影响力指数

10.81/100

超过 33.4%

全站排名 #42,884

发表论文3 篇

平均评分4.8

年均产出1.5 篇/年

Xin Cheng

MS student@Renmin University of China·中国·OpenReview

研究方向

Audio Generation · Video Generation · Speech Generation · Multimodal

VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning

ICLR 2026Rejected

Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction

ICLR 2026Rejected

AFlow: Automating Agentic Workflow Generation

合作者 (20)