1 citations · 2 across the 7 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
The Convergence Gap: Instruction-Tuned Language Models Stabilize Later in the Forward Pass
Yifan Zhou
Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes each layer's next-token distrib…
cs.LG2026
Same Targets, Different Computation: How Post-Training Divides Work Across Model Layers
Yifan Zhou
A late-layer change learned during post-training may work on the base model's earlier state, or it may depend on earlier computation learned with it. We distinguish these cases wit…
cs.LG2025
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
Zelin Tan, Hejia Geng, Xiaohang Yu +14
While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largel…