works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

RIPPLE: Generating Multi-Channel Phase, Not Recovering It

Jaehyuk Lee, Yeajin Lee, Dayeon Shin +1

The paper introduces RIPPLE, a method that generates inter‑channel phase directly using a prior‑based Griffin–Lim approach and rectified flow, improving phase coherence for multi‑c…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

Jaeheun Jung, Bosung Jung, Suhyun Bae +1

Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show that this is not enough. Across 14 rep…

cs.LG2025

Data-Driven Dimensional Synthesis of Diverse Planar Four-bar Function Generation Mechanisms via Direct Parameterization

Woon Ryong Kim, Jaeheun Jung, Jeong Un Ha +2

Dimensional synthesis of planar four-bar mechanisms is a challenging inverse problem in kinematics, requiring the determination of mechanism dimensions from desired motion specific…

cs.LG2025

Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Space

Jaeheun Jung, Donghun Lee

Structured pruning aims to reduce the size and computational cost of deep neural networks by removing entire filters or channels. The traditional regularizers such as L1 or Group L…