arXiv:2607.08041v1 Announce Type: new Abstract: How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introdu…
arXiv cs.AI
TIER_1English(EN)·Jinkyu Kim, Jinyoung Choi, Bohyung Han·
arXiv:2607.06609v1 Announce Type: cross Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep schedules and classifier-free guidance (CFG) weights. Our work is motivated by a …
How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information r…
arXiv cs.AI
TIER_1English(EN)·Mansi, Avinash Kori, Francesco Leofante·
arXiv:2607.03397v1 Announce Type: new Abstract: Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene only at the text encoder or provide inference-time guidance, often leading to gene…
Flash-BoN improves text-to-image generation efficiency by using inexpensive draft candidates generated through timestep truncation, layer skipping, and activation proxies, followed by multi-stage verification that outperforms existing methods under fixed wall-clock budgets.
arXiv:2607.08757v1 Announce Type: new Abstract: Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory. We show that small forward-marginal error does not guarantee numerical s…
arXiv:2607.07967v1 Announce Type: new Abstract: Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action distributions as terminal laws of diffusion processes with parameterized drifts. T…
Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory. We show that small forward-marginal error does not guarantee numerical stability. We construct a single smooth score fie…
arXiv stat.ML
TIER_1English(EN)·Jonas Arruda, Niels Bracher, Ullrich K\"othe, Jan Hasenauer, Stefan T. Radev·
arXiv:2512.20685v3 Announce Type: replace Abstract: Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-based formulation offers a fl…
arXiv:2601.20498v2 Announce Type: replace-cross Abstract: Diffusion models provide a principled framework for generative modeling via stochastic differential equations and time-reversed dynamics. However, extension of spectral diffusion approaches to spherical data raises nontriv…
Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action distributions as terminal laws of diffusion processes with parameterized drifts. This terminal-law representation has shown substa…
arXiv cs.CV
TIER_1English(EN)·Yu Zhe, Yang Jiayan, Wei Junhao, Yu-Lin Tsai, Wang Chen·
arXiv:2605.10439v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter updates. However, LoRAs can memorize training i…
arXiv:2607.04442v1 Announce Type: new Abstract: Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution. Their training and evaluation primarily rely on an Evidence Lower Bound (ELBO), which relates the Kullback-Leibler…
arXiv:2607.03256v1 Announce Type: new Abstract: Few-step distilled diffusion students cut text-to-image inference from ~50 to 1-8 network evaluations, but the quality gap is usually summarised by a single FID/CLIP scalar that cannot say which axis of the conditioning response cha…
arXiv stat.ML
TIER_1English(EN)·Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan·
arXiv:2602.02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed. We trace this consistency to a simple linear effect: the shared Gaussian …
arXiv:2506.20294v5 Announce Type: replace Abstract: Diffusion models generate conditional samples by progressively denoising Gaussian noise, yet the denoising trajectory can stall at visually plausible but low-quality outcomes with conditional misalignment or structural artifacts…
arXiv:2607.04461v1 Announce Type: new Abstract: Inference-time scaling for text-to-image generation has progressed from simple Best-of-$N$ (BoN) sampling to guided search methods that verify and steer candidate trajectories at intermediate denoising steps. These approaches focus …
Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution. Their training and evaluation primarily rely on an Evidence Lower Bound (ELBO), which relates the Kullback-Leibler (KL) divergence of model samples to the score m…
<p>You've probably seen the benchmarks — 4x faster, 6x more mistakes, 273-vote threads on r/LocalLLaMA. DiffusionGemma is the most interesting image generation model to land this year. But actually running it outside of a HuggingFace notebook is a different story.</p> <p>Here's t…
