14 papers
Stochastic Heavy Ball with Polyak Step Size and Armijo Line Search: A General Convergence Analysis
Jiawei Zhang, Qitan Shi, Yuantao Gu
Polyak step size (PS) and Armijo line search (ALS) have received increasing attention in stochastic optimization, with encouraging empirical performance and theoretical guarantees.…
Quantization-Aware Kalman Estimation for Diffusion Sampling
Qitan Shi, Cheng Jin, Jiawei Zhang +1
Quantization offers a practical path to deploying diffusion models with reduced memory and computation, but aggressive compression can cause quantized outputs to deviate substantia…
Manifold-Constrained Noise Optimization for Diverse Diffusion Sampling
Qitan Shi, Cheng Jin, Ziyuan Liu +1
Few-step distilled diffusion models generate high-quality images quickly, but often lose per-prompt diversity, producing near-identical samples across random seeds. Optimizing the…
Distilling Drifting Transformers with Representation Autoencoders
Jiawei Zhang, Mengfei Xia, Gen Li +1
Despite the significant training acceleration and promising performance, Representation Autoencoders (RAEs) are mainly criticized for poor distillation effectiveness. In this work,…
Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
Jiawei Zhang, Ziyuan Liu, Leon Yan +2
The distortion-perception (D-P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between distortion performance and perce…
Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
Musheng Li, Ziying Zhang, Cheng jin +1
Token-based time series large language models (TS-LLMs) have emerged as a promising direction for time series analysis and reasoning. However, prior studies largely overlook the in…
Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models
Cheng Jin, Qitan Shi, Yuantao Gu
Classifier-Free Guidance (CFG) is widely used to improve conditional fidelity in diffusion models, but its impact on sampling dynamics remains poorly understood. Prior studies, oft…
ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
Qitan Shi, Cheng Jin, Jiawei Zhang +1
Diffusion models excel at generating high-quality, diverse images but suffer from training data memorization, raising critical privacy and safety concerns. Data unlearning has emer…
A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Sampler
Cheng Jin, Zhenyu Xiao, Yuantao Gu
Diffusion models deliver state-of-the-art generative performance across diverse modalities but remain computationally expensive due to their inherently iterative sampling process.…
Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation
Cheng Jin, Zhenyu Xiao, Chutao Liu +1
Classifier-free guidance (CFG) has emerged as a pivotal advancement in text-to-image latent diffusion models, establishing itself as a cornerstone technique for achieving high-qual…
MCD: A Unified MultiModal Framework for Optical-SAR Change Detection with Mixture of Experts and Self-Distillation
Ziyuan Liu, Jiawei Zhang, Wenyu Wang +1
Most existing change detection (CD) methods focus on optical images captured at different times, and deep learning (DL) has achieved remarkable success in this domain. However, in…
Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation
Jiawei Zhang, Ziyuan Liu, Leon Yan +2
Diffusion-based inverse algorithms have shown remarkable performance across various inverse problems, yet their reliance on numerous denoising steps incurs high computational costs…
JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework
Ziyuan Liu, Ruifei Zhu, Long Gao +3
Change detection (CD) in remote sensing images plays a vital role in Earth observation. However, the scarcity of high-resolution, comprehensive open-source datasets and the difficu…
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
Jiawei Zhang, Jiaxin Zhuang, Cheng Jin +2
The recent emergence of diffusion models has significantly advanced the precision of learnable priors, presenting innovative avenues for addressing inverse problems. Since inverse…