PPL
Kun Wang
Papers (8)
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMsEntropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning ModelsUncovering Latent Pathological Signatures in Pulmonary CT via Cross-Window Knowledge DistillationMem-W: Latent Memory-Native GUI AgentsOn Characterizing Learnability for Adversarial Noisy BanditsTyche: One Step Flow for Efficient Probabilistic Weather ForecastingHaM-World: Soft-Hamiltonian World Models with Selective Memory for PlanningRoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models