arXiv subjects

Mingyuan Zhou

Publications and source records attributed to Mingyuan Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2025

Score Distillation of Flow Matching Models

Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a distinct framework, has since been shown to be theoretically equivalent to diffusion under Gaussian assumptions, raising the question of whether distillation techniques such as score distillation transfer directly. We provide a simple derivation -- based on Bayes' rule and conditional expectations -- that unifies Gaussian diffusion and flow matching without relying on ODE/SDE formulations. Building on this view, we extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models, including SANA, SD3-Medium, SD3.5-Medium/Large, and FLUX.1-dev, all with DiT backbones. Experiments show that, with only modest flow-matching- and DiT-specific adjustments, SiD works out of the box across these models, in both data-free and data-aided settings, without requiring teacher finetuning or architectural changes. This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models, resolving prior concerns about stability and soundness and unifying acceleration techniques across diffusion- and flow-based generators. A project page is available at https://yigu1008.github.io/SiD-DiT.

cs.CV↗

arXiv2025

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs during inference. Unlike prior methods that denoise future frames based on ground-truth context frames, Self Forcing conditions each frame's generation on previously self-generated outputs by performing autoregressive rollout with key-value (KV) caching during training. This strategy enables supervision through a holistic loss at the video level that directly evaluates the quality of the entire generated sequence, rather than relying solely on traditional frame-wise objectives. To ensure training efficiency, we employ a few-step diffusion model along with a stochastic gradient truncation strategy, effectively balancing computational cost and performance. We further introduce a rolling KV cache mechanism that enables efficient autoregressive video extrapolation. Extensive experiments demonstrate that our approach achieves real-time streaming video generation with sub-second latency on a single GPU, while matching or even surpassing the generation quality of significantly slower and non-causal diffusion models. Project website: http://self-forcing.github.io/

cs.CV↗

arXiv2025

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps. We introduce Continuously Augmented Discrete Diffusion (CADD), a framework that augments the discrete state space with a paired diffusion in a continuous latent space. This yields graded, gradually corrupted states in which masked tokens are represented by noisy yet informative latent vectors rather than collapsed 'information voids'. At each reverse step, CADD may leverage the continuous latent as a semantic hint to guide discrete denoising. The design is clean and compatible with existing discrete diffusion training. At sampling time, the strength and choice of estimator for the continuous latent vector enables a controlled trade-off between mode-coverage (generating diverse outputs) and mode-seeking (generating contextually precise outputs) behaviors. Empirically, we demonstrate CADD improves generative quality over mask-based diffusion across text generation, image synthesis, and code modeling, with consistent gains on both qualitative and quantitative metrics against strong discrete baselines.

stat.ML↗

arXiv2025

Generative Model Inversion Through the Lens of the Manifold Hypothesis

Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models. Recent generative MIAs utilize generative adversarial networks to learn image priors that guide the inversion process, yielding reconstructions with high visual quality and strong fidelity to the private training data. To explore the reason behind their effectiveness, we begin by examining the gradients of inversion loss with respect to synthetic inputs, and find that these gradients are surprisingly noisy. Further analysis reveals that generative inversion implicitly denoises these gradients by projecting them onto the tangent space of the generator manifold, filtering out off-manifold components while preserving informative directions aligned with the manifold. Our empirical measurements show that, in models trained with standard supervision, loss gradients often exhibit large angular deviations from the data manifold, indicating poor alignment with class-relevant directions. This observation motivates our central hypothesis: models become more vulnerable to MIAs when their loss gradients align more closely with the generator manifold. We validate this hypothesis by designing a novel training objective that explicitly promotes such alignment. Building on this insight, we further introduce a training-free approach to enhance gradient-manifold alignment during inversion, leading to consistent improvements over state-of-the-art generative MIAs.

