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/gouqi666/rast

공식 코드

Diversify Question Generation with Retrieval-Augmented Style Transfer

https://github.com/goyalanil/DAMVI

공식 코드

Diversity-Aware Weighted Majority Vote Classifier for Imbalanced Data

https://github.com/goyalanil/PB-MVBoost

공식 코드

Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voters

https://github.com/gracexu182/dyng2g

공식 코드

DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs

https://github.com/grayhong/self-diagnosing-gan

공식 코드

Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks

https://github.com/greencubic/lookhere

공식 코드

LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate

https://github.com/grey-area/modular-loss-experiments

공식 코드

To Ensemble or Not Ensemble: When does End-To-End Training Fail?

https://github.com/grimmlab/step-and-reconsider

공식 코드

Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimization

https://github.com/grypesc/seed

공식 코드

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

https://github.com/gtangg12/samesh

공식 코드

Segment Any Mesh: Zero-shot Mesh Part Segmentation via Lifting Segment Anything 2 to 3D

https://github.com/gtfintechlab/LMs-Perceive-Social-Norms

공식 코드

How Inclusively do LMs Perceive Social and Moral Norms?

https://github.com/guanghuixu/AnchorCaptioner

공식 코드

Towards Accurate Text-based Image Captioning with Content Diversity Exploration

https://github.com/guanlinlee/art

공식 코드

ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users

https://github.com/gugarosa/opfython

공식 코드

OPFython: A Python-Inspired Optimum-Path Forest Classifier

https://github.com/guilgautier/DPPy

공식 코드

Zonotope hit-and-run for efficient sampling from projection DPPs

https://github.com/guillermo-navas-palencia/optbinning

공식 코드

Optimal Counterfactual Explanations for Scorecard modelling

https://github.com/guoweixu368/sld-hmp

공식 코드

Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction

https://github.com/guoxoug/ens-div-ood-detect

공식 코드

On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection

https://github.com/gutianpei/mid

공식 코드

Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion

https://github.com/guydav/goals-as-reward-producing-programs

공식 코드

Goals as Reward-Producing Programs

https://github.com/gyhandy/3d-copy-paste

공식 코드

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

https://github.com/hadarishav/beyond-digital-echo-chambers

공식 코드

Beyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion

https://github.com/haha-lisa/mgad-multimodal-guided-artwork-diffusion

공식 코드

Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion

https://github.com/haiduo/Jakiro

공식 코드

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE

https://github.com/haiyunyao/diversemix

공식 코드

Out-Of-Distribution Detection with Diversification (Provably)

https://github.com/hamedr96/antm

공식 코드

ANTM: An Aligned Neural Topic Model for Exploring Evolving Topics

https://github.com/hammoudhasan/diversityssl

공식 코드

On Pretraining Data Diversity for Self-Supervised Learning

https://github.com/hampusgs/smiles-rnn-rl

공식 코드

Utilizing Reinforcement Learning for de novo Drug Design

https://github.com/hanane-djeddal/attributed-ir

공식 코드

An Evaluation Framework for Attributed Information Retrieval using Large Language Models

https://github.com/hannahblo/statistical_multicriteria_evaluation_of_llm-generated_text

공식 코드

Statistical Multicriteria Evaluation of LLM-Generated Text

https://github.com/hannahkirk/prism-alignment

공식 코드

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

https://github.com/hanqi-qi/mirror

공식 코드

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning

https://github.com/hanqi-qi/revisit_monosemanticity

공식 코드

Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective

https://github.com/hans66hsu/gats

공식 코드

What Makes Graph Neural Networks Miscalibrated?

https://github.com/haowang1992/DSN

공식 코드

Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval

https://github.com/happygu0524/multicontrol

공식 코드

Controllable Text Generation via Probability Density Estimation in the Latent Space

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