The paper investigates how diffusion transformers (DiTs) denoise images by framing them as aggregator–predictor models that use context aggregation and patch prediction. It shows that for Gaussian Markov random field priors, a global Bayes denoiser can be approximated with a limited context, and that patchwise linear denoisers recover empirical local denoisers when aggregation is informative. Experiments confirm that DiTs trained on real images exhibit noise‑dependent denoising contexts and that replacing DiT MLPs with shared‑memory patch predictors yields competitive performance, while cross‑dataset component transplantation supports the proposed functional roles of attention and MLPs.
arXiv:2608.30720v1 Announce Type: new Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied...
The paper introduces a transformer-based framework that learns an in‑context score operator for diffusion models, allowing the model to perform reverse‑diffusion sampling on unseen target distributions specified by a small empirical context set. By representing the task‑dependent score as a Gaussian‑kernel conditional mean and approximating it with a transformer‑based query‑dependent attention architecture, the method can adapt to new tasks without retraining or parameter updates. The authors provide theoretical generalization‑error bounds and evaluate the approach on scientific and visual datasets, noting strong performance on simple task families and limitations as task complexity grows.
arXiv:2603.17825v2 Announce Type: replace Abstract: In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in vi...
arXiv:2601. 11641v3 Announce Type: replace-cross Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment.
arXiv:2607. 15693v1 Announce Type: cross Abstract: We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters.
arXiv:2609.40305v1 Announce Type: new Abstract: Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternat...
The paper investigates how variational autoencoders (VAEs) can be made more learnable in latent diffusion by analyzing diffusability through spectral properties. It introduces the Spectrum Matching Hypothesis, which posits that latents with better diffusability should have a flattened power‑law power spectral density (Encoding Spectrum Matching) and preserve frequency‑to‑frequency semantic correspondence via the decoder (Decoding Spectrum Matching). The authors implement these ideas by matching PSDs between images and latents and applying shared spectral masking, demonstrating improved diffusion generation on CelebA and ImageNet and extending the approach to representation alignment with a DoG‑based method.
arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.
ORCA (Orthogonal Residual Compositional Alignment) is a method that improves text-to-image diffusion models by aligning the diffusion transformer’s latent space with a low‑rank target derived from a frozen visual encoder. It introduces an auxiliary loss that uses a predictor with an orthogonal basis parameterised by a learned residual between T5 and CLIP embeddings, providing a prompt‑dependent signal for selecting the visual readout subspace. Experiments on three diffusion‑transformer backbones show that ORCA improves FID and GenEval scores, especially on attribute binding, spatial relations, and multi‑object prompts, without adding inference‑time cost.
arXiv:2608.14740v2 Announce Type: replace Abstract: Unified image and video creation requires a model to follow diverse instructions while preserving identity, geometry, and temporal structure from v...
V-Co investigates visual co-denoising for pixel-space diffusion models, using a unified JiT-based framework to isolate key design choices. The study identifies two essential components: a dual-stream architecture with flexible cross-stream interaction and a perceptual-drifting hybrid loss combined with RMS-based feature rescaling for stronger semantic supervision. Experiments on ImageNet-256 demonstrate that V-Co surpasses baseline pixel-space diffusion and strong prior pixel-diffusion methods at comparable model sizes while requiring fewer training epochs.
arXiv:2608. 03025v3 Announce Type: replace Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual evidence.