4 papers
RIPPLE: Generating Multi-Channel Phase, Not Recovering It
Jaehyuk Lee, Yeajin Lee, Dayeon Shin +1
Generative models synthesize magnitude spectra with high fidelity, while phase is delegated to a recovery module---Griffin--Lim, a vocoder, or a latent decoder---applied independen…
ASAP: Attention Sink Anchored Pruning
Jaehyuk Lee, Hanyoung Kim, Yanggee Kim +1
Vision Transformers (ViTs) face severe computational bottlenecks due to the quadratic complexity of self-attention at high resolutions. Existing token reduction methods rely on loc…
IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning
Jaeheun Jung, Jaehyuk Lee, Yeajin Lee +1
Importance-based structured pruning overwhelmingly relies on filter magnitude. This proxy is fundamentally flawed: due to scale invariance, functionally identical filters can recei…
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
Jaeheun Jung, Jaehyuk Lee, Changhae Jung +3
Shock waves caused by earthquakes can be devastating. Generating realistic earthquake-caused ground motion waveforms help reducing losses in lives and properties, yet generative mo…