arxiv:2607.07976
Xiuyi Lou
vvvvverispencer
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching authored a paper 2 days ago
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning upvoted an article 5 months ago
🚀 DTS: A Candidate for the Best Parallel Reasoning in LLMsOrganizations
None yet
