3 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
Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
Yan Zhou
Foundation models are often used as fixed black-box predictors for downstream tasks with limited labeled data, but their predictions may be biased and unsafe to trust blindly. We s…
cs.CL2026
The Impossibility Triangle of Long-Context Modeling
Yan Zhou
We identify and prove a fundamental trade-off governing long-sequence models: no model can simultaneously achieve (i) per-step computation independent of sequence length (Efficienc…