Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large language models to downstream tasks. However, most existing PEFT methods rely on uniform and static adaptations, without accounting for the structured heterogeneity of attention across dimensions, heads, layers, and input tokens. I...
Dayan Pan, Jing-Yuan Wang, Xie Yu· Proceedings of the 32nd ACM...· 0 citations
This work presents AgentCity, an AI-maintained framework for the continuous construction and evaluation of traffic prediction benchmarks and validate the reliability of AgentCity through benchmark validation studies on reproduction fidelity and consistency across different code-oriented agents.
Dayan Pan, Hongkang Su, Jing-Yuan Wang et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.