arXiv:2606. 20076v1 Announce Type: cross Abstract: Latent Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio.
arXiv:2608.24293v1 Announce Type: new Abstract: Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with varia...
arXiv:2608. 01298v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks.
arXiv:2608.29281v1 Announce Type: new Abstract: Natural images concentrate their detail in a small fraction of the frame, yet diffusion models spend a full token on every patch, in every layer and at...
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing.
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas th...
arXiv:2607. 19064v1 Announce Type: cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy.
arXiv:2609.35232v2 Announce Type: replace-cross Abstract: Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pr...
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...
arXiv:2508. 10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm.
arXiv:2505. 18227v4 Announce Type: replace-cross Abstract: In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks.
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
The paper introduces SVDtrunc, a two‑step block‑level compression method for Diffusion Transformers (DiTs) that allocates ranks across blocks, applies truncated SVD to the least important ones, and then fine‑tunes all blocks with modular knowledge distillation and a rectified‑flow objective. Experiments on FLUX.dev show that SVDtrunc achieves near‑full performance at 68% of the original parameters and remains competitive even at 57%, outperforming all competing approaches on GenEval, HPSv2, and DPG benchmarks. The method also works well without fine‑tuning, complementing step distillation and offering a practical path to efficient large‑scale generative models.