collaborators

7 papers

cs.LG2026

Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

Soyeon Kim, Kyowoon Lee, Jaesik Choi

Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to inpu…

cs.CV2026

Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution

Soyeon Kim, Seongwoo Lim, Kyowoon Lee +1

Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integration path significantly affect…

cs.LG2026

Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution

Soyeon Kim, Seongwoo Lim, Kyowoon Lee +1

Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield…

cs.RO2026

Refining Compositional Diffusion for Reliable Long-Horizon Planning

Kyowoon Lee, Yunhao Luo, Anh Tong +1

Compositional diffusion planning generates long-horizon trajectories by stitching together overlapping short-horizon segments through score composition. However, when local plan di…

cs.LG2025

State-Covering Trajectory Stitching for Diffusion Planners

Kyowoon Lee, Jaesik Choi

Diffusion-based generative models are emerging as powerful tools for long-horizon planning in reinforcement learning (RL), particularly with offline datasets. However, their perfor…

cs.LG2025

Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning

Kyowoon Lee, Jaesik Choi

Recent advances in diffusion-based generative modeling have demonstrated significant promise in tackling long-horizon, sparse-reward tasks by leveraging offline datasets. While the…