7 papers
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…
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…
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…
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…
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…
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…