Search papers, labs, and topics across Lattice.
Macquarie University
3
0
3
3
MMEACR achieves significant performance improvements in visually grounded recommendations by effectively integrating multimodal memory and collaborative reasoning.
Stop drowning your MLLMs in irrelevant document noise: FES-RAG shows that carefully selecting multimodal fragments as evidence boosts performance by up to 27% while shrinking context length.
Semantic grounding, not token probability, is the key to better multimodal RAG.