Results for "preference optimization"

Coordinating models, tools, and logic.

Limiting inference usage.

Maximum system processing rate.

Mathematical framework for controlling dynamic systems.

Optimizes future actions using a model of dynamics.

Control that remains stable under model uncertainty.

Computing joint angles for desired end-effector pose.

High-fidelity virtual model of a physical system.

Randomizing simulation parameters to improve real-world transfer.

Directly optimizing control policies.

Sampling-based motion planner.

Modeling environment evolution in latent space.

Ensuring robots do not harm humans.

Acting to minimize surprise or free energy.

Learning without catastrophic forgetting.

Fabrication of cases or statutes by LLMs.

AI-driven buying/selling of financial assets.

AI applied to scientific problems.

Finding mathematical equations from data.

Designing efficient marketplaces.

Collective behavior without central control.

Stored compute or algorithms enabling rapid jumps.

Tradeoff between safety and performance.

Regulating access to large-scale compute.

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...