On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
Paper • 2603.27481 • Published • 31
Dong Gong
dginf
AI & ML interests
None yet
Recent Activity
authored a paper about 23 hours ago
On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models upvoted a paper about 2 months ago
HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion ModelsOrganizations
None yet