papers

Publications (8)

cs.CV2024

Imagen 3

Imagen-Team-Google, :, Jason Baldridge +257

We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CV2021

Synthetic Data and Hierarchical Object Detection in Overhead Imagery

Nathan Clement, Alan Schoen, Arnold Boedihardjo +1

The performance of neural network models is often limited by the availability of big data sets. To treat this problem, we survey and develop novel synthetic data generation and aug…

cs.CE2016

Quantifying and Visualizing Uncertainties in Molecular Models

Muhibur Rasheed, Nathan Clement, Abhishek Bhowmick +1

Computational molecular modeling and visualization has seen significant progress in recent years with sev- eral molecular modeling and visualization software systems in use today.…

cs.CY2024

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation

Jessica Quaye, Alicia Parrish, Oana Inel +12

With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generatio…

cs.HC2024

The Evolution of LLM Adoption in Industry Data Curation Practices

Crystal Qian, Michael Xieyang Liu, Emily Reif +7

As large language models (LLMs) grow increasingly adept at processing unstructured text data, they offer new opportunities to enhance data curation workflows. This paper explores t…

q-bio.BM2019

Quantified uncertainty of flexible protein-protein docking algorithms

Nathan Clement

The strength or weakness of an algorithm is ultimately governed by the confidence of its result. When the domain of the problem is large (e.g. traversal of a high-dimensional space…

math.AG2016

Isomorphisms between moduli of parabolic Higgs bundles

Nathan Clement

In this paper we study four families of moduli problems which give rise to two dimensional examples of the Hitchin map. Using a few Fourier-Mukai transforms on the corresponding sp…