AI Dataset2018
Alex Wang, Amanpreet Singh +4New York University, Paul G. Allen School of Computer Science & Engineering, University of Washington +1
A multi-task English NLU benchmark for evaluating models across nine tasks (acceptability, sentiment, paraphrase, similarity, and various NLI setups), with a diagnostic evaluation set and an online leaderboard to compare generalization and transfer learning.
AI Model2021
Learns a joint image–text embedding via contrastive pretraining to enable zero-shot image classification. Uses a ViT‑B/32 image encoder and transformer text encoder; intended primarily for research into robustness and generalization, not untested deployment.
AI Model2022
Pretrained uncased English BERT base model for masked language modeling and next-sentence prediction. ~110M parameters, pretrained on BookCorpus and English Wikipedia; commonly fine-tuned for classification, token labeling, and question answering.
AI Dataset2024
Provides a 1 trillion-token multimodal interleaved dataset (HTML subset updated as data_v1_1 with 742B HTML tokens) and 3.4B images drawn from HTML/PDF/ArXiv sources for multimodal pretraining; released under CC-BY-4.0 with safety and deduplication guidance.
AI Agent Papers2025
Tests research agents on 100 expert-written tasks across 22 fields. Separates report quality from citation reliability, using adaptive reference-based grading and checks that cited pages support individual claims.
AI Agent2025
Orchestrates code-running agents to hunt verifiable open problems: schedules runs, applies null tests and skeptic re-checks, and packages found objects with short checkers so anyone can reproduce or validate a claim.
AI Agent Papers2025
Trains long-horizon web researchers by combining agentic mid-training, synthetic trajectories, and reinforcement learning. A 30.5B-parameter model activates 3.3B parameters per token and learns to plan, search, and synthesize evidence.
AI Model2025
Performs open-vocabulary promptable segmentation and tracking on images and videos, returning instance masks and unique IDs from short noun-phrase or exemplar prompts. Trained on a 4M-concept, 52M-mask dataset; uses a presence head and a decoupled detector–tracker design, with near real-time inference for multi-object video.
AI Agent Papers2025
Trains an 8B model to search, synthesize evidence, and write cited research reports. Its reinforcement-learning rewards use evolving rubrics grounded in retrieved evidence and contrasting model responses.
AI Dataset2026
Provides a machine-readable collection of 5,426 open and historically significant mathematical problems with LaTeX statements, structured metadata and curated per-problem AI-assisted research notes. Includes difficulty labels, canonical problem sets (Millennium, Hilbert, Erdős) and files optimized for benchmarking math reasoning.
AI Dataset2026
Provides 10 million synchronized egocentric experience episodes with structured 3D/4D multimodal annotations — 2.88B RGB frames, 720M depth frames, 576M pose/mocap frames and ~1PB total. Designed for embodied AI, robotics, and multimodal pretraining; research-only, gated access.
AI Dataset2026
Provides a sanitized, labeled SOC capture and merged provenance graph for intrusion-detection research, including 2,011,674 live signals, 51,371 incident graphs, MITRE ATT&CK mappings, and deterministic attack reports.