影响力指数

35.83/100

前 18%

全站排名 #11,585

发表论文7 篇

平均评分5.4

年均产出2.3 篇/年

Zi-Yi Dou

PhD student@University of California, Los Angeles·美国·OpenReview

研究方向

vision and language · natural language processing · machine translation

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

ICLR 2026Poster

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

ICLR 2026Rejected

UltraCUA: Scaling Computer Use Agent through GUI and Programmatic Control

ICLR 2026Desk Rejected

VaPR - Vision-language Preference alignment for Reasoning

COLM 2025Poster

Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning

ICLR 2025Rejected

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

ICLR 2025Poster

合作者 (20)

博士导师4 篇

Alexander T Toshev

Anh Tuan Nguyen