ICML 2026 Schedule

Oral

Mon Jul 06 06:00 PM -- 06:15 PM (PDT) @ HALL C None

Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs

In Oral 1A LLM Adaptation and Dataset Selection

Sagnik Mukherjee ⋅ Lifan Yuan ⋅ Pavan Jayasinha ⋅ Dilek Hakkani-Tür ⋅ Hao Peng

[ OpenReview]

Oral

Mon Jul 06 06:15 PM -- 06:30 PM (PDT) @ HALL C None

Learning Unmasking Policies for Diffusion Language Models

In Oral 1A LLM Adaptation and Dataset Selection

Metod Jazbec ⋅ Theo X. Olausson ⋅ Louis Béthune ⋅ Pierre Ablin ⋅ Michael Kirchhof ⋅ Joao Monteiro ⋅ Victor Guilherme Turrisi da Costa ⋅ Jason Ramapuram ⋅ Marco Cuturi

[ OpenReview]

Oral

Mon Jul 06 06:30 PM -- 06:45 PM (PDT) @ HALL C None

Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders

In Oral 1A LLM Adaptation and Dataset Selection

Zhongzhi Li ⋅ Xuansheng Wu ⋅ Yijiang Li ⋅ Lijie Hu ⋅ Ninghao Liu

[ OpenReview]

Oral

Mon Jul 06 06:45 PM -- 07:00 PM (PDT) @ HALL C None

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

In Oral 1A LLM Adaptation and Dataset Selection

Shaobo Wang ⋅ Xuan Ouyang ⋅ Tianyi Xu ⋅ Yuzheng Hu ⋅ Jialin Liu ⋅ Guo Chen ⋅ Tianyu Zhang ⋅ Junhao Zheng ⋅ Kexin Yang ⋅ Xingzhang Ren ⋅ Dayiheng Liu ⋅ Linfeng Zhang

[ Slides] [ OpenReview]