10 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…
Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
Dahee Kwon, Haeun Lee, Jaesik Choi
Recent text-to-image models built on large-scale Transformer backbones and flow-based objectives deliver strong text-image alignment and high visual quality, yet often produce over…
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…
LoCO: Low-rank Compositional Rotation Fine-tuning
An Nguyen, Jaesik Choi, Anh Tong
Parameter-efficient fine-tuning (PEFT) has emerged as an critical technique for adapting large-scale foundation models across natural language processing and computer vision. While…
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…