2 papers
cs.AI2026
A Tropical Geometry View of Forgetting: A Per-Unit Projector for Knowledge-Preserving Fine-Tuning
Yuyang Zhang, Xiaoyin Chen, Chunlin Ren +1
Fine-tuning a language model on new text degrades what it already does. Replay-free projectors such as Adam-NSCL and GPM forbid one shared subspace of a layer's inputs in every row…
cs.LG2026
A Measure-Theoretic Analysis of Reasoning in Transformers: Structural Generalization and Approximation Limits
Yuyang Zhang, Yifu Zhang, Xuehai Zhou +1
Scaling laws for reasoning in large language models (LLMs) are well documented, but little theory explains their out-of-distribution (OOD) generalization. We formalize reasoning wi…