AURA: Always-On Understanding and Real-Time Assistance via Video Streams Paper • 2604.04184 • Published Apr 5 • 52
On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models Paper • 2603.27481 • Published Mar 29 • 35
Rethinking Training Dynamics in Scale-wise Autoregressive Generation Paper • 2512.06421 • Published Dec 6, 2025 • 7
HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models Paper • 2601.15968 • Published Jan 22 • 9
SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts Paper • 2412.05552 • Published Dec 7, 2024 • 6
