Kaifeng Chen

MARDoc's innovative use of structured memory allows for clearer reasoning in long-document QA, outperforming traditional methods that struggle with context dilution.

Gemini Embedding 2's unified multimodal embeddings beat specialized models across diverse tasks and even generalize zero-shot to niche fields like astronomy and culinary arts.

Distilling patch-text alignment knowledge from a teacher model to a student surprisingly *improves* the student's alignment beyond that of the teacher.