作者位次 #4/11ICML 2026Poster· Deep Learning / Large Language Models
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
Chen Liu · Xingzhi Sun · Xi Xiao · Alexandre Van Tassel · Ke Xu · Kristof Reimann · Danqi Liao · Mark Gerstein · Tianyang Wang · Xiao Wang · Smita Krishnaswamy
理论与学习动力学OpenReview