Topic
vla
Artificial Intelligence #finetuning#vision-language-action
New Training-Free Method Compresses Vision-Language-Action Models by 50% Without Performance Loss
A research team led by Gia-Binh Ho et al. discovered that Vision-Language-Action (VLA) models exhibit severe layer-wise redundancy. They introduced a training-free compression pipeline using Centered Kernel Alignment to remove twin layers, achieving up to 50% depth reduction, 40-50% faster fine-tuning, and 30% faster inference while matching or exceeding full-scale performance.
Jun 20, 2026 1 source
Artificial Intelligence #autonomous driving#safety envelopes
New Research Reveals Two-Dimensional Safety Envelopes for Autonomous Driving AI Planners
A new arXiv paper evaluates Alpamayo R1, a 10B-parameter driving VLA, on 15,968 attack pairs and finds that a single aggregate safety threshold masks scenario-specific failure severity. The researchers propose two-dimensional safety envelopes combining noise tolerance and high-severity failure rate for ISO 21448 (SOTIF) certification.
Jun 17, 2026 1 source