Papers
1–3 of 3Research Paper·Feb 10, 2026
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scala...
8.0 viability
Research Paper·Jan 15, 2026
On the origin of neural scaling laws: from random graphs to natural language
Scaling laws have played a major role in the modern AI revolution, providing practitioners predictive power over how the model performance will improve with increasing data, compute, and number of mod...
5.0 viability
Research Paper·Feb 16, 2026
Fast and Effective On-policy Distillation from Reasoning Prefixes
On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yiel...
5.0 viability