The paper introduces internal guidance as a new sampling technique for tilted diffusion models, which modifies the evaluation point of the base denoiser rather than altering its output. For discrete distributions in the hypercube, the denoiser of a linearly tilted density can be obtained by evaluating the base denoiser at a shifted and rescaled input. By augmenting training with random diagonal rescalings, a single denoiser network can sample binary reward tilts, class labels, and infilling without fine‑tuning or external guidance.
arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
arXiv:2611.02170v2 Announce Type: replace Abstract: Diffusion models are often inaccurate in critical, data-sparse regions of the target distribution. Sampling from restrained distributions, biased d...
arXiv:2602. 03211v2 Announce Type: replace-cross Abstract: Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent.
The paper investigates training diffusion models to sample from distributions defined by unnormalized densities or energy functions. It benchmarks various diffusion-structured inference techniques, including simulation-based variational methods and off-policy approaches such as continuous generative flow networks, highlighting their relative strengths and challenging some prior claims. Additionally, the authors introduce a new exploration strategy for off-policy methods that employs local search in the target space with a replay buffer, demonstrating improved sample quality across multiple target distributions.
arXiv:2609.31882v2 Announce Type: replace-cross Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to esti...
arXiv:2610.19802v1 Announce Type: new Abstract: Negative guidance of diffusion models generates samples that avoid an undesired condition, specified either by reference samples or by a conditional sc...
arXiv:2512.17303v3 Announce Type: replace Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free gu...
arXiv:2607. 14398v1 Announce Type: cross Abstract: Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution.
arXiv:2609.37147v1 Announce Type: cross Abstract: Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a \emph{distributional} denoiser trained via a scoring rule...
arXiv:2609.00279v1 Announce Type: cross Abstract: This work shows that diffusion models learned with standard denoising loss can provide effective global MCMC proposals for complex high-dimensional t...
DiffusionRVGE presents a reinforcement learning approach that improves diffusion models by estimating value gradients through regression of centered rewards on centered final denoised images, avoiding costly reward derivatives and backpropagation through the sampling trajectory. The method adapts rollout bandwidth and query weights based on reward continuity, enabling efficient training across multiple rewards. Experiments show that a single SD3.5‑Medium model trained with DiffusionRVGE matches or surpasses DiffusionNFT on most metrics while using roughly one‑fifth of the training compute, and achieves faster reward convergence in single‑reward settings.
The paper introduces GRAS, a method that improves training‑free reward alignment for discrete diffusion models by reducing variance in guided proposals and adapting the resampling temperature during search. It achieves this without adding denoiser cost, using Rao‑Blackwellized estimates for differentiable rewards and a leave‑one‑out baseline for non‑differentiable ones. Experiments on regulatory DNA and protein design show GRAS outperforms existing training‑free techniques and rivals reward‑fine‑tuned models.