2 citations · 2 across the 13 of their papers we have counts for
Showing 2026 · cs.LGShow all
3 papers · 2 filters
cs.LG2026
Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning
Shinichi Uemura, Taiji Suzuki
On-policy self-distillation (OPSD) of large language models (LLMs) has demonstrated the ability to improve reasoning capabilities while preserving previously acquired knowledge. De…
cs.LG2026
DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models
Dake Bu, Wei Huang, Andi Han +5
Discrete diffusion models admit many token orders, yet most systems rely on confidence-based decoding. Confidence is a strong and efficient heuristic, but it can be myopic because…
cs.LG2026
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
Tongcheng Zhang, Zhanpeng Zhou, Mingze Wang +4
One crucial factor behind the success of deep learning lies in the implicit bias induced by noise inherent in gradient-based training algorithms. Motivated by empirical observation…