2 papers
stat.ML2026
Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks
Xiaojing Sun, Yuhan Zeng, Zihua She +1
As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies on finite evaluation resources, such as…
stat.ML2026
Coreset-Induced Conditional Velocity Flow Matching
Xiao Wang, Zihua She, Jianxi Su
We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-informed source distribution. Standa…