作者位次 #2/4ICML 2026Poster· Deep Learning / Algorithms
Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
Qilin Ye · Deqing Fu · Robin Jia · Vatsal Sharan
理论与学习动力学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。
Qilin Ye · Deqing Fu · Robin Jia · Vatsal Sharan
Mohammadamin Banayeeanzade · Qingchuan Yang · Deqing Fu · Spencer Hong · Erin Babinsky · Alfy Samuel · Anoop Kumar · Robin Jia · Sai Praneeth Reddy Karimireddy
Woody Haosheng Gan · Deqing Fu · Julian Asilis · Ollie Liu · Vatsal Sharan · Robin Jia · Willie Neiswanger
Steering methods have emerged as effective tools for guiding large language models’ behavior, yet multimodal large language models (MLLMs) lack comparable techniques due to architectural diversity and limited availability of multimodal steering vectors. Inspired by this gap, we demonstrate that s...