影响力指数

38.05/100

前 15.9%

全站排名 #10,214

发表论文10 篇

平均评分5.6

年均产出3.3 篇/年

Wenyi Hong

PhD student@Department of Computer Science and Technology, Tsinghua University·中国·OpenReview

研究方向

Multimodal pre-training

UI2Code$^N$: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation

ICLR 2026Rejected

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

ICLR 2025Poster

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

ICLR 2025Poster

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

ICLR 2025Poster

MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model

ICLR 2025Rejected

LVBench: An Extreme Long Video Understanding Benchmark

ICLR 2025Withdrawn

合作者 (20)

博士导师10 篇