cs.LG↗

arXiv2025

KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing code-focused resources typically fail to ensure either the breadth of coverage (e.g., spanning simple coding tasks to advanced algorithmic problems) or verifiable correctness (e.g., unit tests). In contrast, KodCode comprises question-solution-test triplets that are systematically validated via a self-verification procedure. Our pipeline begins by synthesizing a broad range of coding questions, then generates solutions and test cases with additional attempts allocated to challenging problems. Finally, post-training data synthesis is done by rewriting questions into diverse formats and generating responses under a test-based reject sampling procedure from a reasoning model (DeepSeek R1). This pipeline yields a large-scale, robust and diverse coding dataset. KodCode is suitable for supervised fine-tuning and the paired unit tests also provide great potential for RL tuning. Fine-tuning experiments on coding benchmarks (HumanEval(+), MBPP(+), BigCodeBench, and LiveCodeBench) demonstrate that KodCode-tuned models achieve state-of-the-art performance, surpassing models like Qwen2.5-Coder-32B-Instruct and DeepSeek-R1-Distill-Llama-70B.

cs.LG↗

arXiv2025

Controllable diffusion-based generation for multi-channel biological data

Spatial profiling technologies in biology, such as imaging mass cytometry (IMC) and spatial transcriptomics (ST), generate high-dimensional, multi-channel data with strong spatial alignment and complex inter-channel relationships. Generative modeling of such data requires jointly capturing intra- and inter-channel structure, while also generalizing across arbitrary combinations of observed and missing channels for practical application. Existing diffusion-based models generally assume low-dimensional inputs (e.g., RGB images) and rely on simple conditioning mechanisms that break spatial correspondence and ignore inter-channel dependencies. This work proposes a unified diffusion framework for controllable generation over structured and spatial biological data. Our model contains two key innovations: (1) a hierarchical feature injection mechanism that enables multi-resolution conditioning on spatially aligned channels, and (2) a combination of latent-space and output-space channel-wise attention to capture inter-channel relationships. To support flexible conditioning and generalization to arbitrary subsets of observed channels, we train the model using a random masking strategy, enabling it to reconstruct missing channels from any combination of inputs. We demonstrate state-of-the-art performance across both spatial and non-spatial prediction tasks, including protein imputation in IMC and gene-to-protein prediction in single-cell datasets, and show strong generalization to unseen conditional configurations.

cs.LG↗

arXiv2025

Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach

We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying shape. The main idea is to combine a contrastive loss between the resulting latent representations with an additional reconstruction loss. That helps to avoid collapsing the latent representations as a trivial solution for minimizing the contrastive loss. A novel dynamic switching approach is used to cross-train two encoders with a shared decoder. The switching approach also enables the stop gradient operation on a random branch. Further classification experiments show that the latent representations learned with our self-supervised method integrate more useful information from the additional input data implicitly, thus leading to better reconstruction and classification performance.

cs.CV↗

arXiv2025

Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer

Although deep neural networks have demonstrated significant success due to their powerful expressiveness, most models struggle to meet practical requirements for uncertainty estimation. Concurrently, the entangled nature of deep neural networks leads to a multifaceted problem, where various localized explanation techniques reveal that multiple unrelated features influence the decisions, thereby undermining interpretability. To address these challenges, we develop a Bayesian Non-negative Decision Layer (BNDL), which reformulates deep neural networks as a conditional Bayesian non-negative factor analysis. By leveraging stochastic latent variables, the BNDL can model complex dependencies and provide robust uncertainty estimation. Moreover, the sparsity and non-negativity of the latent variables encourage the model to learn disentangled representations and decision layers, thereby improving interpretability. We also offer theoretical guarantees that BNDL can achieve effective disentangled learning. In addition, we developed a corresponding variational inference method utilizing a Weibull variational inference network to approximate the posterior distribution of the latent variables. Our experimental results demonstrate that with enhanced disentanglement capabilities, BNDL not only improves the model's accuracy but also provides reliable uncertainty estimation and improved interpretability.

cs.LG↗

arXiv2025

Mechanical in-sensor computing: a programmable meta-sensor for structural damage classification without external electronic power

