15 papers
MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation
Yunyi Chen, Chenru Wang, Xinyi Ye +2
Diffusion-based dataset distillation (DD) suffers from a fundamental objective mismatch: likelihood-driven diffusion models prioritize density approximation over the discriminative…
BAG: Budget-Aware Gating for Diffusion Caching
Tong Zhao, Mingkun Lei, Yucheng Han +1
Diffusion caching is a lightweight strategy that accelerates Diffusion Transformers (DiTs) by reusing intermediate features across denoising steps, but existing paradigms face a fu…
Budget-Constrained Step-Level Diffusion Caching
Mingkun Lei, Tong Zhao, Liangyu Yuan +1
Step-level caching accelerates diffusion models by exploiting temporal redundancy across denoising steps. Existing methods make per-step cache decisions using threshold-based heuri…
Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
Liangyu Yuan, Yufei Huang, Mingkun Lei +5
Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often…
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation
Jiawei Zhou, Chi Zhang, Xiang Feng +6
We present Omni-I2C, a comprehensive benchmark designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executa…
Few-Step Diffusion Sampling Through Instance-Aware Discretizations
Liangyu Yuan, Ruoyu Wang, Tong Zhao +4
Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Stochastic Differential Equations (ODEs/SDEs), starting from a tractable p…
IMS3: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation
Chenru Wang, Yunyi Chen, Zijun Yang +2
Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing c…
DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
Tong Zhao, Mingkun Lei, Liangyu Yuan +5
Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for h…
CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization
Xiaoman Feng, Mingkun Lei, Yang Wang +2
Style transfer in diffusion models enables controllable visual generation by injecting the style of a reference image. However, recent encoder-based methods, while efficient and tu…
Free Lunch for Stabilizing Rectified Flow Inversion
Chenru Wang, Beier Zhu, Chi Zhang
Rectified-Flow (RF)-based generative models have recently emerged as strong alternatives to traditional diffusion models, demonstrating state-of-the-art performance across various…
Momentum Guidance: Plug-and-Play Guidance for Flow Models
Runlong Liao, Jian Yu, Baiyu Su +3
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…
Parallel Diffusion Solver via Residual Dirichlet Policy Optimization
Ruoyu Wang, Ziyu Li, Beier Zhu +5
Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based a…
Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
Ruoyu Wang, Beier Zhu, Junzhi Li +2
Diffusion-based generative processes, formulated as differential equation solving, frequently balance computational speed with sample quality. Our theoretical investigation of ODE-…
Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models
Beier Zhu, Ruoyu Wang, Tong Zhao +2
Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based a…
Detail++: Training-Free Detail Enhancer for T2I Diffusion Models
Lifeng Chen, Jiner Wang, Zihao Pan +3
Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, parti…