3 papers
cs.LG2026
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
Tianyu Li, Dongchen Han, Zixuan Cao +7
The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and represen…
cs.LG2025
Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones
Ranfei Chen, Ming Chen, Kaifei Wang
Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly…
cs.LG2025
DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns
Ranfei Chen, Ming Chen
Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but the…