Certain Gaussian initial noises act as winning tickets that bias motion diffusion toward specific semantics; retrieving and KL-refining them improves text-motion alignment without retraining.
In: ICLR (2022)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Low-rank additive experts with dual-scale gating and threat-guided diversification improve multi-perturbation adversarial robustness by routing different threat types through distinct model pathways.
citing papers explorer
-
Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
Certain Gaussian initial noises act as winning tickets that bias motion diffusion toward specific semantics; retrieving and KL-refining them improves text-motion alignment without retraining.
-
RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations
Low-rank additive experts with dual-scale gating and threat-guided diversification improve multi-perturbation adversarial robustness by routing different threat types through distinct model pathways.