A learned simulator can reproduce its training conditions accurately yet fail in two distinct ways once those conditions change. Over long rollouts, small errors accumulate until the trajectory drifts away from physically plausible behavior; under an intervention on a physical parameter, the model may continue to follo...
Yu-Feng Wang, Parivesh Priye, Lu Wei et al.· 0 citations
Bayesian quantum tomography requires efficient inference while preserving a posterior fixed by the prior and Born likelihood. Learned transport provides fast amortized samples, but reward tuning can reshape the generated distribution rather than improve exploration of this fixed target. We introduce GRPO-QPS, a target-...
Yu-Feng Wang, Parivesh Priye, Lu Wei et al.· 0 citations
VoiceLongMemEval (VLME) benchmark, where every answer depends on paralinguistic metadata attached to conversational turns, which is otherwise unrecoverable from the words alone, is presented.