Leadership in frontier AI research and filmmaking.

Frontier AI research leaders from CMU.Former CTO of Warner Bros.AI researchers and engineers who are filmmakers.

Zhiqiu Lin

CEO · CMU Robotics PhD

Generative AI research adopted by 100+ frontier labs, including DeepMind, xAI and ByteDance.
Worked with 300+ filmmakers on cinematic video generation (CameraBench/CHAI). Research spans data, models, and evaluation to understand film language, control camera motion, build filmmaking agents, and more.
VQAScore: significantly outperforms OpenAI's CLIP; 2M+ model downloads.
GenAI-Bench: sole image generation benchmark used in Deepmind's Nano-Banana technical report; CVPR'24 Best Short Paper.
CVPR / NeurIPS orals, spotlights, and best paper nominations.

Deva Ramanan

CMU Professor · Robotics Institute

20+ years pioneering computer vision
Best Paper honors: ICCV'09, ECCV'20, ICCV'21, ICCV'25.
2x Test-of-Time Prize: Longuet-Higgins, 2018 & Koenderink, 2024.

Graham Neubig

CMU Professor · Language Technology Institute

Co-founder & Chief Scientist, All Hands AI.
Co-led OpenHands, the world's most widely used open-source agent platform (90K stars).
EMNLP'24 Best Paper; hundreds of publications on language models, agents, and evaluation.

Team

BACKED BY EXPERIENCE FROM

NeurIPS 2025

Spotlight · Top 3%

CameraBench

Understanding camera motion in any video. Adopted by Google DeepMind, xAI, Kling, and frontier video labs.

Read paper

CVPR 2026

Highlight · Top 3%

CHAI

Building precise video language with human-AI oversight.

Read paper

ECCV 2024

Adopted in Google Imagen 3

VQAScore

State-of-the-art metric for evaluating text-to-visual generation. Google DeepMind named it the strongest replacement for CLIPScore.

Read paper

CVPR 2024

Best Paper · SynData Workshop

GenAI-Bench

Benchmark for compositional text-to-visual generation. Uniquely adopted in the official Google Nano Banana technical report.

Read paper

Whitepaper

Cinematic Video Search · Data

Moodio Retrieval

The first to bring visual reference into the video generation workflow. Retrieval outperforms both Google Gemini Embedding 2 and Alibaba Qwen-3-VL Embedding.

Read paper

Whitepaper · Forthcoming

Agent Post-Training