΎΠ²ΠΊΠ° с собСсу: t.me/python_job_interview
ΠœΠΠ’Π•ΠœΠΠ’Π˜ΠšΠ: t.me/data_math

πŸ’Ό Папка с вакансиями: t.me/addlist/_zyy_jQ_QUsyM2Vi
Папка Go Ρ€Π°Π·Ρ€Π°Π±ΠΎΡ‚Ρ‡ΠΈΠΊΠ°: t.me/addlist/MUtJEeJSxeY2YTFi
Папка Python Ρ€Π°Π·Ρ€Π°Π±ΠΎΡ‚Ρ‡ΠΈΠΊΠ°: t.me/addlist/eEPya-HF6mkxMGIy
Папка ML: https://t.me/addlist/2Ls-snqEeytkMDgy
C++ ΠΏΠ°ΠΏΠΊΠ°: https://t.me/addlist/CdBs5DLepLJmZjY6
C# ΠΏΠ°ΠΏΠΊΠ°: https://t.me/addlist/u15AMycxRMowZmRi
Java ΠΏΠ°ΠΏΠΊΠ°: https://t.me/addlist/ZM3J6oFNAnRlNWU6
FRONTEND ΠΏΠ°ΠΏΠΊΠ°: https://t.me/addlist/mzMMG3RPZhY2M2Iy
Linux ΠΏΠ°ΠΏΠΊΠ°: https://t.me/addlist/w4Doot-XBG4xNzYy

πŸ˜†Π˜Π’-ΠœΠ΅ΠΌΡ‹: t.me/memes_prog
πŸ‡¬πŸ‡§ΠΠ½Π³Π»ΠΈΠΉΡΠΊΠΈΠΉ: t.me/english_forprogrammers
🧠ИИ: t.me/vistehno

πŸ“•Π˜Ρ‚-ΠΊΠ½ΠΈΠ³ΠΈ бСсплатно: https://t.me/addlist/BkskQciUW_FhNjEy
❀1πŸ‘1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5πŸ”₯2❀1
Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling

πŸ–₯ Github: https://github.com/linghuyuhangyuan/m2s

πŸ“• Paper: https://arxiv.org/abs/2407.05875v1

πŸ”₯Dataset: https://paperswithcode.com/task/denoising
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘3πŸ”₯2❀1
Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation (ECCV 2024)

πŸ–₯ Github: https://github.com/fanghaook/ovformer

πŸ“• Paper: https://arxiv.org/abs/2407.07427v1

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘3πŸ”₯2❀1
Multimodal contrastive learning for spatial gene expression prediction using histology images

πŸ–₯ Github: https://github.com/shizhiceng/mclstexp

πŸ“• Paper: https://arxiv.org/abs/2407.08216v1

πŸ”₯Dataset: https://doi.org/10.48610/4fb74a9.

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀3πŸ‘2πŸ”₯2
Multimodal contrastive learning for spatial gene expression prediction using histology images

πŸ–₯ Github: https://github.com/modelscope/data-juicer

πŸ“• Paper: https://arxiv.org/abs/2407.08583v1

πŸš€ Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5❀2πŸ”₯2
🌟 Gradient Boosting Reinforcement Learning (GBRL)

πŸ–₯ Github: https://github.com/nvlabs/gbrl

πŸ“• Paper: https://arxiv.org/abs/2407.08250v1

πŸš€ Dataset: https://paperswithcode.com/task/reinforcement-learning-2

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀8πŸ‘3πŸ”₯1
🌟 An Empirical Study of Mamba-based Pedestrian Attribute Recognition

πŸ–₯ Github: https://github.com/event-ahu/openpar

πŸ“• Paper: https://arxiv.org/pdf/2407.10374v1.pdf

πŸš€ Dataset: https://paperswithcode.com/dataset/peta

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘4πŸ₯°4πŸ”₯2
Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment

πŸ–₯ Github: https://github.com/kaistmm/SSLalignment

πŸ“• Paper: https://arxiv.org/abs/2407.13676v1

πŸš€ Dataset: https://paperswithcode.com/dataset/is3-interactive-synthetic-sound-source

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘4❀3πŸ”₯3
πŸ–₯ StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset.

πŸ–₯ Github: https://github.com/huochf/StackFLOW

πŸ“• Paper: https://arxiv.org/abs/2407.20545v1

πŸš€ Dataset: https://paperswithcode.com/dataset/behave

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀4πŸ”₯3πŸ‘2
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ”₯4❀2πŸ‘2
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5πŸ”₯3❀2