NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
30 results for “keyword:"document understanding"” in ICLR 2027. 9 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]formal300: Evaluating Local-to-Global Procedure Reconstruction from FAA Approach Charts▼1601.50
[PDF]Vision-Language Models on Specification-Governed Instrument Approach Charts: Which Failures, and Which Supplied Information Changes Them▲11.00
[PDF]AmbiHTMLBench: A Multidimensional Benchmark for Image-to-HTML Reconstruction of Heterogeneous Documents▲3.0k2.33
[PDF]ITJoint: Benchmarking and Diagnosing MLLMs on Query-Driven Image-Text Joint Extraction from Long Documents▼5.8k2.33
[PDF]ExamOCRBench: A Multi-Task Benchmark for Real-World Exam Document Understanding and Automated Grading▼1.2k1.67
[PDF]ScienceDoc: Multidisciplinary Multimodal Evidence-Grounded Question Answering for Scientific Documents▼5.8k2.33
[PDF]RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures▼4.5k2.67
[PDF]EviOntoKG: Paper-Specific Ontology Induction for Evidence-Grounded Multimodal Scientific Knowledge Graph Construction▼5.3k1.33
Withdrawn or desk rejected (9)
[PDF]DERIVE: Dependency-Aware and Evidence-Responsive Reasoning via Intervention and Verifiable Execution for MLLM Long-Document UnderstandingWithdrawn1.33
[PDF]PubTables-QA: A Multi-Page Table Visual Question Answering for Cross-Page Table ReasoningWithdrawn1.67
[PDF]ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual DensityWithdrawn1.00
[PDF]SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document UnderstandingDesk rejected3.00