Search papers, labs, and topics across Lattice.
4
0
6
Shrinking visual document retrieval storage by 95% is now possible without sacrificing accuracy, thanks to a layout-aware parsing strategy.
Stop feeding VLMs the same graph representation for every question – DynamicGTR dynamically picks the best one, boosting accuracy and brevity in graph Q&A without retraining.
Multi-vector visual document retrieval gets a speed boost without sacrificing accuracy thanks to a novel "Prune-then-Merge" approach that intelligently compresses visual features.
The first comprehensive survey of Visual Document Retrieval reveals how MLLMs are reshaping the field, highlighting the shift towards RAG and agentic systems for complex document understanding.
