Conformal prediction under ambiguous ground truth

Paper: https://arxiv.org/pdf/2307.09302v2.pdf

Codes:

https://github.com/google-deepmind/uncertain_ground_truth

https://github.com/alaalab/webcp

Dataset: Dermatology ddx dataset

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

WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Paper: https://arxiv.org/pdf/2408.16532v1.pdf

Code: https://github.com/jishengpeng/wavtokenizer

Dataset: AudioSet LibriTTS SLURP

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

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Paper: https://arxiv.org/pdf/2408.15998v1.pdf

Code: https://github.com/nvlabs/eagle

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

Text2SQL is Not Enough: Unifying AI and Databases with TAG

Paper: https://arxiv.org/pdf/2408.14717v1.pdf

Code: https://github.com/tag-research/tag-bench

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

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Paper: https://arxiv.org/pdf/2408.16725v2.pdf

Code: https://github.com/gpt-omni/mini-omni

Dataset: LibriSpeech

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

DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification

Paper:https://arxiv.org/pdf/2407.03575v1.pdf

Code: https://github.com/chongqingnosubway/dgr-mil

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

aTENNuate: is a network that can be configured for real-time speech enhancement on raw audio waveforms.

🖥 Github: https://github.com/Brainchip-Inc/aTENNuate

📕 Paper: https://arxiv.org/abs/2409.03377v1

🚀 Dataset:  https://paperswithcode.com/dataset/deep-noise-suppression-2020

💡 1M-Deepfakes Detection Challenge

🖥 Github: https://github.com/controlnet/av-deepfake1m

📕 Paper: https://arxiv.org/abs/2409.06991v1

⚡️ Dataset: https://paperswithcode.com/dataset/celeb-df

BEST AI RESEARCH PAPER SUMMARIZERS

Paperguide - Provides tools for extracting key insights, managing references, and annotating documents within PDFs to enhance study and research.

Tenorshare AI PDF Tool - Quickly analyzes and condenses papers using AI, and features an interactive chat interface powered by ChatGPT.

Elicit - Improves how users find and summarize academic papers using intelligent search and natural language processing to generate concise summaries.

QuillBot - Leverages AI for its Summarizer tool to analyze documents and generate extractive summaries, customizing length and format.

Semantic Scholar - An AI-powered academic search engine that generates one-sentence paper summaries and identifies influential citations.

IBM Watson Discovery - Harnesses cognitive computing to understand context within texts and enable precise searches across large document libraries for summarization.

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

LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Paper: https://arxiv.org/pdf/2409.06666v1.pdf

Code: https://github.com/ictnlp/llama-omni

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

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Paper: https://arxiv.org/pdf/2408.16725v2.pdf

Code: https://github.com/gpt-omni/mini-omni

Dataset: LibriSpeech

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

MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery

Paper: https://arxiv.org/pdf/2409.05591v2.pdf

Code: https://github.com/qhjqhj00/memorag

Dataset: GovReport

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

Data Science Cheat Sheets
Quick help to make a data scientist's life easier

About Dataset
A collection of cheat sheets for various data-science related languages and topics


http://t.me/codeprogrammer 🔒

💡 #deeplearning #AI #ML #python

Data Science Cheat Sheets
Quick help to make a data scientist's life easier ✅

http://t.me/codeprogrammer 🔒

💡 #deeplearning #AI #ML #python

🖥 UNet 3+ Implementation in TensorFlow

This article presents an implementation of the UNet 3+ architecture using TensorFlow.

UNet 3+ extends the classic UNet and UNet++ architecture.

This article looks at each block of the UNet 3+ architecture and explains how they work and what helps improve the performance of the model.

Understanding these blocks will help us understand the mechanisms behind UNet 3+ and how it effectively tackles tasks such as image segmentation or other pixel-wise prediction tasks.

https://idiotdeveloper.com/unet-3-plus-implementation-in-tensorflow/

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

SGFormer: Simplified Graph Transformers

🖥 Github: https://github.com/qitianwu/sgformer

📕 Paper: https://arxiv.org/pdf/2306.10759.pdf

🤗 Blog: https://zhuanlan.zhihu.com/p/674548352