Artificial Intelligence
12.9K subscribers
948 photos
3 videos
1 file
1.83K links
Artificial Intelligence

admin - @haarrp

@itchannels_telegram - 🔥 best it channels

@ai_machinelearning_big_data - Machine learning channel

@pythonl - Our Python channel

@pythonlbooks- python книги📚

@datascienceiot - ml 📚

@programming_books_it
Download Telegram
Please open Telegram to view this post
VIEW IN TELEGRAM
ZHEM: An Integrated Data Processing Framework for Pretraining Foundation Models

🖥 Github: https://github.com/emanual20/zhem

📕 Paper: https://arxiv.org/pdf/2402.16358v1.pdf

🔥Dataset: https://paperswithcode.com/dataset/wikitext-2

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation

🖥 Github: https://github.com/naver/poc

📕 Paper: https://arxiv.org/pdf/2402.16392v1.pdf

🔥Dataset: https://paperswithcode.com/dataset/cityscapes

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

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
RENT (Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning, ICLR 2024)

🖥 Github: https://github.com/BaeHeeSun/RENT

📕 Paper: https://arxiv.org/pdf/2403.02690v1.pdf

🔥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
Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

🖥 Github: https://github.com/hikvision-research/3dvision

📕 Paper: https://arxiv.org/abs/2403.05117v1

🔥Dataset: https://paperswithcode.com/dataset/scanobjectnn

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

🖥 Github: https://github.com/Traffic-X/ViT-CoMer

📕 Paper: https://arxiv.org/pdf/2403.07392.pdf

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

🔥Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
Scattered Mixture-of-Experts Implementation

🖥 Github: https://github.com/shawntan/scattermoe

📕 Paper: https://arxiv.org/abs/2403.08245v1

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding

🖥 Github: https://github.com/opengvlab/video-mamba-suite

📕 Paper: https://arxiv.org/abs/2403.09626v1

🔥Dataset: https://paperswithcode.com/dataset/egoschema

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model

🖥 Github: https://github.com/andychiangsh/cdgp

📕 Paper: https://github.com/andychiangsh/cdgp

🔥Dataset: https://paperswithcode.com/dataset/cloth

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
📌skscope: Fast Sparse-Constraint Optimization


🖥 Github: https://github.com/abess-team/skscope

📕 Paper: https://arxiv.org/abs/2403.18540v1

🔥Dataset: skscope.readthedocs.io
Topics

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations

🖥 Github: https://github.com/divelab/AIRS

📕 Paper: https://arxiv.org/abs/2403.19507v1

🔥Project: www.air4.science/
Resources

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

🖥 Github: https://github.com/thudm/autowebglm

📕 Paper: https://arxiv.org/abs/2404.03648v1

🔥Dataset: https://paperswithcode.com/dataset/mind2web

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
💛 Visualizing Attention, a Transformer's Heart

Внимание - ключевой механизм в трансформерах и LLM.

Новый крутой и подробный разбор от 3Blue1Brown.

Видео

@data_analysis_ml
Dynamic Prompt Optimizing for Text-to-Image Generation

🖥 Github: https://github.com/mowenyii/pae

📕 Paper: https://arxiv.org/abs/2404.04095v1

🔥Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM