Minhyuk Sung

5 papers KAIST

• $\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
• Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
• Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models
• Neural Green’s Functions
• ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation