[CVPR-2024] The First High Definition (HD) Event based Visual Object Tracking Benchmark Dataset
[NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding
The MAMA-MIA Dataset: A Multi-Center Breast Cancer DCE-MRI Public Dataset with Expert Segmentations
[Pattern Recognition 2025] A large-scale benchmark dataset for color-event based visual tracking
This repository contains a gym environment that can be used for developing solvers for robotic 3D bin packing problems.
A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation (INTERSPEECH 2022)
[IJCV-2026, arXiv:2408.09764] Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
Dataset package for facile training and testing of machine learning/AI algorithms that predict drug response in cancer model systems.
AdvSV stands as the first dataset developed specifically for evaluating Speaker Verification (SV) systems against adversarial attacks. It aims to benchmark the robustness of ASV models in the face of such attacks and offers vital resources for researchers to explore the characteristics of adversarial and replay attacks in this domain.
The SWAN-SF dataset is now fully preprocessed, optimized, and ready for binary classification tasks. Our team is excited to release the enhanced version of the SWAN-SF dataset across all five partitions.
[FAccT '25] Characterizing Bias: Benchmarking LLMs in Simplified versus Traditional Chinese
Real-time detection and repair of LLM agent failures — a one-class behavioural monitor at ~200 µs/step, with 2,823 committed traces.
Documentation associated with preparing and formatting datasets LARRY datasets for ML applications with pytorch / pytorch lightning
Code for LEMMA-RCA website
100 long-horizon reverse engineering tasks generated by ProgramSmith.
Reproducible FCC synthetic data factory for transaction monitoring - customers, accounts, transactions, alerts, cases - ready for analytics & model testing.
Collaborating to improve population dynamics models through benchmark dataset validation
Open topology-grounded benchmark for datacenter RCA, hidden-target localization, and counterfactual remediation validation.
Benchmarking seven forecasting approaches on AgriPriceBD — a novel daily agricultural commodity price dataset of five commodities for Bangladesh. Covers BiLSTM, Transformer, Time2Vec ablation, Prophet and Informer failure analysis, with Diebold-Mariano significance testing.
BanglaPhish-2026: A synthetic, privacy-safe Bangla phishing and scam detection benchmark dataset. 6,000 samples, 30 domains, CC BY-NC 4.0.
To associate your repository with the benchmark-dataset topic, visit your repo's landing page and select "manage topics."