Max Ku
University of Waterloo / TIGER-Lab researcher; co-author on multimodal benchmarks like ImagenHub and MEGA-Bench.
- Role
- grad-student
- Currently at
- TIGER-Lab
- twitter.com/maxku2002
- GitHub
- github.com/kbressem
- Scholar
- scholar.google.com/scholar
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
arXiv 2026
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
arXiv 2026
TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding
arXiv 2025
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
NeurIPS
AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks
arXiv 2024
MANTIS: Interleaved Multi-Image Instruction Tuning
arXiv 2024
ImagenHub: Standardizing the evaluation of conditional image generation models
arXiv 2023
TheoremQA: A Theorem-driven Question Answering dataset
arXiv 2023
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers
Wenhu Chen
professor
Cong Wei
Dongfu Jiang
Ping Nie
Thomas Chong
Tianle Li
research-scientist
Weiming Ren
grad-student
Xiang Yue
researcher
Xuan He
researcher
Xueguang Ma
grad-student