Kijung Jeon
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Algorithms×1Numerical Analysis×1Probability×1Stats ML×1
Frequent co-authors
Research Timeline
2026
VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
The paper introduces MDM-VGB, a reward-guided sampler for Masked Diffusion Models, which extends the Jerrum-Sinclair backtracking Markov chain to a masked-state graph for effective high-reward generation and efficient repair of low-reward samples.
Highlighted terms show continued research focus across papers