QEncodeBench tasks large language models with encoding classical constraint problems as phase oracles and scores the generated circuits with an adversarially self-validated verifier that decides full solution-set equivalence up to a global phase, with ancillas restored and resource budgets enforced.
Xu-Jun Che, Han-Han Wu, Yu-Chen Yuan et al.· 1 citation
Poisson subsampling is the default sampler in differentially private optimization because its independence makes privacy amplification tractable. Practical systems, however, are moving toward structured participation: random allocation (balls-in-bins), per-epoch allocation, random check-ins, schemes widely believed to...
The results indicate that diffusion transformers carry more concept-level information than current attribution methods recover, and that much of it is lost on the way to the mask rather than absent from the model.
Rajatsubhra Chakraborty, Xu-Jun Che, Ritabrata Chakraborty et al.· 0 citations
The exact DP constant is pin down for the two that carry the practical weight, counterfactual memorization and adaptive extraction, and it is shown that they do not control each other.
On the NPLIB1 benchmark, MARLIN is the strongest method evaluated without a ground-truth formula across exact-match accuracy, structural distance, and fingerprint similarity, and it recovers the correct molecular formula as a byproduct about as often as a dedicated predictor without ever using one.
Xujun Che, Xiuxia Du, Depeng Xu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.