2 papers
cs.AI2026
Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training
Liang He, Xiangyu Li, Yuxin Wang +4
Reasoning language models increasingly rely on test-time compute scaling, yet most existing work studies how to allocate inference computation while treating the model itself as fi…
cs.LG2026
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Yuxuan Wang, Guangxiang Zhao, Xinyu Tan +6
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also pe…