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 451–500 of 9051 papers

TitleStatusHype
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text GenerationCode1
Self-Supervision Improves Diffusion Models for Tabular Data ImputationCode1
Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial OptimizationCode1
A Quantum Leaky Integrate-and-Fire Spiking Neuron and NetworkCode1
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingCode1
DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous DrivingCode1
Diffusion for Out-of-Distribution Detection on Road Scenes and BeyondCode1
Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph GenerationCode1
Personalized Privacy Protection Mask Against Unauthorized Facial RecognitionCode1
Are Large Language Models Capable of Generating Human-Level Narratives?Code1
Learning Semantic Latent Directions for Accurate and Controllable Human Motion PredictionCode1
DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion ModelsCode1
Visual Prompt Selection for In-Context Learning SegmentationCode1
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical ImagingCode1
Dual-stage Hyperspectral Image Classification Model with Spectral SupertokenCode1
Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph DiffusionCode1
Virtual Personas for Language Models via an Anthology of BackstoriesCode1
General and Task-Oriented Video SegmentationCode1
Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual SupportCode1
3D Vision and Language Pretraining with Large-Scale Synthetic DataCode1
FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain GeneralizationCode1
Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking DatasetCode1
RobocupGym: A challenging continuous control benchmark in RobocupCode1
RuBLiMP: Russian Benchmark of Linguistic Minimal PairsCode1
Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across HeadsCode1
Selective Prompting Tuning for Personalized Conversations with LLMsCode1
Variationist: Exploring Multifaceted Variation and Bias in Written Language DataCode1
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning GraphCode1
STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionalsCode1
Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based RecommendationCode1
InternLM-Law: An Open Source Chinese Legal Large Language ModelCode1
Voice Disorder Analysis: a Transformer-based ApproachCode1
Advancing Fine-Grained Classification by Structure and Subject Preserving AugmentationCode1
Latent Denoising Diffusion GAN: Faster sampling, Higher image qualityCode1
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity RecognitionCode1
Concept-skill Transferability-based Data Selection for Large Vision-Language ModelsCode1
FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food CultureCode1
Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata EcosystemsCode1
LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal DataCode1
A Large-scale Universal Evaluation Benchmark For Face Forgery DetectionCode1
Optimal Kernel Orchestration for Tensor Programs with KorchCode1
MMRel: A Relation Understanding Benchmark in the MLLM EraCode1
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic EntropyCode1
Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-TrainingCode1
MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story GenerationCode1
Bootstrapping Referring Multi-Object TrackingCode1
Diversified Batch Selection for Training AccelerationCode1
The ULS23 Challenge: a Baseline Model and Benchmark Dataset for 3D Universal Lesion Segmentation in Computed TomographyCode1
CLoG: Benchmarking Continual Learning of Image Generation ModelsCode1
Improving Geo-diversity of Generated Images with Contextualized Vendi Score GuidanceCode1
Show:102550
← PrevPage 10 of 182Next →

No leaderboard results yet.