Search Results for "table"

uCO3D is a large-scale 3D vision dataset and toolkit centered on turn-table videos of everyday objects drawn from the LVIS taxonomy. It provides about 170,000 full videos per object instance rather than still frames, along with per-video annotations including object masks, calibrated camera poses, and multiple flavors of point clouds. Each sequence also ships with a precomputed 3D Gaussian Splat reconstruction, enabling fast, differentiable rendering workflows and modern implicit/point-based modeling experiments. ...

TabFM is a tabular foundation model from Google Research for zero-shot classification and regression on structured datasets. It is designed to work with mixed numerical and categorical columns without requiring a custom training run for every new table. Instead of fitting model weights to the user’s dataset, TabFM uses in-context learning by reading training examples and test rows together at inference time. The library provides scikit-learn-compatible classifier and regressor interfaces, which makes it familiar for data scientists already using Python ML workflows. It supports both JAX and PyTorch backends and can automatically download pretrained TabFM v1.0.0 weights. ...

GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B), enabling deployment in high-concurrency services and edge environments. The model’s multimodal capabilities allow it to reason across image and text content holistically, capturing structured and unstructured information from pages that include dense tables, seals, code snippets, and varied document graphics. ...

DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body...

...Instead of conditioning on free-form text alone, it leverages graph structure to control layout and interactions, generating scenes that respect constraints like “person left of dog” or “cup on table.” The pipeline typically predicts object layouts (bounding boxes and masks) from the graph, then renders a realistic image conditioned on those layouts. This separation lets the model reason about geometry and composition before committing to texture and color, improving spatial fidelity. The repository includes training code, datasets, and evaluation scripts so researchers can reproduce baselines and extend components such as the graph encoder or image generator. ...

...It uses a two-phase training process: supervised fine-tuning (SFT) followed by reinforcement learning (GRPO) with a layout-centric reward for accuracy on challenging documents. The model excels at non-standard layouts and complex table structures, outperforming non-reasoning OCR systems like GPT-4o and OCRFlux, and competing with large closed-source reasoning models like Gemini 2.5. Thinking token usage can range from 20% to 500% of the final answer, depending on task difficulty. NuMarkdown-8B-Thinking is released under the MIT license and supports vLLM and Transformers for deployment.