Papers with Code 아카이브

Diversity

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Diversity in data sampling is crucial across various use cases, including search, recommendation systems, and more. Ensuring diverse samples means capturing a wide range of variations and perspectives, which leads to more robust, unbiased, and comprehensive models. In search use cases, for instance, diversity helps avoid redundancy, ensuring that users are exposed to a broader set of relevant information rather than repeated similar results.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/smortezah/napr

공식 코드

The chemical space of terpenes: insights from data science and AI

https://github.com/snakeztc/NeuralDialog-CVAE

공식 코드

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

https://github.com/sngdng/msunsupvae

공식 코드

Learning from Multiple Sources for Data-to-Text and Text-to-Data

https://github.com/snipsco/automatic-data-generation

공식 코드

Conditioned Query Generation for Task-Oriented Dialogue Systems

https://github.com/snu-mllab/Co-Mixup

공식 코드

Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity

https://github.com/snudatalab/AugWard

공식 코드

AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classification

https://github.com/soCzech/TransNetV2

공식 코드

TransNet V2: An effective deep network architecture for fast shot transition detection

https://github.com/sobieskibj/gcd

공식 코드

Global Counterfactual Directions

https://github.com/social-info-lab/global_news_synchrony

공식 코드

Global News Synchrony and Diversity During the Start of the COVID-19 Pandemic

https://github.com/socialfoundations/benchbench

공식 코드

Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks

https://github.com/soda-lmu/llm-opinion-german

공식 코드

Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study

https://github.com/sofeeyaj/poetry-in-pixels-coling2025

공식 코드

Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models

https://github.com/softsys4ai/athena

공식 코드

ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense

https://github.com/soheilabadifard/dyned

공식 코드

DynED: Dynamic Ensemble Diversification in Data Stream Classification

https://github.com/sohomd/3D2M-Dataset

공식 코드

3D2M Dataset: A 3-Dimension diverse Mesh Dataset

https://github.com/sonettoo/aerogen

공식 코드

AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation

https://github.com/sony/genwarp

공식 코드

GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

https://github.com/sonyai/a_view_from_somewhere

공식 코드

A View From Somewhere: Human-Centric Face Representations

https://github.com/sonyresearch/responsible_data_curation

공식 코드

Ethical Considerations for Responsible Data Curation

https://github.com/soullessrobot/human-m3-dataset

공식 코드

Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes

https://github.com/soyoung97/standard_korean_gec

공식 코드

Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation

https://github.com/spirit-moon-fly/CAL

공식 코드

Causal-Guided Active Learning for Debiasing Large Language Models

https://github.com/squeezeailab/ets

공식 코드

ETS: Efficient Tree Search for Inference-Time Scaling

https://github.com/sreyan88/abex

공식 코드

ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions

https://github.com/sreyan88/synthio

공식 코드

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

https://github.com/srishtigautam/protovae

공식 코드

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model

https://github.com/ssg-research/distribution-attestation

공식 코드

Attesting Distributional Properties of Training Data for Machine Learning

https://github.com/sssaury/ham

공식 코드

Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification

https://github.com/staeiou/gigo_qss_2021

공식 코드

"Garbage In, Garbage Out" Revisited: What Do Machine Learning Application Papers Report About Human-Labeled Training Data?

https://github.com/stanford-iliad/corgi

공식 코드

Generating Language Corrections for Teaching Physical Control Tasks

https://github.com/stansuro/exgen

공식 코드

Automatic Generation of Word Problems for Academic Education via Natural Language Processing (NLP)

https://github.com/stat-ml/dpp-dropout-uncertainty

공식 코드

Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling

https://github.com/statbiophys/Global_and_Local_Variability_2023

공식 코드

Variability in the local and global composition of human T-cell receptor repertoires during thymic development across cell types and individuals

https://github.com/statbiophys/soNNia

공식 코드

Deep generative selection models of T and B cell receptor repertoires with soNNia

https://github.com/statbiophys/star

공식 코드

Computational detection of antigen specific B cell receptors following immunization

https://github.com/statusrank/LibCML

공식 코드

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.