SOTAVerified

Diversity

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5651–5700 of 9051 papers

TitleStatusHype
Rethinking and Refining the Distinct Metric—0
On the Importance of Data Size in Probing Fine-tuned Models—0
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities—0
First the worst: Finding better gender translations during beam search—0
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech—0
A Natural Diet: Towards Improving Naturalness of Machine Translation Output—0
Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling—0
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference—0
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation—0
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning—0
Measuring HLT Research Equality of European Languages—0
Evaluating Inclusivity, Equity, and Accessibility of NLP Technology: A Case Study for Indian Languages—0
Linguistic Diversity Scores for NLP Data Sets—0
Computational historical linguistics and language diversity in South Asia—0
SHCT: A Successively Hierarchical Conditional Transformer for Controllable Paraphrase Generation—0
The role of attraction-repulsion dynamics in simulating the emergence of inflectional class systems—0
Thermodynamic constraints on the assembly and diversity of microbial ecosystems are different near to and far from equilibrium—0
An Empirical Study of Finding Similar Exercises—0
Words of Wisdom: Representational Harms in Learning From AI Communication—0
Modelling the effect of within-host dynamics on the diversity of a multi-strain pathogenCode0
Synthetic Unknown Class Learning for Learning Unknowns—0
Exploring Story Generation with Multi-task Objectives in Variational Autoencoders—0
Benchmarking deep generative models for diverse antibody sequence design—0
Detecting Quality Problems in Data Models by Clustering Heterogeneous Data Values—0
Scalable Diverse Model Selection for Accessible Transfer LearningCode1
Diversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder—0
A Spiking Neuron Synaptic Plasticity Model Optimized for Unsupervised Learning—0
Global and local epidemiology of Group A Streptococcus indicates that naturally-acquired immunity is enduring and strain-specific—0
AlphaGarden: Learning to Autonomously Tend a Polyculture GardenCode1
Palette: Image-to-Image Diffusion ModelsCode2
Complementary Ensemble Learning—0
Towards Active Vision for Action Localization with Reactive Control and Predictive LearningCode1
Mito-nuclear selection induces a trade-off between species ecological dominance and evolutionary lifespanCode0
There is no Double-Descent in Random ForestsCode0
Universal and data-adaptive algorithms for model selection in linear contextual bandits—0
Increasing Data Diversity with Iterative Sampling to Improve Performance—0
Functional connectivity ensemble method to enhance BCI performance (FUCONE)Code1
Generating Diverse Realistic Laughter for Interactive Art—0
Qimera: Data-free Quantization with Synthetic Boundary Supporting SamplesCode1
Testing macroecological theories in cryptocurrency market: neutral models can not describe diversity patterns and their variation—0
Oblique and rotation double random forest—0
First experimental evaluation of ambient backscatter communications with massive MIMO reader—0
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP—0
ISP-Agnostic Image Reconstruction for Under-Display Cameras—0
Collaborative Data Relabeling for Robust and Diverse Voice Apps Recommendation in Intelligent Personal Assistants—0
Toward Deconfounding the Effect of Entity Demographics for Question Answering Accuracy—0
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context—0
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation NetworksCode0
CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation—0
Minimizing Annotation Effort via Max-Volume Spectral Sampling—0
Show:102550
← PrevPage 114 of 182Next →

No leaderboard results yet.