FollowTable is the first large-scale benchmark for instruction-following table retrieval, paired with an Instruction Responsiveness Score, showing that existing models fail to adapt to fine-grained constraints beyond topical similarity.
hub Mixed citations
MinerU: An Open-Source Solution for Precise Document Content Extraction
Mixed citation behavior. Most common role is background (55%).
46
Pith papers citing it
14
external citations · Pith
Background
55% of classified citations
abstract
Document content analysis has been a crucial research area in computer vision. Despite significant advancements in methods such as OCR, layout detection, and formula recognition, existing open-source solutions struggle to consistently deliver high-quality content extraction due to the diversity in document types and content. To address these challenges, we present MinerU, an open-source solution for high-precision document content extraction. MinerU leverages the sophisticated PDF-Extract-Kit models to extract content from diverse documents effectively and employs finely-tuned preprocessing and postprocessing rules to ensure the accuracy of the final results. Experimental results demonstrate that MinerU consistently achieves high performance across various document types, significantly enhancing the quality and consistency of content extraction. The MinerU open-source project is available at https://github.com/opendatalab/MinerU.
hub tools
citation-role summary
background 7
method 3
baseline 1
citation-polarity summary
representative citing papers
LiveK12Bench is a growing multi-disciplinary benchmark showing LMMs like GPT-5 drop from 79 to 53 under realistic exam constraints including process rigor and efficiency.
JMed48k is a new benchmark of Japanese healthcare licensing exams used to evaluate 21 VLMs, with a paired image-removal audit revealing large differences in how models and professions benefit from visual content.
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.
HUGO-CS is a 4,383-experiment cold-spray dataset extracted from literature via a new hybrid LLM-manual framework that is 30 times larger than prior collections and released with code.
RegReAct deploys self-correcting multi-agent pipelines across seven stages to extract hierarchical compliance criteria from regulatory texts, outperforming single-pass GPT-4o on EU Taxonomy documents.
ParseBench is a new benchmark for document parsing in AI agents that reveals fragmented performance across five semantic dimensions with LlamaParse Agentic scoring highest at 84.9%.
EpiBench is a new episodic multi-turn multimodal benchmark where even leading AI agents score only 29.23% on hard tasks requiring cross-paper evidence integration from figures and tables.
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.
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
StrucTab achieves SOTA table parsing performance by unifying structural subtasks through sequential reasoning and using decomposed RL rewards in Uni-TabRL, plus a new TableVerse-5K benchmark.
P-MTP uses progressive curriculum loss and confidence-gated dynamic drafting to scale look-ahead depth in multi-token prediction, claiming up to 5x speedup with negligible accuracy loss in document parsing.
A new multi-domain benchmark shows scientifically fine-tuned LLMs have degraded factual reliability and are less confident yet more assertive than their base models.
Xcientist is a research harness that externalizes an AI scientist's literature grounding, idea evolution, experiments, and repairs into auditable artifacts, demonstrated on memory, traffic forecasting, and PDE-solving tasks.
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
PathPocket constructs a 4.55M-entity pathology hypergraph from 110k graded documents and deploys a multi-agent framework that outperforms prior systems on 200k cases while raising pathologist accuracy in user studies.
Constrained Dominant Sets on query-augmented graphs select complementary evidence for long multimodal document QA, claiming new SOTA of 66.99 on VisDoMBench and gains of 37.1 and 4.8 points over baselines.
FLOWREADER reframes multimodal long-document evidence assembly as min-cost flow optimization and reports competitive results on VisDoMBench subsets with fragmented evidence.
STR rewrites table cells as <item path, feature path, value> triplets and uses TripletQL to match or exceed HTML baselines on four benchmarks while cutting tokens.
DeepSurvey introduces an agentic system for automated survey generation that improves depth through full-text keynotes, cross-paper clustering, and code analysis, while boosting citation reliability via graph expansion, hybrid filtering, and evidence-constrained assignment, with reported gains over
MPDocBench-Parse provides 433 annotated multi-page documents and an evaluation protocol covering text/table/formula extraction, merging, figure extraction, reading order, and heading hierarchy for realistic document parsing.
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.
