Evaluating alignment of behavioral dispositions in LLMs
As LLMs integrate into our daily lives, understanding their behavior becomes essential. In our ongoing efforts to study model behavior and alignment, we present this work as an early step…
-
-
Towards demystifying the creativity of diffusion models
Score smoothing facilitates manifold recovery In the real world, complex data like high-resolution images live in high-dimensional pixel spaces rather than a simple 1-D world. The vast majority of that…
-
Introducing two AI agents for better figures and peer review
PaperVizAgent: Generating publication-ready figures PaperVizAgent is an autonomous framework designed to generate publication-ready academic illustrations from academic text. By bridging the gap between technical descriptions and visual communication, PaperVizAgent allows…
-
Measuring and bridging the realism gap in user simulators
Modern conversational AI agents can typically handle complex, multi-turn tasks like asking clarifying questions and proactively assisting users. However, they frequently struggle with long interactions, often forgetting constraints or generating…
-
AI-generated synthetic neurons speed up brain mapping
Using computers to create full wiring maps of complex brains is enabling a new era of neuroscience. A recently released map of the complete male fruit fly brain and central…
-
Mechanism design and reasoning from first principles
The rapid advance of generalist AI models has been fueled by the abundance of internet data. However, widespread integration of AI will require models to specialize in novel, uncommon, and…
-
Enabling agents to learn from experience
Distilling insights with ReasoningBank ReasoningBank distills global reasoning patterns into high-level, structured memories. Each structured memory item contains the following: Title: A concise identifier summarizing the core strategy. Description: A…
-
Verifying Rust cryptography in SymCrypt, from standards to code
How Rust, Lean, Aeneas, and AI agents are helping scale formal verification for production cryptographic algorithms At a glance SymCrypt develops new verified cryptography using Rust, Aeneas, and Lean to…
-
Four ways Google Research scientists have been using Empirical Research Assistance
Climate and sustainability: Using weather satellites to monitor CO2 Regular observations of carbon dioxide (CO2) began at Hawaii’s Mauna Loa Observatory in the late 1950s, yielding the iconic Keeling Curve…
-
Catalyzing scientific impact through global partnerships and open resources
A scientific breakthrough reaches its full potential only when it empowers others to replicate and expand upon findings, pushing the boundaries of science even further. At Google Research, we recognize…
