82 datasets found

The UAV20L dataset is a benchmark for visual tracking.

The OTB-2013 dataset is a benchmark for visual tracking.

A benchmark dataset for grounding natural language referring expressions to distinguish 3D objects.

A comprehensive multi-modal video understanding benchmark.

The nvBench dataset is a benchmark for text-to-vis models, containing natural language questions and their corresponding data visualizations.

The 3DLoMatch [12] is a registration dataset with low overlap pairs between 10% − 30%.

The ACE and CoNLL04 datasets are widely used entity-relation extraction benchmarks.

The dataset used in the paper is the HumanEval dataset, which is used to evaluate the performance of language models.

The SciMT-Safety dataset is a benchmark for evaluating the safety of AI systems in science. It consists of hundreds of refined red-teaming queries that span the fields of...

The SciGuard dataset is a benchmark for evaluating the safety of AI systems in science. It consists of hundreds of refined red-teaming queries that span the fields of chemistry...

A benchmark for neural architecture search.

A benchmark for automated machine learning.

The PennML benchmark suite consists of over 90 regression problems and provides a performance overview of several common regression algorithms.

The dataset used in this paper is the CEC2013 benchmark functions.

The dataset used in the paper is a collection of robot locomotion tasks with various constraints.

The Building a conversational agent overnight with dialogue self-play dataset is a benchmark for conversational AI.

A video benchmark for binaural audio generation from video.

The AI-Feynman database is a widely used public benchmark for symbolic regression.

The Keijzer benchmark is a widely used public benchmark for symbolic regression.

The Nguyen benchmark is a widely used public benchmark for symbolic regression.