Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
Xupeng Chen, Chenqian Le, Jiayi Cheng +2
A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-activation gr…
cs.AI2026
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretr…
cs.AI2026
Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can…