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
FT-RAG introduces a fine-grained graph-based retrieval framework for tables plus a new 9870-pair benchmark, reporting 23.5% and 59.2% gains in table- and cell-level hit rates and 62.2% higher exact-value recall over baselines.
citing papers explorer
-
FollowTable: A Benchmark for Instruction-Following Table Retrieval
FollowTable is the first large-scale benchmark for instruction-following table retrieval, paired with an Instruction Responsiveness Score, showing that existing models fail to adapt to fine-grained constraints beyond topical similarity.
-
LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?
LiveK12Bench is a growing multi-disciplinary benchmark showing LMMs like GPT-5 drop from 79 to 53 under realistic exam constraints including process rigor and efficiency.
-
JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
JMed48k is a new benchmark of Japanese healthcare licensing exams used to evaluate 21 VLMs, with a paired image-removal audit revealing large differences in how models and professions benefit from visual content.
-
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.
-
HUGO-CS: A Hybrid-Labeled, Uncertainty-Aware, General-Purpose, Observational Dataset for Cold Spray
HUGO-CS is a 4,383-experiment cold-spray dataset extracted from literature via a new hybrid LLM-manual framework that is 30 times larger than prior collections and released with code.
-
REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction
RegReAct deploys self-correcting multi-agent pipelines across seven stages to extract hierarchical compliance criteria from regulatory texts, outperforming single-pass GPT-4o on EU Taxonomy documents.
-
ParseBench: A Document Parsing Benchmark for AI Agents
ParseBench is a new benchmark for document parsing in AI agents that reveals fragmented performance across five semantic dimensions with LlamaParse Agentic scoring highest at 84.9%.
-
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
EpiBench is a new episodic multi-turn multimodal benchmark where even leading AI agents score only 29.23% on hard tasks requiring cross-paper evidence integration from figures and tables.
-
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.
-
El Agente Quntur: A research collaborator agent for quantum chemistry
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
-
StrucTab: A Structured Optimization Framework for Table Parsing
StrucTab achieves SOTA table parsing performance by unifying structural subtasks through sequential reasoning and using decomposed RL rewards in Uni-TabRL, plus a new TableVerse-5K benchmark.
-
P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling
P-MTP uses progressive curriculum loss and confidence-gated dynamic drafting to scale look-ahead depth in multi-token prediction, claiming up to 5x speedup with negligible accuracy loss in document parsing.
-
Finetuning with Scientific Data Increases Hallucinations: A Multi-domain Factuality Evaluation of LLMs
A new multi-domain benchmark shows scientifically fine-tuned LLMs have degraded factual reliability and are less confident yet more assertive than their base models.
-
Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness
Xcientist is a research harness that externalizes an AI scientist's literature grounding, idea evolution, experiments, and repairs into auditable artifacts, demonstrated on memory, traffic forecasting, and PDE-solving tasks.
-
EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
-
A Multi-modal Agentic Co-pilot for Evidence Grounded Computational Pathology
PathPocket constructs a 4.55M-entity pathology hypergraph from 110k graded documents and deploys a multi-agent framework that outperforms prior systems on 200k cases while raising pathologist accuracy in user studies.
-
Constrained Dominant Sets for Multimodal Document Question Answering
Constrained Dominant Sets on query-augmented graphs select complementary evidence for long multimodal document QA, claiming new SOTA of 66.99 on VisDoMBench and gains of 37.1 and 4.8 points over baselines.
-
FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A
FLOWREADER reframes multimodal long-document evidence assembly as min-cost flow optimization and reports competitive results on VisDoMBench subsets with fragmented evidence.
-
Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models
STR rewrites table cells as <item path, feature path, value> triplets and uses TripletQL to match or exceed HTML baselines on four benchmarks while cutting tokens.
-
DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation
DeepSurvey introduces an agentic system for automated survey generation that improves depth through full-text keynotes, cross-paper clustering, and code analysis, while boosting citation reliability via graph expansion, hybrid filtering, and evidence-constrained assignment, with reported gains over
-
MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
MPDocBench-Parse provides 433 annotated multi-page documents and an evaluation protocol covering text/table/formula extraction, merging, figure extraction, reading order, and heading hierarchy for realistic document parsing.
