Human-Guided Complexity-Controlled Abstractions

🖥 Github: https://github.com/mycal-tucker/human-guided-abstractions

📕 Paper: https://arxiv.org/pdf/2310.17550v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/fashion-mnist

https://news.1rj.ru/str/DataScienceT

DialogLLMScenic

🖥 Github: https://github.com/avmb/dialogllmscenic

📕 Paper: https://arxiv.org/pdf/2310.17372v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/carla

⭐ Tasks: https://paperswithcode.com/task/self-driving-cars

https://news.1rj.ru/str/DataScienceT

⚡️ LLMRec: Large Language Models with Graph Augmentation for Recommendation

🖥 Github: https://github.com/hkuds/llmrec

📕 Paper: https://arxiv.org/abs/2311.00423v1

⏩ Project: https://llmrec.github.io/

🌐 Dataset: https://llmrec.github.io/#

https://news.1rj.ru/str/DataScienceT

🖥 TORCH UNCERTAINTY

Comprehensive PyTorch Library for deep learning uncertainty quantification techniques.

pip install torch-uncertainty

🖥 Github: https://github.com/ensta-u2is/torch-uncertainty

📕 Paper: https://arxiv.org/abs/2311.01434v1

⏩ Project: https://llmrec.github.io/

👣 Api: https://torch-uncertainty.github.io/api.html

🌐 Dataset: https://paperswithcode.com/dataset/cifar-10

https://news.1rj.ru/str/DataScienceT

PETA: Evaluating the Impact of Protein Transfer Learning with Sub-word Tokenization on Downstream Applications

🖥 Github: https://github.com/ginnm/proteinpretraining

📕 Paper: https://arxiv.org/pdf/2310.17415v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/peta-protein

⭐ Tasks: https://paperswithcode.com/task/language-modelling

https://news.1rj.ru/str/DataScienceT

🎧 Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model.

🖥 Github: https://github.com/amaai-lab/video2music

📕 Paper: https://arxiv.org/abs/2311.00968v1

⏩ Demo: https://llmrec.github.io/

🌐 Dataset: https://zenodo.org/records/10057093

https://news.1rj.ru/str/DataScienceT

Data Science Math Skills (Free Course)

Enroll Link: https://www.clcoding.com/2023/10/data-science-math-skills-free-course.html?m=1

https://news.1rj.ru/str/DataScienceT

Top execs from billion-dollar giants are whispering about next crypto "GEM". Want in?

This Tuesday, Blockchain Whispers pulls back the curtain. Join the insiders now: https://news.1rj.ru/str/+c5yEZuGFtsc5NDlk

🔥 One of the most beautiful interactive visualizations on how LLMs work.

http://ig.ft.com/generative-ai/

https://news.1rj.ru/str/DataScienceT

🚀 Introducing YOLO-NAS Pose : A Game-Changer in Pose Estimation 🚀

This Model is a redefinition of pose estimation's potential.

🖥 Github: https://github.com/Deci-AI/super-gradients

📕 Notebook: https://colab.research.google.com/drive/1O4N5Vbzv0rfkT81LQidPktX8RtoS5A40

🚀 Demo: https://huggingface.co/spaces/Deci/YOLO-NAS-Pose-Demo

🌐 Colab: https://colab.research.google.com/drive/1agLj0aGx48C_rZPrTkeA18kuncack6lF

https://news.1rj.ru/str/DataScienceT

Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Trannoscripts

🖥 Github: https://github.com/shyyhs/CourseraParallelCorpusMining

📕 Paper: https://arxiv.org/abs/2311.03696v1

🔥 Datasets: https://paperswithcode.com/dataset/aspec

https://news.1rj.ru/str/DataScienceT

Large Language Models (in 2023)

An excellent summary of the research progress and developments in LLMs.

Hyung Won chung, OpenAI (ex.Google and MIT Alumni) made this content publicly available. It's a great way to catch up on some important themes like scaling and optimizing LLMs.

Watch his talk here and Slides shared here.

https://news.1rj.ru/str/DataScienceT

Soon

Our new channel - Datasets repositories

https://news.1rj.ru/str/datasets1

NVIDIA just made Pandas 150x faster with zero code changes.

All you have to do is:

%load_ext cudf.pandas
import pandas as pd

Their RAPIDS library will automatically know if you're running on GPU or CPU and speed up your processing.

You can try it in this colab notebook

GitHub repo: https://github.com/rapidsai/cudf

https://news.1rj.ru/str/DataScienceT

Conic10K

🖥 Github:https://github.com/whynlp/conic10k

📕 Paper: https://arxiv.org/pdf/2311.05113v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/gsm8k

✨ Tasks: https://paperswithcode.com/task/natural-language-understanding

https://news.1rj.ru/str/DataScienceT

⚡️ LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference.

pip install diffusers transformers accelerate gradio==3.48.0

🖥 Github: https://github.com/luosiallen/latent-consistency-model

📕 Paper: https://arxiv.org/abs/2311.05556v1

🌐 Project: https://latent-consistency-models.github.io

🤗 Demo: https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model

https://news.1rj.ru/str/DataScienceT

Quantized Distillation for Driver Activity Recognition

🖥 Github: https://github.com/calvintanama/qd-driver-activity-reco

📕 Paper: https://arxiv.org/pdf/2311.05970v1.pdf

🔥 Datasets: https://paperswithcode.com/dataset/drive-act

✨ Tasks: https://paperswithcode.com/task/activity-recognition

https://news.1rj.ru/str/DataScienceT