任务感知提示重写器TAPR，让大模型性能再上台阶。
arXiv:2607.28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, w…
提出任务感知Stein正则化方法，用几何先验增强深度学习模型鲁棒性
arXiv:2605.30601v1 Announce Type: new Abstract: Modern deep networks remain fragile under distribution shift and adversarial perturbations, often due …
通过引入任务感知机制，直接在结构空间建模LLM输出，提升生成质量与不确定性估计的准确性。
arXiv:2601.21500v2 Announce Type: replace Abstract: In many applications of LLMs, natural language responses often have an underlying structure such a…
探究任务感知剪枝如何提升模型在分布外数据上的表现，揭示内在机制
arXiv:2605.14738v1 Announce Type: cross Abstract: Recent work has promoted task-aware layer pruning as a way to improve model performance on particula…