Structural health monitoring (SHM) involves sensor deployment, data acquisition, and data interpretation, commonly implemented via a tedious wired system. The information processing in current practice majorly depends on electronic computers, albeit with universal applications, delivering challenges such as high energy consumption and low throughput due to the nature of digital units. In recent years, there has been a renaissance interest in shifting computations from electronic computing units to the use of real physical systems, a concept known as physical computation. This approach provides the possibility of thinking out of the box for SHM, seamlessly integrating sensing and computing into a pure-physical entity, without relying on external electronic power supplies, thereby properly coping with resource-restricted scenarios. The latest advances of metamaterials (MM) hold great promise for this proactive idea. In this paper, we introduce a programmable metamaterial-based sensor (termed as MM-sensor) for physically processing structural vibration information to perform specific SHM tasks, such as structural damage warning (binary classification) in this initiation, without the need for further information processing or resource-consuming, that is, the data collection and analysis are completed in-situ at the sensor level. We adopt the configuration of a locally resonant metamaterial plate (LRMP) to achieve the first fabrication of the MM-sensor. We take advantage of the bandgap properties of LRMP to physically differentiate the dynamic behavior of structures before and after damage. By inversely designing the geometric parameters, our current approach allows for adjustments to the bandgap features. This is effective for engineering systems with a first natural frequency ranging from 9.54 Hz to 81.86 Hz.

cs.LG↗

arXiv2025

InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO

Recent advances in text-to-video generation, particularly with autoregressive models, have enabled the synthesis of high-quality videos depicting individual scenes. However, extending these models to generate long, cross-scene videos remains a significant challenge. As the context length grows during autoregressive decoding, computational costs rise sharply, and the model's ability to maintain consistency and adhere to evolving textual prompts deteriorates. We introduce InfLVG, an inference-time framework that enables coherent long video generation without requiring additional long-form video data. InfLVG leverages a learnable context selection policy, optimized via Group Relative Policy Optimization (GRPO), to dynamically identify and retain the most semantically relevant context throughout the generation process. Instead of accumulating the entire generation history, the policy ranks and selects the top-$K$ most contextually relevant tokens, allowing the model to maintain a fixed computational budget while preserving content consistency and prompt alignment. To optimize the policy, we design a hybrid reward function that jointly captures semantic alignment, cross-scene consistency, and artifact reduction. To benchmark performance, we introduce the Cross-scene Video Benchmark (CsVBench) along with an Event Prompt Set (EPS) that simulates complex multi-scene transitions involving shared subjects and varied actions/backgrounds. Experimental results show that InfLVG can extend video length by up to 9$\times$, achieving strong consistency and semantic fidelity across scenes. Our code is available at https://github.com/MAPLE-AIGC/InfLVG.

cs.CV↗

arXiv2025

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation

Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn meaningful distributions from corrupted samples. This limitation restricts their applicability in scientific domains where clean data is scarce or costly to obtain. In this work, we introduce denoising score distillation (DSD), a surprisingly effective and novel approach for training high-quality generative models from low-quality data. DSD first pretrains a diffusion model exclusively on noisy, corrupted samples and then distills it into a one-step generator capable of producing refined, clean outputs. While score distillation is traditionally viewed as a method to accelerate diffusion models, we show that it can also significantly enhance sample quality, particularly when starting from a degraded teacher model. Across varying noise levels and datasets, DSD consistently improves generative performancewe summarize our empirical evidence in Fig. 1. Furthermore, we provide theoretical insights showing that, in a linear model setting, DSD identifies the eigenspace of the clean data distributions covariance matrix, implicitly regularizing the generator. This perspective reframes score distillation as not only a tool for efficiency but also a mechanism for improving generative models, particularly in low-quality data settings.

