Search papers, labs, and topics across Lattice.
This paper adapts self-consistency, an established technique for improving LLM performance, to the visual domain of motion trajectory generation and verification. They model families of shapes associated with a prompt as a prototype trajectory paired with geometric transformations, enabling the identification of consistent trajectories via clustering. Results show a 4-6% improvement in trajectory generation accuracy and an 11% precision gain in verification compared to baselines.
LLMs can generate more accurate motion trajectories by clustering them into geometrically consistent families, even without retraining.
Self-consistency has proven to be an effective technique for improving LLM performance on natural language reasoning tasks in a lightweight, unsupervised manner. In this work, we study how to adapt self-consistency to visual domains. Specifically, we consider the generation and verification of LLM-produced motion graphics trajectories. Given a prompt (e.g.,"Move the circle in a spiral path"), we first sample diverse motion trajectories from an LLM, and then identify groups of consistent trajectories via clustering. Our key insight is to model the family of shapes associated with a prompt as a prototype trajectory paired with a group of geometric transformations (e.g., rigid, similarity, and affine). Two trajectories can then be considered consistent if one can be transformed into the other under the warps allowable by the transformation group. We propose an algorithm that automatically recovers a shape family, using hierarchical relationships between a set of candidate transformation groups. Our approach improves the accuracy of LLM-based trajectory generation by 4-6%. We further extend our method to support verification, observing 11% precision gains over VLM baselines. Our code and dataset are available at https://majiaju.io/trajectory-self-consistency .
