Ruiqi Zhang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation
The paper proposes Distribution-Aligned Self-Distillation (DASD) to improve self-distillation by dynamically filtering high-perplexity tokens, thereby preserving useful logical knowledge while suppressing harmful stylistic biases.
Highlighted terms show continued research focus across papers