Greed is Good: A Unifying Perspective on Guided Generation

• URL: http://arxiv.org/abs/2502.08006v2
• Date: Mon, 19 May 2025 17:57:30 GMT
• Title: Greed is Good: A Unifying Perspective on Guided Generation
• Authors: Zander W. Blasingame, Chen Liu,
• Abstract summary: Two families of techniques have emerged for solving the problem for gradient-based guidance.<n>We show that these two seemingly separate families can actually be unified by looking at posterior guidance.<n>We then show a method for interpolating between these two families enabling a trade-off between compute and accuracy of the guidance gradients.
• Score: 2.0795007613453445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training-free guided generation is a widely used and powerful technique that allows the end user to exert further control over the generative process of flow/diffusion models. Generally speaking, two families of techniques have emerged for solving this problem for gradient-based guidance: namely, posterior guidance (i.e., guidance via projecting the current sample to the target distribution via the target prediction model) and end-to-end guidance (i.e., guidance by performing backpropagation throughout the entire ODE solve). In this work, we show that these two seemingly separate families can actually be unified by looking at posterior guidance as a greedy strategy of end-to-end guidance. We explore the theoretical connections between these two families and provide an in-depth theoretical of these two techniques relative to the continuous ideal gradients. Motivated by this analysis we then show a method for interpolating between these two families enabling a trade-off between compute and accuracy of the guidance gradients. We then validate this work on several inverse image problems and property-guided molecular generation.

