Ahmed Masry

Intern@Mila - Quebec Artificial Intelligence Institute·加拿大·OpenReview

研究方向

Multimodal Document Understanding · Document Question Answering · Document LLMs · Vision Language LLMs · Multimodal Chart Understanding · Chart Question Answering · Chart Summarization · Chart LLMs

4.0

SCOPE: Selective Cross-modal Orchestration of Visual Perception Experts

ICLR 2026Rejected

3.5

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

ICLR 2026Withdrawn

三作

6.8

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

NeurIPS 2025Poster

一作

6.0

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

COLM 2025Poster

一作

5.8

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

合作者 (20)