Artificial Intelligence
16.8K subscribers
1.13K photos
18 videos
1 file
1.99K 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‘8❀2πŸ”₯2πŸ₯°1
ZHEM: An Integrated Data Processing Framework for Pretraining Foundation Models

πŸ–₯ Github: https://github.com/emanual20/zhem

πŸ“• Paper: https://arxiv.org/pdf/2402.16358v1.pdf

πŸ”₯Dataset: https://paperswithcode.com/dataset/wikitext-2

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ”₯10❀2πŸ‘1
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation

πŸ–₯ Github: https://github.com/naver/poc

πŸ“• Paper: https://arxiv.org/pdf/2402.16392v1.pdf

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

✨ Tasks: https://paperswithcode.com/task/segmentation

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀9πŸ”₯3πŸ‘1
RENT (Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning, ICLR 2024)

πŸ–₯ Github: https://github.com/BaeHeeSun/RENT

πŸ“• Paper: https://arxiv.org/pdf/2403.02690v1.pdf

πŸ”₯Dataset: https://paperswithcode.com/dataset/cifar-10

✨ Tasks: https://paperswithcode.com/task/learning-with-noisy-labels

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8❀3πŸ”₯3
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘9❀4πŸ₯°1
Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

πŸ–₯ Github: https://github.com/hikvision-research/3dvision

πŸ“• Paper: https://arxiv.org/abs/2403.05117v1

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘11❀2πŸ”₯2
ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

πŸ–₯ Github: https://github.com/Traffic-X/ViT-CoMer

πŸ“• Paper: https://arxiv.org/pdf/2403.07392.pdf

✨ Tasks: https://paperswithcode.com/task/object-detection

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8πŸ”₯4❀1
Scattered Mixture-of-Experts Implementation

πŸ–₯ Github: https://github.com/shawntan/scattermoe

πŸ“• Paper: https://arxiv.org/abs/2403.08245v1

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ”₯8πŸ‘5❀1
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding

πŸ–₯ Github: https://github.com/opengvlab/video-mamba-suite

πŸ“• Paper: https://arxiv.org/abs/2403.09626v1

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
❀7πŸ‘5πŸ”₯1
CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model

πŸ–₯ Github: https://github.com/andychiangsh/cdgp

πŸ“• Paper: https://github.com/andychiangsh/cdgp

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8❀2πŸ”₯1
[CVPR 2024] Diversity-aware Channel Pruning for StyleGAN Compression

πŸ–₯ Github: https://github.com/jiwoogit/dcp-gan

πŸ“• Paper: https://arxiv.org/pdf/2403.13548v1.pdf

⭐️ Tasks: https://paperswithcode.com/task/image-generation

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘9❀3πŸ‘Ž1
Please open Telegram to view this post
VIEW IN TELEGRAM
❀8πŸ”₯4πŸ‘3
πŸ“Œskscope: Fast Sparse-Constraint Optimization


πŸ–₯ Github: https://github.com/abess-team/skscope

πŸ“• Paper: https://arxiv.org/abs/2403.18540v1

πŸ”₯Dataset: skscope.readthedocs.io
Topics

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘4❀3πŸ”₯2
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations

πŸ–₯ Github: https://github.com/divelab/AIRS

πŸ“• Paper: https://arxiv.org/abs/2403.19507v1

πŸ”₯Project: www.air4.science/
Resources

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8πŸ”₯2❀1
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘10❀2πŸ”₯2
AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

πŸ–₯ Github: https://github.com/thudm/autowebglm

πŸ“• Paper: https://arxiv.org/abs/2404.03648v1

πŸ”₯Dataset: https://paperswithcode.com/dataset/mind2web

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘6❀3πŸ”₯2
πŸ’› Visualizing Attention, a Transformer's Heart

Π’Π½ΠΈΠΌΠ°Π½ΠΈΠ΅ - ΠΊΠ»ΡŽΡ‡Π΅Π²ΠΎΠΉ ΠΌΠ΅Ρ…Π°Π½ΠΈΠ·ΠΌ Π² трансформСрах ΠΈ LLM.

Новый ΠΊΡ€ΡƒΡ‚ΠΎΠΉ ΠΈ ΠΏΠΎΠ΄Ρ€ΠΎΠ±Π½Ρ‹ΠΉ Ρ€Π°Π·Π±ΠΎΡ€ ΠΎΡ‚ 3Blue1Brown.

β–ͺ Π’ΠΈΠ΄Π΅ΠΎ

@data_analysis_ml
❀8πŸ”₯4πŸ‘2
Dynamic Prompt Optimizing for Text-to-Image Generation

πŸ–₯ Github: https://github.com/mowenyii/pae

πŸ“• Paper: https://arxiv.org/abs/2404.04095v1

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
πŸ‘8πŸ”₯3❀2
Mixtral 8x22B weights are now available on 🐢
@TheRealDagsHub

πŸ“¦model: https://dagshub.com/MistralAI/Mixtral-8x22B-v0.1
🌐page: https://mistral.ai

@ArtificialIntelligencedl
πŸ‘11❀3πŸ”₯3