Related papers: Adaptive Diffusion Guidance via Stochastic Optimal Control

Related papers

INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning [61.60016491769943]
In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding.<n>We propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI) with a stage-wise preference training strategy.<n>Experiments across multiple model scales and families demonstrate consistent improvements, even surpassing larger open-source models.
arXiv Detail & Related papers (2026-08-27T03:24:03Z)
Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows [24.177502329901817]
We propose LyaGuide, a unified Lyapunov-guided framework that formulates flow guidance as a Lyapunov control problem.<n>Our main theoretical result establishes an equivalence between guided flow matching and Lyapunov control, thereby unifying common guidance strategies.<n>LyaGuide is compatible with existing guidance methods, introduces minimal additional computational overhead, and is straightforward to integrate in practice.
arXiv Detail & Related papers (2026-07-15T18:28:08Z)
D2PO: Optimizing Diffusion Samplers via Dynamic Preference [55.530862428116244]
D2PO is a principled framework for optimizing diffusion sampling policies.<n>We introduce dynamic preferences, where the preferred samples used for alignment progressively improve.<n>Experiments demonstrate that D2PO aligns diffusion samplers with perceptual quality more faithfully.
arXiv Detail & Related papers (2026-07-07T06:05:42Z)
Inference-Time Attribute Distribution Alignment for Unconditional Diffusion [54.28942858023809]
We formalize the inference-time attribute distributional alignment problem for pretrained unconditional diffusion models.<n>To address this, we cast inference-time attribute distributional alignment as an optimal control problem over the reverse diffusion process.<n>We solve for the perturbations using an optimal-control-based algorithm to optimize a differentiable distribution-matching objective.
arXiv Detail & Related papers (2026-05-08T09:02:47Z)
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline [7.967038299436285]
We propose a deterministic adjoint matching framework that formulates human preference alignment for flow-based generative models.<n>Building on this perspective, we introduce a truncated adjoint scheme that focuses on the terminal portion of the trajectory.<n>We further generalize the framework beyond standard KL-based regularization, allowing more flexible trade-offs between alignment strength and distributional preservation.
arXiv Detail & Related papers (2026-05-07T17:12:47Z)
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis [25.481226578749418]
We provide a rigorous theoretical analysis of the inherent dynamics of free guidance.<n>We show that C$2$FG is effective and broadly applicable across diverse generative tasks.
arXiv Detail & Related papers (2026-03-09T09:37:17Z)
Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
arXiv Detail & Related papers (2026-02-01T12:56:10Z)
Solving Inverse Problems with Flow-based Models via Model Predictive Control [41.551726534223704]
MPC-Flow is a model predictive control framework that formulates inverse problem solving with flow-based generative models as a sequence of control sub-problems.<n>We show how different algorithmic choices yield a spectrum of guidance algorithms, including regimes that avoid backpropagation through the generative model trajectory.
arXiv Detail & Related papers (2026-01-30T17:59:09Z)
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models [64.92045568376705]
Coherent Contextual Decoding (CCD) is a novel inference framework built upon two core innovations.<n>CCD employs a trajectory rectification mechanism that leverages historical context to enhance sequence coherence.<n>Instead of rigid allocations based on diffusion steps, we introduce an adaptive sampling strategy that dynamically adjusts the unmasking budget for each step.
arXiv Detail & Related papers (2025-11-26T09:49:48Z)
An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient Boosting and Fuzzy Rule-Based Models [59.13182819190547]
Fuzzy rule-based models excel in interpretability and have seen widespread application across diverse fields.<n>They face challenges such as complex design specifications and scalability issues with large datasets.<n>This paper proposes an Integrated Fusion Framework that merges the strengths of both paradigms to enhance model performance and interpretability.
arXiv Detail & Related papers (2025-11-11T10:28:23Z)
Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity [35.95129874095729]
Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-subject descriptions.<n>We introduce the first theoretical framework with principled optimizable objective for steering sampling dynamics toward multi-subject fidelity.
arXiv Detail & Related papers (2025-10-02T17:59:58Z)
RAAG: Ratio Aware Adaptive Guidance [7.2455669888408085]
We show that the earliest reverse steps are acutely sensitive to the guidance scale, owing to a pronounced spike in the relative strength (RATIO) of conditional to unconditional predictions.<n>We propose a simple, theoretically grounded, RATIO-aware adaptive guidance schedule that automatically dampens the guidance scale at early steps based on the evolving RATIO.<n>Our approach enables up to 3x faster sampling while maintaining or improving generation quality, robustness, and semantic alignment.
