arXiv AI July 13, 2026 By Yiting Wang, Jingyi Zhang, Wenhu Zhang, Ke Chao, Yves Liang, Kun Cheng, Kang Zhao

IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation

arXiv:2607. 09133v1 Announce Type: cross Abstract: While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs severe inference latency.

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 AI.

arXiv AI

Jun 30

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

arXiv:2603. 22282v2 Announce Type: replace-cross Abstract: We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture.

By Ziyi Wang, Xinshun Wang, Shuang Chen, Yang Cong, Mengyuan Liu

llms nlp efficiency multimodal benchmarks safety

arXiv Computer Vision

Sep 1

Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model

arXiv:2608.29904v1 Announce Type: new Abstract: Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-...

By Hai Nguyen-Truong, Tuan-Anh Vu, Dang Huynh

rag

arXiv AI

Jul 9

Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

arXiv:2607. 06631v1 Announce Type: cross Abstract: Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs.

By Yu Cheng, Siyue Yao, Zhongang Qi, Shanyan Guan, Wei Li, Fajie Yuan

diffusion efficiency

arXiv AI

Aug 3

MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation

arXiv:2607. 29180v1 Announce Type: cross Abstract: Text-to-motion generation must produce motions that are semantically correct, temporally coherent, and physically plausible.

By Yifei Zhu, Mingyi Shi, Yangyang Cai, Miao Cheng, Yoshifumi Kitamura, Taku Komura

diffusion benchmarks

arXiv Machine Learning

Jun 30

Momentum Guidance: Plug-and-Play Guidance for Flow Models

arXiv:2602. 20360v2 Announce Type: replace Abstract: Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in image generation, samples without guidance often appear diffuse and lack fine-grained detail.

By Runlong Liao, Jian Yu, Baiyu Su, Chi Zhang, Lizhang Chen, Qiang Liu

diffusion benchmarks

arXiv Computer Vision

Aug 25

Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution

arXiv:2604.24136v3 Announce Type: replace Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohi...

By Shyang-En Weng, Yi-Cheng Liao, Yu-Syuan Xu, Chia-Hung Yuan, Wei-Chen Chiu, Ching-Chun Huang

diffusion fine-tuning benchmarks

One email a morning, machine-written

Related stories

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model

Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation

Momentum Guidance: Plug-and-Play Guidance for Flow Models

Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution