Sungeun Hong

4

Papers

15

Total Citations

Papers (4)

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

Question-Aware Gaussian Experts for Audio-Visual Question Answering

Task Vector Quantization for Memory-Efficient Model Merging

PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models