DiffusionOPD applies online policy distillation from per-task teachers to a unified diffusion student, with a derived closed-form per-step KL objective that unifies SDE and ODE sampling via mean matching.
One-step diffusion with distribution matching distillation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
X-Cache achieves 71% block skip rate and 2.6x wall-clock speedup in few-step autoregressive multi-camera driving world models via cross-chunk residual caching with dual-metric gating and forced KV updates.
citing papers explorer
-
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
DiffusionOPD applies online policy distillation from per-task teachers to a unified diffusion student, with a derived closed-form per-step KL objective that unifies SDE and ODE sampling via mean matching.
-
X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
X-Cache achieves 71% block skip rate and 2.6x wall-clock speedup in few-step autoregressive multi-camera driving world models via cross-chunk residual caching with dual-metric gating and forced KV updates.