arXiv Machine Learning
Visualizing Distribution Coverage in Generative Diffusion Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
2d ago
GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales
The paper introduces GFD-OPD, a method for on‑policy distillation of diffusion models that addresses challenges when compressing large teachers into smaller students. It identifies that standard distillation fails due to distribution gaps and classifier‑free guidance amplification, and proposes Fixed‑State KL to measure these gaps. GFD‑OPD reduces the student‑teacher discrepancy and achieves state‑of‑the‑art performance across multiple benchmarks.
arXiv AI
2d ago
Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution
The paper introduces a new method for training data attribution in diffusion models called TID, which uses a local score discrepancy measure and can be estimated without retraining. It further distills this approach into TIDE, a forward‑only student that reproduces the teacher’s rankings using internal activations, achieving comparable accuracy at dramatically lower query cost. Experiments on CIFAR‑10, ArtBench‑10, and MS‑COCO show that TID outperforms existing methods and TIDE attributes samples in milliseconds, faster than generation itself.
arXiv AI
1d ago
DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
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...
arXiv AI
2d ago
CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models
CAST introduces a reinforcement‑learning fine‑tuning framework for diffusion models that addresses three key limitations: it automatically selects the denoising window based on each model’s trajectory, decomposes prompts into verifiable semantic atoms via Causal Scene Graphs, and applies atom‑level rewards spatially weighted in the policy objective. The method is applied to FLUX.2‑dev and Qwen‑Image‑2512, yielding up to 3.07× improvement on the hardest GenEval 2 prompts compared with Flow‑GRPO while also enhancing overall generation quality.
arXiv Computer Vision
2d ago
ReDiF: Resource-Efficient Few-Step Diffusion Distillation via Reinforcement Learning
arXiv:2512.22802v2 Announce Type: replace-cross Abstract: Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remai...
arXiv Machine Learning
Aug 4
Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models
arXiv:2608. 01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-token distributions at prefixes along those trajectories.