影响力指数

23.9/100

前 33.2%

全站排名 #21,362

发表论文6 篇

平均评分4.8

年均产出2.0 篇/年

Mingi Kwon

PhD student@Yonsei University·韩国·OpenReview

研究方向

Video generation · Diffusion models · generative model.

Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers

ICLR 2026Poster

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

ICLR 2026Desk Rejected

T-VecTTS: Adding time-varying-emotion control to flow-matching-based TTS

ICLR 2026Rejected

Balanced Conic Rectified Flow

NeurIPS 2025Poster

Balanced conic rectified flow

ICLR 2025Rejected

合作者 (9)

博士导师6 篇