作者位次 #3/5ICLR 2026Poster· Deep Learning / Algorithms
LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
Nurbek Tastan · Stefanos Laskaridis · Martin Takáč · Karthik Nandakumar · Samuel Horváth
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。
Nurbek Tastan · Stefanos Laskaridis · Martin Takáč · Karthik Nandakumar · Samuel Horváth
Slavomir Hanzely · Farshed Abdukhakimov · Martin Takáč
Yanda Li · Yuhan Liu · Zirui Song · Yunchao Wei · Martin Takáč · Salem Lahlou
Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a temporal smoothing bias: transient acoustic cues may be underutilized in favor of temporally smooth context that is better supported by language priors, leading to less specific audi...