arXiv Detail & Related papers (2025-08-05T13:41:05Z)
LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization [48.91511514636768]
We present Length-Adaptive Policy Optimization (LAPO), a framework that transforms reasoning length control from an external constraint into an intrinsic model capability.<n>LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process.<n> Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9% while improving accuracy by 2.3%.
arXiv Detail & Related papers (2025-07-21T16:14:41Z)
Navigating Sparse Molecular Data with Stein Diffusion Guidance [48.21071466968102]
optimal control (SOC) has emerged as a principled framework for fine-tuning diffusion models.<n>A class of training-free approaches has been developed that guides diffusion models using off-the-shelf classifiers on predicted clean samples.<n>We propose a novel training-free guidance framework based on a surrogate optimal control objective.
arXiv Detail & Related papers (2025-07-07T21:14:27Z)
How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models [57.42800112251644]
We propose Step AG, which is a simple, universally applicable adaptive guidance strategy.<n>Our evaluations focus on both image quality and image-text alignment.
arXiv Detail & Related papers (2025-06-10T02:09:48Z)
Feedback Guidance of Diffusion Models [0.0]
Interval-Free Guidance (CFG) has become standard for improving sample fidelity in conditional diffusion models.<n>We propose FeedBack Guidance (FBG), which uses a state-dependent coefficient to self-regulate guidance amounts based on need.
arXiv Detail & Related papers (2025-06-06T13:46:32Z)
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws [52.10468229008941]
This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting.<n>We provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model.<n>Building on these insights, we introduce a novel method for Contrastive Language-Image Pretraining with a reference model, termed DRRho-CLIP.
arXiv Detail & Related papers (2025-05-10T16:55:03Z)
On-the-fly Preference Alignment via Principle-Guided Decoding [27.50204023448716]
We introduce On-the-fly Preference Alignment via Principle-Guided Decoding (OPAD) to align model outputs with human preferences during inference.<n>OPAD achieves competitive or superior performance in both general and personalized alignment tasks.
arXiv Detail & Related papers (2025-02-20T02:23:09Z)
REG: Rectified Gradient Guidance for Conditional Diffusion Models [16.275782069986253]
We propose rectified gradient guidance (REG) to boost the performance of existing guidance methods.<n>REG provides a better approximation to the optimal solution than prior guidance techniques.<n>In experiments on class-conditional ImageNet and text-to-image generation tasks, REG consistently improves FID and Inception/CLIP scores.
arXiv Detail & Related papers (2025-01-31T03:16:18Z)
Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence [11.400431211239958]
Diffusion models have emerged as powerful tools for generative modeling.<n>We propose a control framework for fine-tuning diffusion models.<n>We show that PI-FT achieves global convergence at a linear rate.
arXiv Detail & Related papers (2024-12-24T04:55:46Z)
Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
arXiv Detail & Related papers (2024-05-09T12:52:22Z)
Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach [3.453622106101339]
We propose a framework towards achieving two intertwined objectives: (i) equipping reinforcement learning with active exploration and deliberate information gathering, and (ii) overcoming the computational intractability of optimal control law. We approach both objectives by using reinforcement learning to compute the optimal control law. Unlike fixed exploration and exploitation balance, caution and probing are employed automatically by the controller in real-time, even after the learning process is terminated.
arXiv Detail & Related papers (2023-09-18T18:05:35Z)
Learning to Optimize with Stochastic Dominance Constraints [103.26714928625582]
In this paper, we develop a simple yet efficient approach for the problem of comparing uncertain quantities. We recast inner optimization in the Lagrangian as a learning problem for surrogate approximation, which bypasses apparent intractability. The proposed light-SD demonstrates superior performance on several representative problems ranging from finance to supply chain management.
arXiv Detail & Related papers (2022-11-14T21:54:31Z)
Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
arXiv Detail & Related papers (2020-07-14T21:10:16Z)
Control as Hybrid Inference [62.997667081978825]
We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
arXiv Detail & Related papers (2020-07-11T19:44:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.