← Back to all news
arXiv Computer Vision By Juntao Xu, Shihong Li, Hoi Fan Au, Ning Zhu

ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models

Read the original on arXiv Computer Vision →

ToPO (Token-Oriented Preference Optimization) is a method for attention-based latent diffusion models that constructs a per‑minibatch, detached, separable spatial‑temporal route using branchwise squared‑residual contrast from a frozen reference denoiser. It employs preferred‑branch cross‑attention with content tokens to modulate spatial factors and adds an auxiliary pixel‑midpoint ordering term, all without local labels or a learned reward model. In experiments with shared update schedules, ToPO outperforms Diffusion‑DPO on five SD‑1.5 metrics and on HPSv2, ImageReward, and CLIP for SDXL, and achieves higher raw win shares in a blind SDXL A/B study.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 28

Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusion

The paper introduces HetA-DiT, a heterogeneous attention mechanism for video diffusion models that allocates computation based on token difficulty. A lightweight uncertainty branch predicts denoising difficulty, routing uncertain tokens through dense global attention while applying efficient local attention to reliable tokens. This adaptive routing retains global context where needed, offers a single parameter to balance quality and efficiency, and achieves competitive generation quality while only about 20% of tokens use dense attention.

By Olga Zatsarynna, Denis Korzhenkov, Juergen Gall, Amir Habibian, Mohsen Ghafoorian
llmsdiffusionefficiency
More like this →
arXiv Machine Learning
Sep 7

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models

The paper introduces Diffusion LAIR, a listwise preference optimization technique that leverages continuous reward scores instead of binary pairwise comparisons to align text‑to‑image diffusion models. LAIR transforms reward scores into centered advantage weights and optimizes an advantage‑weighted regression objective on an implicit reward defined by denoising‑loss improvement over a reference model, with a quadratic penalty to regulate reward magnitude. Experiments demonstrate that Diffusion LAIR surpasses strong baseline methods on SD1.5 and SDXL across generation, compositional, and editing tasks.

By Austin Wang, Jiaqi Han, Stefano Ermon, Yisong Yue
diffusionreinforcement-learningbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 16

ReState: Noise-Level-Aware State Correction for Training-Free Object Removal in Few-Step Diffusion Models

ReState is a training‑free method for object removal in few‑step diffusion models that corrects the masked clean prediction toward background evidence using a noise‑level‑aware weight that fades out at the final forward pass. It complements attention rerouting, requiring no additional denoiser evaluations, and outperforms existing training‑free techniques on two paired benchmarks and two distilled backbones, improving PSNR by an average of 3.17 dB. On the OBER‑Test set, ReState also surpasses a 50‑step attention‑forcing reference while running 6.7× faster.

By Donghwan Lee, Sanghyun Jo, Sihyun Kim, Ziseok Lee, Kyungsu Kim
diffusionbenchmarks
More like this →