activity
20242026
collaborators

5 papers

cs.LG2026

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Neha Kalibhat, Zi Wang, Prasoon Bajpai +4

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior,…

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.CR2025

X-Guard: Multilingual Guard Agent for Content Moderation

Bibek Upadhayay, Vahid Behzadan, Ph. D

Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety framew…

cs.CV2025

ShieldGemma 2: Robust and Tractable Image Content Moderation

Wenjun Zeng, Dana Kurniawan, Ryan Mullins +14

We introduce ShieldGemma 2, a 4B parameter image content moderation model built on Gemma 3. This model provides robust safety risk predictions across the following key harm categor…

cs.AI2024

Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty

Meera Hahn, Wenjun Zeng, Nithish Kannen +4

User prompts for generative AI models are often underspecified, leading to a misalignment between the user intent and models' understanding. As a result, users commonly have to pai…