SEM-RAG compiles telecommunication standards into structure-preserving graphs and uses entropy-guided retrieval to reach 94.1% accuracy on TeleQnA and 93.8% on ORAN-Bench-13K while reducing indexing token usage compared to standard GraphRAG.
Infinity parser: Layout aware reinforcement learning for scanned document parsing
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 9roles
background 3polarities
background 3representative citing papers
A 2B-parameter model trained with RL on verifiable LaTeX unit tests produces more compilable page-to-LaTeX reconstructions than prior OCR systems across structural and compilation metrics.
UIPress is the first encoder-side learned optical compression method for UI-to-Code that compresses visual tokens to 256, outperforming the uncompressed baseline by 7.5% CLIP score and the best inference-time baseline by 4.6% while delivering 9.1x TTFT speedup.
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.
Introduces a 200-document benchmark and character-level R-Score for contextual PII redaction, with model evaluations and human agreement data showing the task remains unsolved.
PresentAgent-2 generates query-driven multimodal presentation videos with research grounding, supporting single-speaker, multi-speaker discussion, and interactive question-answering modes.
Converting visuals to text descriptions with VLMs for explicit representation alignment, combined with token selection and uniformity regularization, yields state-of-the-art results on multimodal sentiment benchmarks.
A structured survey of multimodal code intelligence that formulates the field by code roles and organizes work into four domains while proposing verification-centered research directions.
citing papers explorer
-
SEM-RAG: Structure-Preserving Multimodal Graph Compilation and Entropy-Guided Retrieval for Telecommunication Standards
SEM-RAG compiles telecommunication standards into structure-preserving graphs and uses entropy-guided retrieval to reach 94.1% accuracy on TeleQnA and 93.8% on ORAN-Bench-13K while reducing indexing token usage compared to standard GraphRAG.
-
TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction
A 2B-parameter model trained with RL on verifiable LaTeX unit tests produces more compilable page-to-LaTeX reconstructions than prior OCR systems across structural and compilation metrics.
-
UIPress: Bringing Optical Token Compression to UI-to-Code Generation
UIPress is the first encoder-side learned optical compression method for UI-to-Code that compresses visual tokens to 256, outperforming the uncompressed baseline by 7.5% CLIP score and the best inference-time baseline by 4.6% while delivering 9.1x TTFT speedup.
-
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.
-
RedactionBench
Introduces a 200-document benchmark and character-level R-Score for contextual PII redaction, with model evaluations and human agreement data showing the task remains unsolved.
-
PresentAgent-2: Towards Generalist Multimodal Presentation Agents
PresentAgent-2 generates query-driven multimodal presentation videos with research grounding, supporting single-speaker, multi-speaker discussion, and interactive question-answering modes.
-
Explicit Representation Alignment for Multimodal Sentiment Analysis
Converting visuals to text descriptions with VLMs for explicit representation alignment, combined with token selection and uniformity regularization, yields state-of-the-art results on multimodal sentiment benchmarks.
-
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
A structured survey of multimodal code intelligence that formulates the field by code roles and organizes work into four domains while proposing verification-centered research directions.