AI Model2026
Parses digital and camera-captured documents into structured outputs (text, layout, tables, formulas, figures) using a lightweight (~1.2B) open-source vision-language model. Uses geometry-aware modeling, multi-node consensus pseudo-labeling, and content-structure decoupling to handle warped, photographed, and digital pages.
AI Dataset2026
Provides 115,293 illustrated page images and a 975,345-row manifest sampled from scanned Encyclopaedia Britannica volumes (1768–1929), with per-page classifier probabilities for illustration — ready for image-classification, OCR-aware vision research, and illustration mining.
Compresses conversational histories and long documents into short sequences of continuous soft memory tokens that a frozen decoder can read directly without text reconstruction. Uses a small reader-matched writer that trains only a tiny adapter, achieving 4–16× compression and much faster write/read latencies.
An all-in-one multilingual scene text recognition approach that pairs a shared visual encoder with a script-aware Mixture-of-Experts (ScriptMoE) decoder to route each image to top-2 script experts. Introduces TextMuSS-10M, a synthetic dataset covering 10 scripts and 229 languages, and reports state-of-the-art accuracy and large end-to-end OCR F1 gains while remaining parameter-efficient.
AI Model2026
Scans long documents rendered as compressed page-images, locates relevant pages, and selectively expands only those pages to full text for question answering; built on Qwen3.5-9B, supports 5x/10x/15x compression and is released under Apple’s research-only model license.
AI Dataset2026
A multimodal supervised fine‑tuning corpus for training MLLMs: 44.3M samples (100.3M QA pairs) over 19.7M image groups, annotated with short/long chain‑of‑thought and produced by rerunning the HoneyPipe curation pipeline with multi‑model rollouts and verifications.
AI Model2026
Parses documents and answers questions about their contents with a 0.8B-parameter model. It combines OCR, structured extraction, and visual question answering, including support for scanned, skewed, and photographed pages.
AI Dataset2026
Provides 98,877 historical newspaper page images (1700s–1940s) paired with ALTO OCR, per-word confidences and line/word bounding boxes in image pixels — ready for line-level OCR training, OCR quality estimation, re‑OCR comparisons and layout analysis. OCR is library-produced (silver); image resolutions and OCR quality vary.
Generates quantized point-and-box visual primitives for precise grounding across detection, referring, OCR, GUI and layout tasks; uses a shared coordinate vocabulary and staged pretraining to improve downstream robotic manipulation and autonomous driving when used as a visual backbone.
AI Dataset2026
Aggregated, screened corpus of 55,050 normalized Indian public-information text bodies and 65,209 source records for retrieval and question-answering. Exports include deduplicated CSV/Parquet with provenance, topic labels, extraction quality flags and a private SQLite backup.
AI Model2026
Turns PDFs and images into readable markdown, plain text, or JSON with per-line and per-block boxes and reading order. Uses ~18 MB ONNX models (1M-parameter recognizer) optimized for CPU throughput (up to 49 pages/s, ~230 ms median/page) and layout extraction; not ideal for complex tables, handwriting or degraded scans.
AI Dataset2026
Benchmark dataset for bilingual (Chinese/English) visual document image editing with 3,506 examples covering 1,578 text edits and 1,928 table edits. Each example pairs input and target images with editing instructions, region masks, and structured annotations for OCR-level evaluation.