arXiv AI
Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 2
Improving Visual Representation Alignment Generation with GRPO
arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.
arXiv Computer Vision
Aug 26
AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer
arXiv:2608.23864v1 Announce Type: new Abstract: Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be or...
Hugging Face Trending Papers
Jul 2
From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself.
arXiv AI
Jun 16
Improved Baselines with Representation Autoencoders
arXiv:2605. 18324v2 Announce Type: replace-cross Abstract: Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders.
arXiv Computer Vision
Sep 10
Let ViT Speak: Generative Language-Image Pre-training
arXiv:2605.00809v3 Announce Type: replace Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining...
arXiv Computer Vision
Sep 14
Semantically Aligned Gradient-Driven Context-Preserving Image Editing
Semantically Aligned Gradient-Driven Context-Preserving Image Editing (IABEdit) is a model‑agnostic framework that embeds differentiable semantic verification into the training of generative image editors. By using a frozen vision‑language model to extract spatially‑aware descriptors from ground‑truth edits and a trainable aligner to reproduce them from generated outputs, the residual becomes a gradient that teaches the generator both what to edit and where, without adding inference‑time VLM cost. IABEdit is compatible with various backbones (e.g., U‑Net in Stable Diffusion and MMDiT in FLUX) and improves structural fidelity on MagicBrush, achieves state‑of‑the‑art instruction adherence on RealEdit and EMU Edit, and outperforms the proprietary Gemini agent on the D‑LORD surveillance benchmark under heavy occlusion. "whyItMatters":"IABEdit demonstrates that incorporating semantic verification during training can produce more accurate, well‑localized edits and outperform existing methods even in challenging surveillance scenarios, as shown by its superior metrics and human/GPT‑4o evaluations."