cs.LG↗

arXiv2025

Few-Step Diffusion via Score identity Distillation

Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models by distilling a pretrained score network into a one- or few-step generator. While existing methods have made notable progress, they often rely on real or teacher-synthesized images to perform well when distilling high-resolution T2I diffusion models such as Stable Diffusion XL (SDXL), and their use of classifier-free guidance (CFG) introduces a persistent trade-off between text-image alignment and generation diversity. We address these challenges by optimizing Score identity Distillation (SiD) -- a data-free, one-step distillation framework -- for few-step generation. Backed by theoretical analysis that justifies matching a uniform mixture of outputs from all generation steps to the data distribution, our few-step distillation algorithm avoids step-specific networks and integrates seamlessly into existing pipelines, achieving state-of-the-art performance on SDXL at 1024x1024 resolution. To mitigate the alignment-diversity trade-off when real text-image pairs are available, we introduce a Diffusion GAN-based adversarial loss applied to the uniform mixture and propose two new guidance strategies: Zero-CFG, which disables CFG in the teacher and removes text conditioning in the fake score network, and Anti-CFG, which applies negative CFG in the fake score network. This flexible setup improves diversity without sacrificing alignment. Comprehensive experiments on SD1.5 and SDXL demonstrate state-of-the-art performance in both one-step and few-step generation settings, along with robustness to the absence of real images. Our efficient PyTorch implementation, along with the resulting one- and few-step distilled generators, will be released publicly as a separate branch at https://github.com/mingyuanzhou/SiD-LSG.

cs.CV↗

arXiv2025

A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation

Estimating individualized treatment effects from observational data is a central challenge in causal inference, largely due to covariate imbalance and confounding bias from non-randomized treatment assignment. While inverse probability weighting (IPW) is a well-established solution to this problem, its integration into modern deep learning frameworks remains limited. In this work, we propose Importance-Weighted Diffusion Distillation (IWDD), a novel generative framework that combines the pretraining of diffusion models with importance-weighted score distillation to enable accurate and fast causal estimation-including potential outcome prediction and treatment effect estimation. We demonstrate how IPW can be naturally incorporated into the distillation of pretrained diffusion models, and further introduce a randomization-based adjustment that eliminates the need to compute IPW explicitly-thereby simplifying computation and, more importantly, provably reducing the variance of gradient estimates. Empirical results show that IWDD achieves state-of-the-art out-of-sample prediction performance, with the highest win rates compared to other baselines, significantly improving causal estimation and supporting the development of individualized treatment strategies. We will release our PyTorch code for reproducibility and future research.

cs.LG↗

arXiv2025

Parameter estimation of structural dynamics with neural operators enabled surrogate modeling

Parameter estimation in structural dynamics generally involves inferring the values of physical, geometric, or even customized parameters based on first principles or expert knowledge, which is challenging for complex structural systems. In this work, we present a unified deep learning-based framework for parameterization, forward modeling, and inverse modeling of structural dynamics. The parameterization is flexible and can be user-defined, including physical and/or non-physical (customized) parameters. In the forward modeling, we train a neural operator for response prediction -- forming a surrogate model, which leverages the defined system parameters and excitation forces as inputs to the model. The inverse modeling focuses on estimating system parameters. In particular, the learned forward surrogate model (which is differentiable) is utilized for preliminary parameter estimation via gradient-based optimization; to further boost the parameter estimation, we introduce a neural refinement method to mitigate ill-posed problems, which often occur in the former. The framework's effectiveness is verified numerically and experimentally, in both interpolation and extrapolation cases, indicating its capability to capture intrinsic dynamics of structural systems from both forward and inverse perspectives. Moreover, the framework's flexibility is expected to support a wide range of applications, including surrogate modeling, structural identification, damage detection, and inverse design of structural systems.

