collaborators

8 papers

cs.LG2026

Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs

Yan Zhou, Sara Kangaslahti, Jonathan Geuter +4

Practical deployment of large language models (LLMs) requires families of post-trained variants---instruction-tuned, reasoning-tuned, and chat-style models---each at multiple sizes…

cs.LG2026

Understanding Layer Patching in Model Size Interpolation

Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak +3

Zero-shot model size interpolation aims to create new models of intermediate target sizes by combining existing models without additional training. Recent work on boomerang distill…

cs.LG2026

Inverse Depth Scaling From Most Layers Being Similar

Yizhou Liu, Sara Kangaslahti, Ziming Liu +1

Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width may contribute to performance differently, requiring more detailed studies. Here,…

cs.LG2026

Hidden Breakthroughs in Language Model Training

Sara Kangaslahti, Elan Rosenfeld, Naomi Saphra

Loss curves are smooth during most of model training, so visible discontinuities stand out as possible conceptual breakthroughs. Studying these breakthroughs enables a deeper under…

cs.LG2026

Boomerang Distillation Enables Zero-Shot Model Size Interpolation

Sara Kangaslahti, Nihal V. Nayak, Jonathan Geuter +3

Large language models (LLMs) are typically deployed under diverse memory and compute constraints. Existing approaches build model families by training each size independently, whic…

cs.SE2026

GenAI for Systems: Recurring Challenges and Design Principles from Software to Silicon

Arya Tschand, Chenyu Wang, Zishen Wan +21

Generative AI is reshaping how computing systems are designed, optimized, and built, yet research remains fragmented across software, architecture, and chip design communities. Thi…