AI Dataset2026
Provides paired images and English captions for vision–language research, curated by Stanford Vision Lab and hosted on Hugging Face; useful for training and evaluating multimodal models and reproducing related research.
AI Dataset2026
Provides 55 million scene-level video clips (each with captions, language labels, and timestamps) extracted from an 80M-video, 10-million-hour raw pool to support multimodal pre-training across video, audio, and frames. Access is gated for academic/non-commercial research.
AI Dataset2026
A small image-folder dataset for multimodal/vision model safety benchmarking, containing under 1,000 curated images with annotations to exercise safety-related model behaviours; licensed CC BY 4.0 and hosted on HuggingFace.
AI Dataset2026
Open egocentric multimodal dataset for embodied AI and robot learning captured on commodity iPhone Pro: ~200 hours and ~10M RGB frames with LiDAR depth, ARKit 6‑DoF poses, IMU, two‑hand MANO mocap, room meshes, and hierarchical action captions.
AI Dataset2026
Labeled Vietnamese handwritten line images paired with text transcriptions for training and evaluating OCR/text-recognition models. Stored in Parquet (optimized) with a dataset size in the 10K–100K sample range, suitable for model training and benchmarking.
AI Dataset2026
Multimodal STEM problem set for verifiable, answer-supervised training and RL: contains single-image, multi-panel, and multi-image PhD-level questions across physics, math, chemistry and biology. Each example has a deterministic ground-truth answer, enabling reward modeling and automated evaluation.
AI Dataset2026
Provides the full caption corpus used to train and ablate the i1 text-to-image model: 12 curated subsets with multiple caption variants (long/short, VLM-generated, rendered text) to enable reproducible training and captioning experiments.
AI Dataset2026
Transfers pretrained latent diffusion priors into pixel space to train pixel-space diffusion models using only synthetic images from LDMs. Trains shallow pixel layers while freezing most LDM internals, reducing data and compute needs and enabling native 4K generation without a VAE.
AI Model2026
Research-focused text-to-image foundation model that prioritizes training efficiency: a 3.8B-parameter architecture trained on an 800M image-text corpus with mixed-resolution learning, FLUX.2 VAE, RL tuning, and a distilled 4-step Lens-Turbo for fast high-resolution generation.
AI Model2026
Delivers image and video generation, editing, and understanding inside a single 3B-parameter multimodal model trained from scratch with a multi-task recipe. Notable for strong unified benchmarks at 3B scale; inference requires large GPU memory (≈40GB+ VRAM).
AI Model2026
A 4-step distilled variant of Microsoft's Lens foundational text-to-image model for fast, high-resolution image synthesis. Optimized for mixed-resolution inference up to 1440×1440, GPT-OSS text features and FLUX.2 latents, intended for low-latency prototyping and research under an MIT license.
AI Dataset2026
Collection of 1,000 AI-generated dreamcore aesthetic images (2K JPEGs, numbered 001–1000) intended for creative prototyping and visual research. Images were produced with GPT Image 2 and released under an MIT license.