-
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.
-
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
-
FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning
FT-RAG introduces a fine-grained graph-based retrieval framework for tables plus a new 9870-pair benchmark, reporting 23.5% and 59.2% gains in table- and cell-level hit rates and 62.2% higher exact-value recall over baselines.
-
BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature
BioMiner introduces a multi-modal extraction system and BioVista benchmark that achieves F1 0.32 on bioactivity triplets and demonstrates utility in scaling datasets and improving QSAR models.
-
QoS-QoE Translation with Large Language Model
A new QoS-QoE Translation dataset is constructed from multimedia literature and fine-tuned LLMs demonstrate strong performance on bidirectional continuous and discrete QoS-QoE predictions.
-
Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing
PaddleOCR-VL uses a Valid Region Focus Module to select key visual tokens and a 0.9B model for guided recognition, delivering SOTA document parsing with far fewer tokens and parameters.
-
Thinking with Drafting: Optical Decompression via Logical Reconstruction
Thinking with Drafting reconceptualizes visual reasoning as optical decompression by forcing models to draft mental models into executable DSL code for deterministic self-verification on the VisAlg benchmark.
-
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.
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
A 40-task, 10-domain benchmark finds current auto-research agents and LLMs score only ~20–26 on re-discovering real published scientific artifacts.
-
An LMM for Precisely Grounding Elements in Documents
PreciseDoc is an LMM that uses synthetic document data pipelines and RL-based joint grounding-reasoning training to achieve higher precision in locating elements within text-rich document images than prior approaches.
-
Unlimited OCR Works
The paper proposes Unlimited OCR using Reference Sliding Window Attention (R-SWA) to achieve constant KV cache for efficient transcription of long multi-page documents.
-
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
SingGuard introduces a policy-adaptive multimodal LLM guardrail with dynamic reasoning regimes and SingGuard-Bench, reporting SOTA F1 scores across 35 datasets and improved policy-following accuracy under runtime shifts.
-
CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science
CMIP-Forge presents a retrieval-augmented agentic system with automated guardrails and adversarial self-review for autonomous execution of climate research tasks on CMIP6 literature and ESGF data.
-
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
Compass is an expert-guided LLM agent framework that extracts 3,751 marine Pb records from 230k papers to build the largest integrated database, achieving 92% accuracy via multi-layered validation.
-
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
FastOCR dynamically selects a small subset of visual tokens per decoding step using focal-guided pruning and cross-step reuse, retaining 98% accuracy on Qwen2.5-VL while attending to only 5% of tokens and cutting attention latency by 3x.
-
DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
DocSeeker improves long-document understanding in MLLMs via a two-stage training process that combines supervised fine-tuning from distilled data with evidence-aware group relative policy optimization and memory-efficient resolution allocation.
-
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
Docling with hierarchical splitting and image descriptions reaches 94.1% RAG QA accuracy on Portuguese admin PDFs, beating manual Markdown and other open-source converters.
-
MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
MegaRAG introduces a multimodal knowledge graph-based RAG system that incorporates visual cues into graph construction, retrieval, and generation to improve question answering on complex textual and multimodal corpora.
-
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
DocMaster builds hierarchical document trees and multi-view semantic indices (PC-KMeans clusters plus hyper-edges) for structure-aware filtering and RAG over complex document collections.
-
DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows
DeepTrans Studio is a demo system that intercepts agentic translation workflows to let experts review, revise, and store decisions in shared team memory for propagation across segments and members.
-
Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval
Large-scale profiling of recent AI literature shows growth in safety, multimodal reasoning, and agent studies alongside stabilization in neural machine translation and graph methods.
-
PaddleOCR 3.0 Technical Report
PaddleOCR 3.0 releases compact open-source models for OCR, document structure parsing, and information extraction that rival billion-parameter VLMs.
-
Multi-Modal LLM based Image Captioning in ICT: Bridging the Gap Between General and Industry Domain
A 7B-parameter domain-specific image captioning model for ICT, trained in three stages on synthesized and annotated data, outperforms 32B-parameter general models on BLEU and expert accuracy metrics.
- Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA