Tag
Explore by tags
A vision-language-action foundation model and reference stack for generalized humanoid and cross-embodiment robot manipulation. Provides pretrained checkpoints, demo datasets, and tooling for fine-tuning, evaluation, and deployment (ONNX/TensorRT); released as Early Access.
Benchmark for evaluating OCR systems that convert PDFs and scans into Markdown and structured text: 1,403 PDFs and 7,010 unit tests covering text presence/absence, reading order, tables, and math formula accuracy. Diverse sources and ODC-BY-1.0 license for research use.
Real-time DETR detector on a DINOv2 backbone, covering detection, segmentation, and keypoints. Ships in six sizes (Nano to 2XL), beats YOLO on the COCO speed-accuracy curve, and transfers better to non-COCO real-world domains.
Lets LLM agents drive real Android and iOS devices from natural-language commands by turning each screen's accessibility tree into structured text the model reads directly, not just screenshots. LLM-agnostic; runs via CLI, Python, or Docker.
Clean-room, modular implementations of multi-object tracking algorithms — SORT, ByteTrack, OC-SORT, BoT-SORT, C-BIoU — behind one interface. Detector-agnostic: works with YOLO, DETR, or any bounding-box model via supervision.Detections.
Provides PyTorch code, pretrained checkpoints, and evaluation tooling for V-JEPA 2 — a Meta FAIR family of self-supervised video encoders and an action-conditioned world model. Includes training recipes, HuggingFace checkpoints, evaluation probes, and robot post‑training artifacts.
Real-time 3D Gaussian Splatting renderer for web apps using THREE.js. Integrates splat and mesh rendering with a Rust + Wasm component, supports major splat formats (.PLY, .SPZ, .SOG) and targets broad WebGL2 support for mobile-friendly dynamic scenes.
Physics-aware simulated sensor dataset for training and evaluating autonomous-vehicle perception and control models. Includes multimodal sensor streams with physical-scene annotations intended for tasks that require grounding in real-world dynamics.
Extends RAG beyond text: parses PDFs and Office files containing images, tables, equations, and charts, then queries them through one multimodal knowledge graph. Built on LightRAG, it replaces separate parsing and retrieval tools.
Provides a unified Python interface to collect data, train visual/dynamics world models, and evaluate them with model-predictive control across many standardized environments. Includes reference baselines, planning solvers, dataset converters, and LanceDB-backed formats for reproducible experiments. Best suited for researchers benchmarking world-model algorithms.
Detects, segments, and tracks every instance of an open-vocabulary concept in images and video from a text phrase or visual exemplar, not just one object per prompt. An 848M-param model reaching ~75-80% of human accuracy across 270K concepts.
A collection of ready-to-run Hugging Face Jobs OCR scripts that add a markdown column (or structured JSON) to image datasets, with model switching, layout detection, server-mode serving, and per-model options for table/form extraction.