LOCUS is a released corpus of nearly all US municipal and county ordinance codes, processed via OCR and paired with ModernBERT classifiers for dimensions such as opacity and paternalism.
olmOCR 2: Unit test rewards for document OCR
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
years
2026 9representative citing papers
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.
RealDocBench supplies 1,356 field-level QA questions over 581 real documents and 1,500 annotated pages, evaluating 18 systems on per-field accuracy, cost, and latency.
METATR is a new benchmark dataset and evaluation framework for ATR covering 29 languages, multiple scripts and layouts, with standardized prompting and a dynamic extensible protocol.
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.
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.
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.
EKSFT masks high-entropy or high-KL tokens in low-data SFT to preserve pre-trained distribution and improve downstream RL performance on math reasoning tasks.
citing papers explorer
-
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
LOCUS is a released corpus of nearly all US municipal and county ordinance codes, processed via OCR and paired with ModernBERT classifiers for dimensions such as opacity and paternalism.
-
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.
-
RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents
RealDocBench supplies 1,356 field-level QA questions over 581 real documents and 1,500 annotated pages, evaluating 18 systems on per-field accuracy, cost, and latency.
-
METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognition
METATR is a new benchmark dataset and evaluation framework for ATR covering 29 languages, multiple scripts and layouts, with standardized prompting and a dynamic extensible protocol.
-
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.
-
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.
-
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.
-
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models
EKSFT masks high-entropy or high-KL tokens in low-data SFT to preserve pre-trained distribution and improve downstream RL performance on math reasoning tasks.