arxiv:2609.37041
xiaotong
xtongji
AI & ML interests
None yet
Recent Activity
commentedon a paper about 12 hours ago
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening authored a paper 8 days ago
iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs authored a paper 8 days ago
Beam Search as Test-Time Self-Distillation via Counterfactual ContextsOrganizations
None yet
models 0
None public yet
datasets 0
None public yet