arxiv:2510.24684
Jack Lanchantin
jcklcn
ยท
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
Bridging Offline and Online Reinforcement Learning for LLMs
authored
a paper
5 days ago
CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning
and non-reasoning tasks
authored
a paper
5 days ago
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
Organizations
models
0
None public yet
datasets
0
None public yet