MathNet delivers the largest multilingual Olympiad math dataset and benchmarks where models like Gemini-3.1-Pro reach 78% on solving but embedding models struggle on equivalent problem retrieval, with retrieval augmentation yielding up to 12% gains.
hub Mixed citations
Nougat: Neural Optical Understanding for Academic Documents
Mixed citation behavior. Most common role is background (56%).
31
Pith papers citing it
Background
56% of classified citations
abstract
Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural Optical Understanding for Academic Documents), a Visual Transformer model that performs an Optical Character Recognition (OCR) task for processing scientific documents into a markup language, and demonstrate the effectiveness of our model on a new dataset of scientific documents. The proposed approach offers a promising solution to enhance the accessibility of scientific knowledge in the digital age, by bridging the gap between human-readable documents and machine-readable text. We release the models and code to accelerate future work on scientific text recognition.
hub tools
citation-role summary
background 6
method 2
baseline 1
citation-polarity summary
representative citing papers
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
Injecting pre-computed layout priors from RT-DETR into VLM prompts raises markdown F1 from 0.37 to 0.92 on a 10k-page OOD benchmark and cuts infinite-loop failures across domains.
PaperFit uses rendered page images in a closed loop to diagnose and repair typesetting defects in LaTeX documents, outperforming baselines on a new benchmark of 200 papers.
ShredBench shows state-of-the-art MLLMs perform well on intact documents but suffer sharp drops in restoration accuracy as fragmentation increases to 8-16 pieces, indicating insufficient cross-modal semantic reasoning for VRDU.
MasterSet is a new large-scale benchmark for must-cite citation recommendation in AI/ML, using LLM-annotated tiers on 150k papers and Recall@K evaluation.
LLM adoption in science follows a compressing inverted-U trajectory where release year predicts time-to-peak and lifespan better than model attributes.
A fixed 1.2B model trained via diversity-aware sampling, cross-model verification, annotation refinement, and progressive stages achieves new state-of-the-art document parsing accuracy of 95.69 on OmniDocBench v1.6.
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
Consensus Entropy measures inter-VLM output agreement to verify OCR reliability and enable self-improving ensembles, yielding 42.1% F1 gains over single-model judging.
Ryze automates evidence-enriched QA synthesis from biomedical papers to produce BioVLM-8B, which reaches 48.0% weighted accuracy on LAB-Bench (+12.6pp over base, +3.8pp over GPT-5.2) at under $200 cost.
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
DocAtlas introduces model-free rendering pipelines to create DocTag-annotated datasets across 82 languages and shows DPO adaptation improves multilingual performance without base-language degradation.
SciTikZer-8B uses a new dataset, benchmark, and dual self-consistency RL to generate TikZ code for scientific graphics, outperforming much larger models like Gemini-2.5-Pro.
AdaQE-CG uses context-aware adaptive query expansion and inter-card knowledge transfer from a MetaGAI Pool to generate higher-quality model and data cards than prior methods, validated on the new expert-annotated MetaGAI-Bench.
SciPostGen supplies a paired dataset linking paper structure to poster layouts and shows that retrieval of matching layouts improves generation while respecting user constraints.
DeepSeek-OCR compresses text contexts up to 20x via 2D optical mapping while achieving 97% OCR accuracy below 10x and 60% at 20x, outperforming prior OCR tools with fewer vision tokens.
MinerU2.5 uses a two-stage decoupled vision-language architecture to achieve state-of-the-art document parsing accuracy with lower computational overhead than existing general and domain-specific models.
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
Release of an AI-ready dataset containing approximately 660,000 reconstructed polarized e+e- collision events at 91.2 GeV from the SLD experiment, translated from legacy formats with accompanying digitized documentation.
RESCORE recovers task-coherent simulations from 40.7% of 500 CDC papers via a three-component LLM agent pipeline and claims a 10X speedup over manual human replication.
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
CogVLM2 family achieves state-of-the-art results on image and video understanding benchmarks through improved visual expert architecture, higher resolution inputs, and automated temporal grounding for videos.
citing papers explorer
-
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
MathNet delivers the largest multilingual Olympiad math dataset and benchmarks where models like Gemini-3.1-Pro reach 78% on solving but embedding models struggle on equivalent problem retrieval, with retrieval augmentation yielding up to 12% gains.
-
A document is worth a structured record: Principled inductive bias design for document recognition
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
-
Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding
Injecting pre-computed layout priors from RT-DETR into VLM prompts raises markdown F1 from 0.37 to 0.92 on a 10k-page OOD benchmark and cuts infinite-loop failures across domains.
