arXiv:2606. 23898v1 Announce Type: cross Abstract: Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs.
arXiv:2610.01723v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable progress in image synthesis, yet can exhibit memorization by closely reproducing individual tra...
arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.
arXiv:2506.02294v4 Announce Type: replace Abstract: Large foundation models trained on extensive datasets demonstrate strong zero-shot capabilities in various domains. Knowledge distillation has beco...
arXiv:2609.10321v1 Announce Type: new Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...
DiffusionOPD introduces a multi-task training framework for diffusion models that leverages Online Policy Distillation (OPD). The method trains task-specific teachers separately and then distills their knowledge into a single student model using the student's own rollout trajectories, thereby separating exploration from integration. The authors extend OPD from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies stochastic SDE and deterministic ODE refinement, and show that this analytic gradient yields lower variance and better generality than PPO-style gradients. Experiments demonstrate that DiffusionOPD outperforms both multi-reward RL and cascade RL baselines in training efficiency and final performance, achieving state-of-the-art results across all evaluated benchmarks.
arXiv:2607. 24731v1 Announce Type: cross Abstract: On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood.
arXiv:2610.01496v1 Announce Type: new Abstract: Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstra...
arXiv:2610.02188v1 Announce Type: cross Abstract: Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it...
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input.
arXiv:2606. 06712v1 Announce Type: cross Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs).
arXiv:2609.30988v1 Announce Type: new Abstract: Real-world image super-resolution (SR) requires recovering perceptually realistic high-resolution images from complex low-resolution observations while...
arXiv:2609.38853v1 Announce Type: new Abstract: Diffusion distillation is widely adopted to accelerate sampling, and the resulting few-step models are broadly believed to match or even surpass their...