一作ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Predicting LLM Output Length via Entropy-Guided Representations
Huanyi Xie · Yubin Chen · Liangyu Wang · Lijie Hu · Di Wang
可解释性OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Huanyi Xie · Yubin Chen · Liangyu Wang · Lijie Hu · Di Wang
Chenyang Ren · Huanyi Xie · Shu Yang · Meng Ding · Dongrui Liu · Lijie Hu · Di Wang
Huanyi Xie · Chenyang Ren · Khouloud Saadi · Shu Yang · Zhen Tan · Jingfeng Zhang · Lijie Hu · Di Wang
Liangyu Wang · Huanyi Xie · Di Wang
Fine-tuning large language models (LLMs) remains resource-intensive due to their sheer scale. While zeroth-order (ZO) optimization provides a memory-efficient alternative by eliminating backward passes, its application to multi-hundred-billion-parameter models is constrained by GPU memory and com...