Zhouchen Lin

The cost of tracking changing comparators in exp-concave online learning is reduced by a factor of $d^{1/3}$, resolving the dimension's optimal dependence.

Fine-tuning low-bit models can be both efficient and deployment-faithful, thanks to a new optimization technique that leverages code surrogate gradients.

Agents can significantly enhance retrieval performance in visually rich document environments, achieving a 67.50% Recall@1 compared to just 37.50% for OCR-text methods.