papers

Publications (7)

cs.GR2017

LayerBuilder: Layer Decomposition for Interactive Image and Video Color Editing

Sharon Lin, Matthew Fisher, Angela Dai +1

Exploring and editing colors in images is a common task in graphic design and photography. However, allowing for interactive recoloring while preserving smooth color blends in the…

cs.HC2025

Towards Understanding the Use of MLLM-Enabled Applications for Visual Interpretation by Blind and Low Vision People

Ricardo E. Gonzalez Penuela, Ruiying Hu, Sharon Lin +2

Blind and Low Vision (BLV) people have adopted AI-powered visual interpretation applications to address their daily needs. While these applications have been helpful, prior work ha…

cs.LG2024

Evaluating Frontier Models for Dangerous Capabilities

Mary Phuong, Matthew Aitchison, Elliot Catt +24

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evalu…

cs.CR2025

Lessons from Defending Gemini Against Indirect Prompt Injections

Chongyang Shi, Sharon Lin, Shuang Song +11

Gemini is increasingly used to perform tasks on behalf of users, where function-calling and tool-use capabilities enable the model to access user data. Some tools, however, require…

cs.CL2024

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei +1132

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…

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.LG2025

Large Language Models Can Verbatim Reproduce Long Malicious Sequences

Sharon Lin, Krishnamurthy, Dvijotham +4

Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generat…