ICLR 2026 Presentations from our group

Check our group's work paper at ICLR!

1 . Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time

Blake Bordelon ⋅ Mary Letey ⋅ Cengiz Pehlevan

2. Discovering alternative solutions beyond the simplicity bias in recurrent neural networks

William Qian ⋅ Cengiz Pehlevan

3. Pretrain–Test Task Alignment Governs Generalization in In-Context Learning

Mary Letey ⋅ Jacob Zavatone-Veth ⋅ Yue Lu ⋅ Cengiz Pehlevan

4. Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate Scheduling

Alexandru Meterez ⋅ Depen Morwani ⋅ Jingfeng Wu ⋅ Costin-Andrei Oncescu ⋅ Cengiz Pehlevan ⋅ Sham Kakade

5. Transfer Learning in Infinite Width Feature Learning Networks

Clarissa Lauditi ⋅ Blake Bordelon ⋅ Cengiz Pehlevan