AI Video Papers2026
Provides a diagnostic suite that audits video-understanding benchmarks to find samples solvable without visual or temporal input, filters those shortcuts, and produces a distilled video-native testbed that reveals major capability gaps in current Video-LLMs.
AI Dataset2026
Provides curated short video clips (49- and 81-frame) with layered ground truth—edit layers, alpha mattes, and composite targets—for training and evaluating content-preserving layered diffusion video editing. Contains background-replace and object-add edits; Apache-2.0 licensed.
AI Model2026
Multimodal image-text-to-text fork of Gemma 4 (31B) using a 'CRACK v2' abliteration — tuned for conversational vision inputs and thinking-mode support in JANG v2 safetensors format. Recommended to run in vMLX; published by dealignai.
AI Model2026
Generates persistent, explorable 3D worlds from a single image by synthesizing long-range, geometry-consistent video and reconstructing it into an explicit 3D Gaussian scene. Intended for internal research use under NVIDIA's research license.
AI Model2026
An open text-to-image generation model built on an 8B Diffusion Transformer that focuses on layout-sensitive, text-heavy, and instruction-following image synthesis. Notable for accurate text rendering, structured/compositional generation (posters, comics), and ability to run on consumer 24GB GPUs when paired with prompt enhancement.
AI Dataset2026
Provides 12.26M synthetically generated multilingual OCR samples (en/ja/ko/ru/zh) with word/line/paragraph bounding boxes and reading-order graphs, packaged as HDF5 shards for training detection, recognition, and layout models; licensed CC BY 4.0.
AI Dataset2026
Benchmarks document-parsing systems on real-world enterprise PDFs and images—evaluates tables, charts, content faithfulness, semantic formatting, and visual grounding with human-verified, rule-level tests. Ships with ~2,000 pages, ~169K test rules, and an open evaluation framework for end-to-end pipeline scoring.
AI Model2026
Generates and reconstructs navigable, editable 3D worlds from text, single images, multi-view photos, or video; outputs meshes and Gaussian Splatting assets and includes WorldMirror 2.0 for fast multi-view reconstruction. Suited for research and production pipelines that import assets into engines; requires substantial GPU resources.
AI Dataset2026
Curated 100K subset of geometrically diverse CAD construction sequences sampled from a 1M agentically synthesized corpus — each item includes executable CadQuery scripts, 8 rendered views, STL/STEP exports, and precomputed DINOv3 embeddings for retrieval and benchmarking.
AI Dataset2026
Provides a ~9.2M-instance Japanese multimodal post-training dataset for vision–language models, combining image–text pairs, PDF corpora and generated VQA to improve Japanese VLM performance; access is restricted by Japanese copyright (download via llm-jp GitLab).
AI Dataset2026
Large-scale in-the-wild robot manipulation dataset with ~76K teleoperated trajectories (~350 hours) that provides synchronized multi-view video, depth, camera calibration, robot state/action traces, and natural-language task instructions to train and evaluate manipulation policies and dynamics models. Collected across 564 scenes, 86 tasks, 52 buildings, on a uniform Franka Panda hardware stack and released in LeRobotDataset v3.0 format (≈707 GB, OpenMDW1.1).
AI Model2026
Delivers an ultra-efficient, edge-friendly multimodal image-and-video-to-text model optimized for on-device deployment. Uses mixed 4x/16x visual token compression, a low-FLOPs visual encoder, and multiple quantized variants for mobile and embedded inference.