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

Showing 5175 of 9051 papers

TitleStatusHype
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language ModelsCode3
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisCode3
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human SupervisionCode3
MiniViT: Compressing Vision Transformers with Weight MultiplexingCode3
MNN: A Universal and Efficient Inference EngineCode3
CRITERIA: a New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous DrivingCode3
Objaverse-XL: A Universe of 10M+ 3D ObjectsCode3
Results of the Big ANN: NeurIPS'23 competitionCode3
SVIT: Scaling up Visual Instruction TuningCode3
Improving Text Embeddings with Large Language ModelsCode3
Sequential Modeling Enables Scalable Learning for Large Vision ModelsCode3
INTERS: Unlocking the Power of Large Language Models in Search with Instruction TuningCode3
LongAlign: A Recipe for Long Context Alignment of Large Language ModelsCode3
Hierarchical Text-Conditional Image Generation with CLIP LatentsCode3
Improved motif-scaffolding with SE(3) flow matchingCode3
Addressing the Abstraction and Reasoning Corpus via Procedural Example GenerationCode3
Generating Long Sequences with Sparse TransformersCode3
Improving Model Evaluation using SMART Filtering of Benchmark DatasetsCode3
Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2Code3
FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse LandscapesCode3
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative WarpingCode3
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture ModelingCode3
Anything-3D: Towards Single-view Anything Reconstruction in the WildCode3
Elucidating the Design Space of Multimodal Protein Language ModelsCode3
AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha FactorsCode3
Show:102550
← PrevPage 3 of 363Next →

No leaderboard results yet.