New research explores diffusion models, bias mitigation, and reinforcement learning applications · 10 sources…
ByPulseAugur Editorial·[19 sources]·
Recent research explores advancements in diffusion models, focusing on theoretical underpinnings, optimization techniques, and bias mitigation. One paper introduces Bayesian Information Restricted Diffusion (BIRD) models to explain how diffusion models generalize by restricting information, identifying a phase boundary between memorization and generalization. Another work, D2PO, optimizes diffusion samplers using dynamic preference learning, improving perceptual quality and outperforming regression-based methods. Additionally, a new approach called CO-ALIGN uses concept-graph alignment to reduce bias in text-to-image models while maintaining generative integrity. Other research investigates numerical stability in diffusion sampling and the expressivity trade-offs in diffusion policy learning for reinforcement learning.
AI
IMPACT
These papers advance the theoretical understanding and practical application of diffusion models, potentially leading to more efficient, stable, and less biased generative AI systems.
RANK_REASON
Cluster consists of multiple academic papers published on arXiv, detailing theoretical advancements and new methodologies in diffusion models.
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…
