JEPA-Anything: Learning Predictive Models across Different Worlds Paper • 2609.20800 • Published 4 days ago • 56
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models Paper • 2609.19671 • Published 4 days ago • 32
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published 13 days ago • 53