Surabhi S Nath

Surabhi S Nath

Doctoral student, Max Planck School of Cognition

Part-time ML Researcher, Bertelsmann AI Hub

I'm a final-year PhD student at the Max Planck Institute for Biological Cybernetics & Max Planck School of Cognition in Tübingen, Germany, in the group of Prof. Peter Dayan. My interdisciplinary research lies at the intersection of computational cognitive science/neuroscience, human-centred AI and machine learning, where I study higher-order cognitive phenomena such as creativity, aesthetics, and design.

Highlights of my PhD:

I am currently on the industry job market and wish to continue tackling hard problems at the frontier of human-centred AI and AI for creativity. Reach out at surabhi.s.nath@maxplanckschools.de for a chat.

Education

2022—present

Ph.D., Computational Neuroscience

Max Planck Institute for Biological Cybernetics, Max Planck School of Cognition & University of Tübingen

Advised by Prof. Peter Dayan

2020—2022

M.Sc., Mind & Brain

Berlin School of Mind and Brain, Humboldt University

2016—2020

B.Tech. (Hons.), Computer Science and Engineering

IIIT Delhi · minor in Computational Biology

Papers

Unified Agentic Video Editing Across Levels of Complexity and Creativity

Nath, S. S., Ferres, K., Petrovic, M. & Schulz, L.

NeurIPS Agentic AI Benchmarks and Applications · 2026 (submitted)

A Compositional Representation for Semantic Search

Nath, S. S., Modirshanechi, A.*, & Dayan, P.*

Under review at Nature Communications · 2026

Designing Rewards for Rewarding Designs

Nath, S. S., Jayawardana, V., Van, M., Klenk, M. & Hakimi, S.

Design Computing and Cognition · 2026

Best Paper Honourable Mention

Solving Spatial Supersensing Without Spatial Supersensing

Udandarao, V., Karthik, S., Nath, S. S., Hochlehnert, A., Bethge, M., & Prabhu, A.

Efficient Spatial Reasoning Workshop, ICLR · 2026

Outstanding Paper Award

A Foundation Model to Predict and Capture Human Cognition

Binz, M., ..., Nath, S. S., ..., Schulz, E.

Nature · 2025

Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AI

Nath, S. S., del Cuvillo y Schröder, G., & Stevenson, C.

CogSci · 2025

Oral, 13.8% acceptance

Complexity in Complexity: Understanding Visual Complexity Through Structure, Color, and Surprise

Saritas, K., Dayan, P., Shen, T. & Nath, S. S.

CogSci · 2025

Characterising the Creative Process in Humans and Large Language Models

Nath, S. S., Dayan, P., & Stevenson, C.

ICCC · 2024

Simplicity in Complexity: Explaining Visual Complexity using Deep Segmentation Models

Nath, S. S.*, Shen, K.*, Dayan, P., & Brielmann, A.

ICLR Representation Alignment Workshop · 2024

Relating Objective Complexity, Subjective Complexity and Beauty

Nath, S. S., Brändle, F., Schulz, E., Dayan, P.*, & Brielmann, A. A.*

Psychology of Aesthetics, Creativity and the Arts · 2023

* denotes equal contribution

Experience

Bertelsmann AI Hub

Machine Learning Researcher

Part-time · Sep 2026–present · 1 mo

Continuing to enhance trailer editing pipelines. Publishing core findings to machine learning conferences, and releasing findings as blog posts.

Research Intern

Full-time · May–Aug 2026 · 4 mos · Hybrid

Developed automated video-editing workflows for deployment across Bertelsmann companies, including Fremantle, Penguin Random House, and RTL Group. Experimented with and applied agentic AI to a wide range of edits such as previews, summaries, precaps, reels, and cinematic trailers. Engaged with multiple stakeholders, and received positive feedback from in-house video editors.

Toyota Research Institute, Human-Centered AI

Research Intern

Jul–Oct 2025 · Advisors: Shabnam Hakimi, Matt Klenk

Worked in the Future Product Innovation team. Developed an AI design feedback tool for designers and demonstrated the impact of goals and rewards on the design process. Work led to a conference paper and award.

Invited Talks

Press

Beyond the lab