PureDocBench shows document parsing is far from solved, with top models at ~74/100, small specialists competing with large VLMs, and ranking reversals under real degradation.
hub Canonical reference
Hunyuanocr technical report
Canonical reference. 80% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
years
2026 17representative citing papers
Introduces 2M synthetic WATER-S dataset and WATERec model achieving 90.40% accuracy on WordArt-Bench, outperforming prior STR methods and VLMs.
ChartArena unifies eight chart families across three real-world visual scenarios and two languages under a format-agnostic triple/graph evaluation protocol, revealing clear gaps among 26 MLLMs.
Chronicles-OCR is the first benchmark with 2,800 images across the complete evolutionary trajectory of Chinese characters, defining four tasks to evaluate VLLMs' cross-temporal visual perception.
GlotOCR Bench shows that OCR models perform well on fewer than 10 scripts and fail to generalize beyond about 30, with results tracking pretraining coverage and models hallucinating from known scripts on unfamiliar ones.
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.
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
An end-to-end document parser trained on 5M synthetic and mined pages with multi-task RL reaches 87.6% on olmOCR-Bench and 74.3% on ParseBench.
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.
CC-OCR V2 reveals that state-of-the-art large multimodal models substantially underperform on challenging real-world document processing tasks.
A parser-oriented refinement stage performs set-level reasoning on detector hypotheses to jointly decide instance retention, refine boxes, and set parser input order, cutting reading order errors to 0.024 on OmniDocBench.
A realistic scene synthesis strategy and document-aware training recipe enable a 1B-parameter MLLM to achieve superior accuracy and robustness in end-to-end parsing of real-world captured documents.
Omni Parsing framework converts complex multimodal signals into locatable, enumerable, and traceable structured knowledge via hierarchical detection, recognition, and interpreting with strict evidence alignment.
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.
ABot-OCR is a new end-to-end VLM for direct image-to-Markdown transcription using a custom data engine and structure-constrained RL optimization, reporting SOTA scores of 92.81/93.30 on OmniDocBench v1.5/v1.6.
PaddleOCR-VL-1.5 is a 0.9B VLM achieving 94.5% SOTA accuracy on OmniDocBench v1.5, with added robustness to physical distortions and support for seal recognition plus text spotting.
PaddleOCR-VL-1.6 improves on PaddleOCR-VL-1.5 via region-aware data optimization and progressive post-training to reach 96.33% on OmniDocBench v1.6.
citing papers explorer
-
How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings
PureDocBench shows document parsing is far from solved, with top models at ~74/100, small specialists competing with large VLMs, and ranking reversals under real degradation.
-
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
Introduces 2M synthetic WATER-S dataset and WATERec model achieving 90.40% accuracy on WordArt-Bench, outperforming prior STR methods and VLMs.
-
ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats
ChartArena unifies eight chart families across three real-world visual scenarios and two languages under a format-agnostic triple/graph evaluation protocol, revealing clear gaps among 26 MLLMs.
-
Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters
Chronicles-OCR is the first benchmark with 2,800 images across the complete evolutionary trajectory of Chinese characters, defining four tasks to evaluate VLLMs' cross-temporal visual perception.
-
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
GlotOCR Bench shows that OCR models perform well on fewer than 10 scripts and fail to generalize beyond about 30, with results tracking pretraining coverage and models hallucinating from known scripts on unfamiliar ones.
-
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.
-
Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
-
Infinity-Parser2 Technical Report
An end-to-end document parser trained on 5M synthetic and mined pages with multi-task RL reaches 87.6% on olmOCR-Bench and 74.3% on ParseBench.
-
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.
-
CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing
CC-OCR V2 reveals that state-of-the-art large multimodal models substantially underperform on challenging real-world document processing tasks.
-
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
A parser-oriented refinement stage performs set-level reasoning on detector hypotheses to jointly decide instance retention, refine boxes, and set parser input order, cutting reading order errors to 0.024 on OmniDocBench.
-
Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
A realistic scene synthesis strategy and document-aware training recipe enable a 1B-parameter MLLM to achieve superior accuracy and robustness in end-to-end parsing of real-world captured documents.
-
Logics-Parsing-Omni Technical Report
Omni Parsing framework converts complex multimodal signals into locatable, enumerable, and traceable structured knowledge via hierarchical detection, recognition, and interpreting with strict evidence alignment.
-
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.
-
ABot-OCR Technical Report
ABot-OCR is a new end-to-end VLM for direct image-to-Markdown transcription using a custom data engine and structure-constrained RL optimization, reporting SOTA scores of 92.81/93.30 on OmniDocBench v1.5/v1.6.
-
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
PaddleOCR-VL-1.5 is a 0.9B VLM achieving 94.5% SOTA accuracy on OmniDocBench v1.5, with added robustness to physical distortions and support for seal recognition plus text spotting.
-
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
PaddleOCR-VL-1.6 improves on PaddleOCR-VL-1.5 via region-aware data optimization and progressive post-training to reach 96.33% on OmniDocBench v1.6.