BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries Paper • 2601.15197 • Published Jan 21 • 55
Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models Paper • 2509.01909 • Published Sep 2, 2025 • 6
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Paper • 2505.21494 • Published May 27, 2025 • 8
