Artificial Intelligence
16.3K subscribers
1.09K photos
7 videos
1 file
1.95K 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
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5❀2πŸ”₯1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘6πŸ”₯3❀1
Discover and Cure: Concept-aware Mitigation of Spurious Correlation

πŸ–₯ Github: https://github.com/wuyxin/disc

⏩ Paper: https://arxiv.org/pdf/2305.00650v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/metashift

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘6❀2πŸ”₯1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘4πŸ”₯3πŸ₯°2
Multimodal Data Augmentation for Image Captioning using Diffusion Models

πŸ–₯ Github: https://github.com/xiaochr/multimodal-augmentation-image-captioning

⏩ Paper: https://arxiv.org/pdf/2305.01855v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8❀2πŸ”₯2
Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models

πŸ–₯ Github: https://github.com/daochenzha/neuroshard

⏩ Paper: https://arxiv.org/pdf/2305.01868v1.pdf


@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀5πŸ”₯3πŸ‘2
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity

πŸ–₯ Github: https://github.com/fe1ixxu/stratified_mixture_of_experts

⏩ Paper: https://arxiv.org/pdf/2305.02176v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/flores-200

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘3πŸ”₯2❀1
Please open Telegram to view this post
VIEW IN TELEGRAM
❀6πŸ”₯2πŸ‘1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5❀4πŸ‘Ž1
Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow

πŸ–₯ Github: https://github.com/gudovskiy/flowenedet

⏩ Paper: https://arxiv.org/pdf/2305.09610v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ”₯6πŸ‘2❀1
Online Continual Learning Without the Storage Constraint

πŸ–₯ Github: https://github.com/drimpossible/acm

⏩ Paper: https://arxiv.org/pdf/2305.09253v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/yfcc100m

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘7πŸ”₯2❀1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘6❀2πŸ”₯1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘6πŸ”₯2
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8❀1πŸ”₯1
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets

πŸ–₯ Github: https://github.com/cownowan/dass

⏩ Paper: https://arxiv.org/pdf/2305.16948v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/cub-200-2011

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘9❀1πŸ”₯1
Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction

πŸ–₯ Github: https://github.com/chaytonmin/occ-bev

⏩ Paper: https://arxiv.org/pdf/2305.18829v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/imagenet

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘6πŸ”₯1πŸ₯°1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘5❀1πŸ”₯1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ”₯7πŸ‘2❀1
(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy

πŸ–₯ Github: https://github.com/erosenfeld/disagree_discrep

⏩ Paper: https://arxiv.org/pdf/2306.00312v1.pdf

πŸ’¨ Dataset: https://paperswithcode.com/dataset/cifar-10

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀8πŸ‘2πŸ”₯1