Reading notes and an experiment sketch for Grounded Language. The repository emphasizes what still needs to be tested instead of manufacturing scores or release claims. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as RefCOCO, Flickr30k, and Visual Genome - reproducibility checks, failure modes, and open questions - topic-relevant references Start with review.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs. The note is…
Independent publisher
Anna Szymanski
annaszymanski
Learning ML every day. Love open source and cool models.
Models in Library1
Datasets in Library1
Models on Hugging Face3
Followers—
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: cc-by-4.0, mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Datasets
Preparation notes and schema examples for Document OCR tasks using Multimodal3 data. Full source material is intentionally not bundled, so provenance and licensing remain explicit. - dataset.py — loading, cleaning, and split preparation code. - datasetinfos.json — schema and split metadata. - metadatasample.jsonl — small, human-readable records for checking the schema. - README.md — data card and usage notes. Before using the prepared data, verify source licenses, duplicates across splits, missing values, label balance, and modality-specific corruption. Record the source version and every filtering rule so a later run can reproduce the same rows. The repository is suitable for testing the…