6 papers
MemeMind: Reference-Guided Trace Construction for Offline Context Optimization
Run Yang, Weihang Wang, Boheng Sheng +7
Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollouts on an adaptation set, bu…
STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
Wenxiao Zhang, Yu Liu, Qiang sun +5
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction require…
Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding
Yihao Ding, Qiang Sun, Puzhen Wu +3
Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads…
DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral
Qiang Sun, Sirui Li, Tingting Bi +4
Acquiring structured data from domain-specific, image-based documents such as scanned reports is crucial for many downstream tasks but remains challenging due to document variabili…
SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration
Qiang Sun, Tingting Bi, Sirui Li +4
We present \textbf{SymbioticRAG}, a novel framework that fundamentally reimagines Retrieval-Augmented Generation~(RAG) systems by establishing a bidirectional learning relationship…
TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs
Qiang Sun, Sirui Li, Du Huynh +2
Question answering over temporal knowledge graphs (TKGs) is crucial for understanding evolving facts and relationships, yet its development is hindered by limited datasets and diff…