Weiwei Xing

Class-imbalance bias in long-tailed semi-supervised learning can be systematically mitigated with a novel dynamic pruning approach that reallocates gradient budgets for better generalization.

RLVR's reasoning boost isn't just about more data – it's a Goldilocks problem: too easy and LLMs skip the reasoning, too hard and they break down, but just right and they become reasoning powerhouses.