4 papers
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Luyi Jia, Boyan Zhang, Yilun Liu +1
Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coeff…
Field-level prediction of mid-plane stress tensor fields in concrete target penetration: a cross-velocity graph neural operator surrogate
Wenpu Du, Peng Zhou, Yunlong Xia +5
Although the impact resistance of concrete has been studied extensively, a framework linking mesoscale heterogeneity to full-field stress-tensor prediction has been lacking. Data w…
CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and Defenses
Boyang Zhang, Qingxin Xiao, Lingwei Dang +1
Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in untrusted tool outputs and c…
A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamics
Wenpu Du, Peng Zhou, Yunlong Xia +5
Neural operators applied to transient-dynamics PDEs with strong discontinuities exhibit autoregressive instability: in concrete-penetration stress-field prediction, the wavelet neu…