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/ZhihongShao/Planning-based-Hierarchical-Variational-Model

공식 코드

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

https://github.com/ZhimingZhou/AM-GAN

공식 코드

Activation Maximization Generative Adversarial Nets

https://github.com/ZhouYuxuanYX/Benchmarking-and-Guiding-Adaptive-Sampling-Decoding-for-LLMs

공식 코드

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation

https://github.com/ZubinGou/multi-view-prompting

공식 코드

MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction

https://github.com/a773938364/divkd

공식 코드

A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving

https://github.com/aaltopml/forde

공식 코드

Input-gradient space particle inference for neural network ensembles

https://github.com/aaltopml/node-bnn-covariate-shift

공식 코드

Tackling covariate shift with node-based Bayesian neural networks

https://github.com/aashish2000/rona

공식 코드

RONA: Pragmatically Diverse Image Captioning with Coherence Relations

https://github.com/aaupadhy/AmCLR

공식 코드

AmCLR: Unified Augmented Learning for Cross-Modal Representations

https://github.com/abanitalebi/Model-Composition

공식 코드

Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?

https://github.com/abc-125/viad-benchmark

공식 코드

Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detection

https://github.com/abdelkarim-elhajjami/synthline

공식 코드

Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models

https://github.com/abhishektandon/bspline-fc

공식 코드

Generating Realistic Forehead-Creases for User Verification via Conditioned Piecewise Polynomial Curves

https://github.com/abrar2652/nlp-roberta-bilstm-attention

공식 코드

A hybrid transformer and attention based recurrent neural network for robust and interpretable sentiment analysis of tweets

https://github.com/acsicuib/ga4fogplacement

공식 코드

Evaluation and Efficiency Comparison of Evolutionary Algorithms for Service Placement Optimization in Fog Architectures

https://github.com/acstarnes/wain23-policy-regularization

공식 코드

Increasing Entropy to Boost Policy Gradient Performance on Personalization Tasks

https://github.com/adam-katona/QualityEvolvabilityES

공식 코드

Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspring

https://github.com/adaptive-intelligent-robotics/AURORA

공식 코드

Unsupervised Behaviour Discovery with Quality-Diversity Optimisation

https://github.com/adaptive-intelligent-robotics/DCRL-MAP-Elites

공식 코드

Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning

https://github.com/adaptive-intelligent-robotics/MOUR-QD

공식 코드

Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces

https://github.com/adaptive-intelligent-robotics/Multi-Emitter_Map-Elites

공식 코드

Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters

https://github.com/adaptive-intelligent-robotics/dominated-novelty-search

공식 코드

Dominated Novelty Search: Rethinking Local Competition in Quality-Diversity

https://github.com/adaptive-intelligent-robotics/hte

공식 코드

Hierarchical Quality-Diversity for Online Damage Recovery

https://github.com/adaptive-intelligent-robotics/mome_pgx

공식 코드

Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration

https://github.com/adaptive-intelligent-robotics/moqd-csp

공식 코드

Multi-Objective Quality-Diversity for Crystal Structure Prediction

https://github.com/adaptive-intelligent-robotics/pga-map-elites

공식 코드

Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains

https://github.com/adaptive-intelligent-robotics/qdac

공식 코드

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

https://github.com/adaptive-intelligent-robotics/qdax

공식 코드

Accelerated Quality-Diversity through Massive Parallelism

https://github.com/adaptive-intelligent-robotics/uncertain_quality_diversity

공식 코드

Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains

https://github.com/adhyasuman/ctmneg

공식 코드

Improving Contextualized Topic Models with Negative Sampling

https://github.com/adiko1997/revit

공식 코드

ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections

https://github.com/adlab-autodrive/ickd

공식 코드

Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation

https://github.com/advocate99/diffgesture

공식 코드

Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation

https://github.com/adwardlee/renderih

공식 코드

RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation

https://github.com/adxcreative/rice

공식 코드

Cross-view Semantic Alignment for Livestreaming Product Recognition

https://github.com/adymaharana/d2pruning

공식 코드

D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning

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