cs.CE↗

arXiv2025

FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors

Federated Learning (FL) has emerged as a promising framework for distributed machine learning, enabling collaborative model training without sharing local data, thereby preserving privacy and enhancing security. However, data heterogeneity resulting from differences across user behaviors, preferences, and device characteristics poses a significant challenge for federated learning. Most previous works overlook the adjustment of aggregation weights, relying solely on dataset size for weight assignment, which often leads to unstable convergence and reduced model performance. Recently, several studies have sought to refine aggregation strategies by incorporating dataset characteristics and model alignment. However, adaptively adjusting aggregation weights while ensuring data security-without requiring additional proxy data-remains a significant challenge. In this work, we propose Federated learning with Adaptive Weight Aggregation (FedAWA), a novel method that adaptively adjusts aggregation weights based on client vectors during the learning process. The client vector captures the direction of model updates, reflecting local data variations, and is used to optimize the aggregation weight without requiring additional datasets or violating privacy. By assigning higher aggregation weights to local models whose updates align closely with the global optimization direction, FedAWA enhances the stability and generalization of the global model. Extensive experiments under diverse scenarios demonstrate the superiority of our method, providing a promising solution to the challenges of data heterogeneity in federated learning.

cs.LG↗

arXiv2025

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and trustworthy GenAI models. Traditional MU methods often rely on stringent assumptions and require access to real data. This paper introduces Score Forgetting Distillation (SFD), an innovative MU approach that promotes the forgetting of undesirable information in diffusion models by aligning the conditional scores of "unsafe" classes or concepts with those of "safe" ones. To eliminate the need for real data, our SFD framework incorporates a score-based MU loss into the score distillation objective of a pretrained diffusion model. This serves as a regularization term that preserves desired generation capabilities while enabling the production of synthetic data through a one-step generator. Our experiments on pretrained label-conditional and text-to-image diffusion models demonstrate that our method effectively accelerates the forgetting of target classes or concepts during generation, while preserving the quality of other classes or concepts. This unlearned and distilled diffusion not only pioneers a novel concept in MU but also accelerates the generation speed of diffusion models. Our experiments and studies on a range of diffusion models and datasets confirm that our approach is generalizable, effective, and advantageous for MU in diffusion models. Code is available at https://github.com/tqch/score-forgetting-distillation. ($\textbf{Warning:}$ This paper contains sexually explicit imagery, discussions of pornography, racially-charged terminology, and other content that some readers may find disturbing, distressing, and/or offensive.)

cs.CV↗

arXiv2025

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is their slow sample generation process, which requires iterative refinement through the same network. To overcome this, we introduce a data-free guided distillation method that enables the efficient distillation of pretrained Stable Diffusion models without access to the real training data, often restricted due to legal, privacy, or cost concerns. This method enhances Score identity Distillation (SiD) with Long and Short Classifier-Free Guidance (LSG), an innovative strategy that applies Classifier-Free Guidance (CFG) not only to the evaluation of the pretrained diffusion model but also to the training and evaluation of the fake score network. We optimize a model-based explicit score matching loss using a score-identity-based approximation alongside our proposed guidance strategies for practical computation. By exclusively training with synthetic images generated by its one-step generator, our data-free distillation method rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Notably, the one-step distillation of Stable Diffusion 1.5 achieves an FID of 8.15 on the COCO-2014 validation set, a record low value under the data-free setting. Our code and checkpoints are available at https://github.com/mingyuanzhou/SiD-LSG.

cs.CV↗

arXiv2025

Preference-grounded Token-level Guidance for Language Model Fine-tuning

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the token level. There is, therefore, a granularity mismatch between the preference and the LM training losses, which may complicate the learning problem. In this paper, we address this issue by developing an alternate training process, where we iterate between grounding the sequence-level preference into token-level training guidance, and improving the LM with the learned guidance. For guidance learning, we design a framework that extends the pairwise-preference learning in imitation learning to both variable-length LM generation and the utilization of the preference among multiple generations. For LM training, based on the amount of supervised data, we present two minimalist learning objectives that utilize the learned guidance. In experiments, our method performs competitively on two distinct representative LM tasks -- discrete-prompt generation and text summarization.

cs.CL↗