6 papers
VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion
Kwanyoung Kim
Masked discrete diffusion models perform strongly on text, code, and biological sequences, but their training objective rewards only naturalness, and retraining the generator for e…
Reward Sharpness-Aware Fine-Tuning for Diffusion Models
Kwanyoung Kim, Byeongsu Sim
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusi…
Directional Attention Guidance for Diffusion Models via Sparse Hopfield Retrieval
Kwanyoung Kim
Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and null-condition training limit its use in few-step regimes. Attention-spa…
Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance
Kwanyoung Kim
Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the s…
Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
Kwanyoung Kim, Sanghyun Kim
The choice of initial noise strongly affects quality and prompt alignment in video diffusion; different seeds for the same prompt can yield drastically different results. While rec…
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Kwanyoung Kim, Byeongsu Sim
Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing me…