5 citations · 5 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
Jisung Hwang, Yunhong Min, Jaihoon Kim +2
We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel u…
cs.LG2026
Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation
Jisung Hwang, Minhyuk Sung
We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable. Test-time noise optimization can unloc…