Explores unsupervised visual pretraining on visually rich documents to improve language-model intelligence; shows visual-pretrained models outperform text-only counterparts on the same corpora. Key aspects: direct use of images/layouts (no OCR-only pipeline), scalable across backbones and benchmarks.
AI Model2026
End-to-end 0.8B multimodal OCR and page-level document parser that converts page images into structured Markdown (text, LaTeX formulas, HTML tables, and image crops). Post-trained from Qwen3.5-0.8B using mixed real/synthetic data and SFT+RL+OPD; achieves 96.58 on OmniDocBench v1.6.
AI Video Papers2026
Personalizes subject-driven videos to preserve human identity and accurate human–object interactions by integrating multimodal references and MLLM-derived semantics. Introduces global multimodal guidance in self-attention and modality-reference embeddings to align MLLM features with VAE tokens, supporting both inter- and intra-subject inputs (e.g., OCR, multi-view).
AI Dataset2026
Evaluates atomic visual perception of multimodal LLMs using 3,000 short visual questions that isolate ten perceptual skills. Built from an error taxonomy across 42 benchmarks, capability-balanced and accompanied by a model leaderboard.
AI Model2026
Delivers image and video understanding plus a built-in event‑gated streaming gate — a unified 4B multimodal foundation model that uses codec-aligned tokenization to cut visual tokens by >75% and yield up to 3.5× wall‑clock inference speedup for streaming and long‑horizon video tasks.
AI Dataset2026
Consolidated dataset of detection, visual grounding and pointing annotations with indexed WebDataset image shards and Megatron‑Energon training metadata. Covers diverse visual domains (COCO, RefCOCO, driving, GUI, documents) and uses a normalized spatial grid for cross‑domain vision–language grounding training.
AI Dataset2026
Provides 1,080,814 images extracted from ~65,000 digitised British Library book volumes (c.1510–c.1900), split into four algorithmic image-type configs and packaged as parquet for image–text multimodal research and retrieval.
AI Dataset2026
Evaluates schema-guided structured extraction from documents: given a document and a JSON schema, systems must return a schema-valid JSON with page-and-box grounding. Covers 370 documents (4,869 pages) across 8 business domains and 67 document types; scores value accuracy, word/page grounding, and long-list completeness.
AI Agent2026
Lets an AI agent control a real or cloud phone by tapping, typing, scrolling and reading the screen. Works with iPhone via macOS iPhone Mirroring, Android over adb, or rented cloud phones; host-side OCR, accessibility trees and CLI helpers provide verifiable UI actions without jailbreaking. Some manual phone pairing/setup is required.
AI Dataset2026
Provides OCR full text for 11.55M public-domain German newspaper pages (1638–1964) with per-page IIIF scans and ALTO XML coordinates; suited for historical NLP, language-model training, and OCR research. Pages carry explicit per-page public-domain licenses.
AI Model2026
Multimodal vision-language model optimized for on-device image+text tasks: image captioning, full-page OCR with layout annotation, grounding/bounding-box prediction, and function calling. Built on the LFM2.5-2.6B backbone with a SigLIP2 NaFlex 400M vision encoder and tuned for low-latency, low-memory edge inference.
AI Model2026
Performs unified parsing of digital and camera-captured documents (layout, text, tables, formulas) using a ~1.2B-parameter vision–language model. Key differences: geometry-aware modeling, curvature-guided sampling, and content-structure decoupled training to handle real-world deformations without separate dewarping.