GeezerVison

About

I am a PhD student in Computer Science at Stanford, advised by Serena Yeung-Levy and Ludwig Schmidt. I work on multimodal generation and representation, with applications to scientific discovery.

I'm also interested in questions of trust and reliance in AI, and their societal implications. I am an organiser of the Cognitive Security Task Force at Stanford HAI, and interned at the Center for Human Compatible AI at Berkeley.

Previously: I received an MPhil in Computer Science from Cambridge, working with Pietro Liò and Petar Veličković; traded for D. E. Shaw & Co.; and got my physics B.A. from Princeton, where I was into condensed matter theory.

Research

• Rethinking Visual Understanding in Text-to-Image Reward Modeling
  Shiye Su, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy
  NeurIPS 2026, Spotlight
  We find that widely-used reward models for text-to-image generation are remarkably poor visual reasoners, with these capabilities degrading during preference tuning. We leverage existing multimodal learning data to create a novel type of preference pairs that differ along the text rather than image axis, and use them to achieve improved prompt adherence.
• Learning to See Through Language: An Exploration of Language Modeling's Effect on Visual Representations
  Mark Endo, Shiye Su, Yuhui Zhang, Serena Yeung-Levy
  NeurIPS 2026
  Does language modeling actually improve vision, or just bend visual features toward text? We find that visual-instruction-fine-tuning can sharpen semantics and learn stronger representations for downstream applications, but can also erode fine-grained geometry. We propose a lightweight adapter to turn frozen MLLMs into competitive visual backbones.
• Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
  Dongxia Wu*, Shiye Su*, Yuhui Zhang*, Elaine Sui, Emma Lundberg, Emily Fox, Serena Yeung-Levy
  ECCV 2026
  We advance cellular perturbation modeling beyond "visually realistic" generations towards "biologically meaningful" ones by introducing a suite of biogically-informed rewards. Used as additional evaluators, training signals for reinforcement post-training, and verifiers for test time scaling, these rewards yield the new state-of-the-art CellFluxRL.
• Stochastic Perturbations Improve Distribution-to-Distribution Generative Models
  Shiye Su, Yuhui Zhang, Linqi Zhou, Rajesh Ranganath, Serena Yeung-Levy
  CVPR 2026 Findings
  We identify sparse supervision as a key challenge in the distribution-to-distribution learning and improve performance using simple and effective perturbations during training.
• OpenThoughts: Data Recipes for Reasoning Models
  Etash Guha, Ryan Marten, Sedrick Keh, Negin Raoof, Georgios Smyrnis, Hritik Bansal, Marianna Nezhurina, Jean Mercat, Trung Vu, Zayne Sprague, Ashima Suvarna, Benjamin Feuer, Liangyu Chen, Zaid Khan, Eric Frankel, Sachin Grover, Caroline Choi, Niklas Muennighoff, Shiye Su, Wanjia Zhao, John Yang, Shreyas Pimpalgaonkar, Kartik Sharma, Charlie Cheng-Jie Ji, Yichuan Deng, Sarah Pratt, Vivek Ramanujan, Jon Saad-Falcon, Jeffrey Li, Achal Dave, Alon Albalak, Kushal Arora, Blake Wulfe, Chinmay Hegde, Greg Durrett, Sewoong Oh, Mohit Bansal, Saadia Gabriel, Aditya Grover, Kai-Wei Chang, Vaishaal Shankar, Aaron Gokaslan, Mike A. Merrill, Tatsunori Hashimoto, Yejin Choi, Jenia Jitsev, Reinhard Heckel, Maheswaran Sathiamoorthy, Alexandros G. Dimakis, Ludwig Schmidt
  ICLR 2026 Oral; NeurIPS 2025, Workshop on Foundations of Reasoning in Language Models
  We create open-source datasets for training reasoning models and investigate each step of the data geneartion pipeline with 1,000+ controlled experiments, yielding the state-of-the-art OpenThoughts3 model.
• Position: AI Development Should Prioritize Cognitive Security
  Batu El*, Shiye Su*, Aneesh Pappu*, Peggy Yin*, Julie Heng*, Eric Heng, Ryan Wang, Andreas Haupt, James Zou
  NeurIPS 2026; ICLR 2026, AIWILD Workshop
  We argue that cognitive security – the protection of human cognitive processes from hazardous influence – is an AI research priority. We review relevant state-of-the-art capabilities and research, and propose an agenda comprising attack/defense mechanisms and metrics for cognitive impacts.
• CellFluxV2: An Image Generative Foundation Model for Virtual Cell Modeling
  Yuhui Zhang, Yuchang Su, Zoe Wefers, Shiye Su, He Li, Tianhong Li, Chenyu Wang, James Burgess, Alejandro Lozano, Linqi Zhou, Daisy Ding, Jeffrey J Nirschl, Emma Lundberg, Serena Yeung-Levy
  ML4H 2025; under journal submission
  We introduce an image generative foundation model to simulate cellular morphology behaviours under chemical and genetic perturbations. We establish biological scaling laws in model size and dataset scale for this virtual cell model.
• Generative Neural Networks for Kerr Combs
  Janet Zhong, Eran Lustig, Shiye Su, Louise Schul, Jamison Sloan, Congyue Deng, Jelena Vuckovic, Shanhui Fan
  NeurIPS 2025, Machine Learning and the Physical Sciences Workshop
  We apply generative modeling to the inverse design of Kerr micro-resonators, finding high-bandwidth steady-state solitons as given by Lugiato-Lefever equation simulations.
• Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts
  Shiye Su, Iulia Duta, Lucie Charlotte Magister, Pietro Liò
  We design an architecture-agnostic, post-hoc method to produce faithful and concise explanations for hypergraph neural networks.
• Commute-Time-Optimised Graphs for GNNs
  Igor Sterner*, Shiye Su*, Petar Veličković
  ICML 2024, GRaM workshop (PMLR)
  We develop a graph rewiring procedure based on Cayley expanders, reducing oversquashing and incorporating user priors.
• ALMANACS: A Simulatability Benchmark for Language Model Explainability
  Edmund Mills, Shiye Su, Stuart Russell, Scott Emmons
  We introduce a simulatability benchmark for language model interpretability, comprising structured, idiosyncratic questions with test-time distributional shift.
• Fitness Aware Human Motion Generation with Fine-Tuning
  Kiril Bikov, Shiye Su, Deepro Choudhury, Zhilin Guo, Weihao Xia, Mehmet Salih Çeliktenyıldız, Chenliang Zhou, Param Hanji, Cengiz Oztireli
  NeurIPS 2025, FITML Workshop
  We condition a human motion diffusion model on subject fitness, learning from a motion-capture dataset of graded Functional Movement Screen actions.
• Chaos and Measurement-Induced Criticality on Stabiliser Circuits
  Shiye Su
  My undergraduate thesis was advised by Sarang Gopalakrishnan and David Huse. We studied the entanglement transition in a many-body system evolving under Clifford gates and projective measurements, as well as the spectral and thermalisation properties of Clifford gates.

Awards

Stanford School of Engineering Fellowship, 2024

Stanford EDGE Fellowship, 2024

QuantCo ICML Travel Scholarship, 2024

Open Philanthropy Scholarship, 2023

Phi Beta Kappa

Sigma Xi

Misc

I am from Brisbane and President of the Australia and New Zealand Club at Stanford; we organised the first ANZ in AI Forum in the Bay Area! In 2023, I walked for one month from the French Pyrenees to Santiago de Compostela. My first research project claims to find a heuristic for the Travelling Salesman Problem by tracking C. Elegans worms in chemotaxis. 🪱