CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching Paper • 2610.08777 • Published 6 days ago • 4
CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching Paper • 2610.08777 • Published 6 days ago • 4
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience Paper • 2610.05303 • Published 8 days ago • 23
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 • 33
view post Post 413 LWDetr is available in 🤗 transformers ! Checkout the collection to find the original paper, model weights and a demo space : https://huggingface.co/collections/stevenbucaille/lwdetr See translation 🔥 2 2 + Reply
HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models Paper • 2601.15968 • Published Jan 22 • 9