-
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
PaperFit uses rendered page images in a closed loop to diagnose and repair typesetting defects in LaTeX documents, outperforming baselines on a new benchmark of 200 papers.
-
ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
ShredBench shows state-of-the-art MLLMs perform well on intact documents but suffer sharp drops in restoration accuracy as fragmentation increases to 8-16 pieces, indicating insufficient cross-modal semantic reasoning for VRDU.
-
MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature
MasterSet is a new large-scale benchmark for must-cite citation recommendation in AI/ML, using LLM-annotated tiers on 150k papers and Recall@K evaluation.
-
The Shrinking Lifespan of LLMs in Science
LLM adoption in science follows a compressing inverted-U trajectory where release year predicts time-to-peak and lifespan better than model attributes.
-
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
A fixed 1.2B model trained via diversity-aware sampling, cross-model verification, annotation refinement, and progressive stages achieves new state-of-the-art document parsing accuracy of 95.69 on OmniDocBench v1.6.
-
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
-
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
Consensus Entropy measures inter-VLM output agreement to verify OCR reliability and enable self-improving ensembles, yielding 42.1% F1 gains over single-model judging.
-
Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers
Ryze automates evidence-enriched QA synthesis from biomedical papers to produce BioVLM-8B, which reaches 48.0% weighted accuracy on LAB-Bench (+12.6pp over base, +3.8pp over GPT-5.2) at under $200 cost.
-
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
-
DocAtlas: Multilingual Document Understanding Across 80+ Languages
DocAtlas introduces model-free rendering pipelines to create DocTag-annotated datasets across 82 languages and shows DPO adaptation improves multilingual performance without base-language degradation.
-
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
SciTikZer-8B uses a new dataset, benchmark, and dual self-consistency RL to generate TikZ code for scientific graphics, outperforming much larger models like Gemini-2.5-Pro.
-
AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation
AdaQE-CG uses context-aware adaptive query expansion and inter-card knowledge transfer from a MetaGAI Pool to generate higher-quality model and data cards than prior methods, validated on the new expert-annotated MetaGAI-Bench.
-
SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts
SciPostGen supplies a paired dataset linking paper structure to poster layouts and shows that retrieval of matching layouts improves generation while respecting user constraints.
-
DeepSeek-OCR: Contexts Optical Compression
DeepSeek-OCR compresses text contexts up to 20x via 2D optical mapping while achieving 97% OCR accuracy below 10x and 60% at 20x, outperforming prior OCR tools with fewer vision tokens.
-
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
MinerU2.5 uses a two-stage decoupled vision-language architecture to achieve state-of-the-art document parsing accuracy with lower computational overhead than existing general and domain-specific models.
-
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
-
An AI-ready, Polarized Electron-Positron Collision Dataset
Release of an AI-ready dataset containing approximately 660,000 reconstructed polarized e+e- collision events at 91.2 GeV from the SLD experiment, translated from legacy formats with accompanying digitized documentation.
-
RESCORE: LLM-Driven Simulation Recovery in Control Systems Research Papers
RESCORE recovers task-coherent simulations from 40.7% of 500 CDC papers via a three-component LLM agent pipeline and claims a 10X speedup over manual human replication.
-
ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
-
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
-
CogVLM2: Visual Language Models for Image and Video Understanding
CogVLM2 family achieves state-of-the-art results on image and video understanding benchmarks through improved visual expert architecture, higher resolution inputs, and automated temporal grounding for videos.
-
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
RADIANT-LLM is a local-first multi-modal RAG system with provenance tracking that delivers lower hallucination rates than general LLMs on nuclear engineering benchmarks.
-
MinerU: An Open-Source Solution for Precise Document Content Extraction
MinerU delivers an open-source pipeline for high-precision document content extraction by integrating specialized models with tuned preprocessing and postprocessing rules.
-
DeepSeek-VL: Towards Real-World Vision-Language Understanding
DeepSeek-VL develops open-source 1.3B and 7B vision-language models that achieve competitive or state-of-the-art results on real-world visual-language benchmarks through diverse data curation, a hybrid vision encoder, and pretraining that preserves language capabilities.
-
Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production
Describes a microservice architecture for production document AI pipelines with OCR and LLMs, reporting that OCR dominates latency and GPU inference capacity limits concurrency.
-
Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition
MolSeek-OCR reaches exact SMILES matching accuracy comparable to leading image-to-sequence OCSR models after two-stage fine-tuning on PubChem renderings and USPTO-MOL patent images, but remains below image-to-graph state-of-the-art.
-
Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
Survey proposing a taxonomy for document parsing into pipeline-based systems and VLM-driven unified models, reviewing components, metrics, benchmarks, and challenges.
- MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing