Aaron D. Ames

Session G Abstracts Effects of kinematic reference quality on dynamics-aware humanoid motion retargeting

CSF: Contextual Safety Filtering for Motion Generators

Contextual safety filtering (CSF), a training-free filter that grounds natural-language safety rules in safe and unsafe reference trajectories produced by the generator, is introduced.

HULK: Learning Whole-Body Forceful Loco-Manipulation for Humanoids

Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the upper body, challenging balance and command tracking. We present HULK, a whole-body control framework for forceful loco-m...

The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface

A reweighting equivalence is derived between the proposed information-bottleneck objectives for action-conditioned InfoNCE and action prediction, motivating InfoNCE as a proxy for layer quality and providing the most consistent positive association with policy success among four evaluated proxies.