Tag
ColGraphRAG replaces single-vector bi-encoder similarity with late-interaction MaxSim scoring for ranking graph-linked image candidates in multimodal GraphRAG, improving retrieval and QA accuracy on MultimodalQA.
Tony Wu released late-interaction-kernels (LIK): fused Triton kernels for MaxSim, the scoring step behind ColBERT and ColPali, integrated into PyLate and colpali-engine, offering memory efficiency and performance gains.