xiaotong

xtongji

·

AI & ML interests

None yet

Recent Activity

commentedon a paper 4 days ago

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

authored a paper 12 days ago

iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs

authored a paper 12 days ago

Beam Search as Test-Time Self-Distillation via Counterfactual Contexts

View all activity

Organizations

None yet

xtongji 's papers 11

arxiv:2609.37041

arxiv:2609.38096

arxiv:2610.00332

arxiv:2609.34992

arxiv:2609.24646

arxiv:2603.20105

arxiv:2602.18292

arxiv:2602.05547

arxiv:2601.21590

arxiv:2509.22921

arxiv:2507.02726