Related papers

• 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)
• Slow Thinking for Sequential Recommendation [88.46598279655575]
  We present a novel slow thinking recommendation model, named STREAM-Rec. Our approach is capable of analyzing historical user behavior, generating a multi-step, deliberative reasoning process, and delivering personalized recommendations. In particular, we focus on two key challenges: (1) identifying the suitable reasoning patterns in recommender systems, and (2) exploring how to effectively stimulate the reasoning capabilities of traditional recommenders.
  arXiv  Detail & Related papers  (2025-04-13T15:53:30Z)
• Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation [2.9631016562930546]
  Balancing the fidelity of the learned concept with its ability for generation in various contexts presents a significant challenge.<n>Existing methods often address this through diverse fine-tuning parameterizations and improved sampling strategies.<n>We propose a decision framework evaluating text alignment, computational constraints, and fidelity objectives to guide strategy selection.
  arXiv  Detail & Related papers  (2025-02-09T13:22:32Z)
• On the Guidance of Flow Matching [5.495430412700785]
  Flow matching has shown state-of-the-art performance in various generative tasks.<n>We propose the first framework of general guidance for flow matching.
  arXiv  Detail & Related papers  (2025-02-04T09:27:57Z)
• Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI [59.96044730204345]
  We introduce Derivative-Free Diffusion Manifold-Constrainted Gradients (FreeMCG)<n>FreeMCG serves as an improved basis for explainability of a given neural network.<n>We show that our method yields state-of-the-art results while preserving the essential properties expected of XAI tools.
  arXiv  Detail & Related papers  (2024-11-22T11:15:14Z)
• Deep Reinforcement Learning for Online Optimal Execution Strategies [49.1574468325115]
  This paper tackles the challenge of learning non-Markovian optimal execution strategies in dynamic financial markets. We introduce a novel actor-critic algorithm based on Deep Deterministic Policy Gradient (DDPG) We show that our algorithm successfully approximates the optimal execution strategy.
  arXiv  Detail & Related papers  (2024-10-17T12:38:08Z)
• CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems [3.3969056208620128]
  We propose to push the boundary of inference steps to 1-2 NFEs while still maintaining high reconstruction quality. Our method achieves new state-of-the-art in diffusion-based inverse problem solving.
  arXiv  Detail & Related papers  (2024-07-17T15:57:50Z)
• Landscape-Aware Growing: The Power of a Little LAG [49.897766925371485]
  We study the question of how to select the best growing strategy from a given pool of growing strategies. We present an alternative perspective based on early training dynamics, which we call "landscape-aware growing (LAG)"
  arXiv  Detail & Related papers  (2024-06-04T16:38:57Z)
• Understanding and Improving Training-free Loss-based Diffusion Guidance [46.803127794547756]
  We develop a deeper understanding of training-free guidance, as well as overcome its limitations. To elucidate their drawbacks, we theoretically demonstrate that training-free guidance is more susceptible to adversarial gradients. We then introduce a collection of techniques designed to overcome the limitations, accompanied by theoretical rationale and empirical evidence.
  arXiv  Detail & Related papers  (2024-03-19T03:27:01Z)
• Few-Shot Learning on Graphs: from Meta-learning to Pre-training and Prompting [56.25730255038747]
  This survey endeavors to synthesize recent developments, provide comparative insights, and identify future directions. We systematically categorize existing studies into three major families: meta-learning approaches, pre-training approaches, and hybrid approaches. We analyze the relationships among these methods and compare their strengths and limitations.
  arXiv  Detail & Related papers  (2024-02-02T14:32:42Z)
• Domain Adaptive Graph Classification [0.0]
  We introduce the Dual Adversarial Graph Representation Learning (DAGRL), which explore the graph topology from dual branches and mitigate domain discrepancies via dual adversarial learning. Our approach incorporates adaptive perturbations into the dual branches, which align the source and target distribution to address domain discrepancies.
  arXiv  Detail & Related papers  (2023-12-21T02:37:56Z)
• Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models [63.1637853118899]
  We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. We employ a shift control module that works on h-space of pre-trained diffusion models to manipulate a sample into a shifted version of itself. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions.
  arXiv  Detail & Related papers  (2023-10-15T18:44:30Z)
• Learning How to Propagate Messages in Graph Neural Networks [55.2083896686782]
  This paper studies the problem of learning message propagation strategies for graph neural networks (GNNs) We introduce the optimal propagation steps as latent variables to help find the maximum-likelihood estimation of the GNN parameters. Our proposed framework can effectively learn personalized and interpretable propagate strategies of messages in GNNs.
  arXiv  Detail & Related papers  (2023-10-01T15:09:59Z)
• Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems [82.92678837778358]
  preference-based methods have demonstrated substantial success in empirical applications such as InstructGPT. We show how human bias and uncertainty in feedback modelings can affect the theoretical guarantees of these approaches.
  arXiv  Detail & Related papers  (2023-07-24T17:50:24Z)
• Thompson sampling for improved exploration in GFlowNets [75.89693358516944]
  Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy. We show in two domains that TS-GFN yields improved exploration and thus faster convergence to the target distribution than the off-policy exploration strategies used in past work.
  arXiv  Detail & Related papers  (2023-06-30T14:19:44Z)
• Discovering Evolution Strategies via Meta-Black-Box Optimization [23.956974467496345]
  We propose to discover effective update rules for evolution strategies via meta-learning. Our approach employs a search strategy parametrized by a self-attention-based architecture. We show that it is possible to self-referentially train an evolution strategy from scratch, with the learned update rule used to drive the outer meta-learning loop.
  arXiv  Detail & Related papers  (2022-11-21T08:48:46Z)
• Multi-Agent Reinforcement Learning with Graph Convolutional Neural Networks for optimal Bidding Strategies of Generation Units in Electricity Markets [1.370633147306388]
  This paper proposes a distributed learning algorithm based on deep reinforcement learning (DRL) and a graph convolutional neural network (GCN) The state and connection between nodes are the inputs of the GCN, which can make agents aware of the structure of the system. We evaluate the proposed algorithm on the IEEE 30-bus system under different scenarios.
  arXiv  Detail & Related papers  (2022-08-11T09:29:31Z)
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance [148.9832328803202]
  We model the infor-mation fusion within focal stack via graph networks. We build a novel dual graph modelto guide the focal stack fusion process using all-focus pat-terns.
  arXiv  Detail & Related papers  (2021-10-02T00:54:39Z)
• Learning Gaussian Graphical Models with Latent Confounders [74.72998362041088]
  We compare and contrast two strategies for inference in graphical models with latent confounders. While these two approaches have similar goals, they are motivated by different assumptions about confounding. We propose a new method, which combines the strengths of these two approaches.
  arXiv  Detail & Related papers  (2021-05-14T00:53:03Z)
• A Survey on Deep Semi-supervised Learning [51.26862262550445]
  We first present a taxonomy for deep semi-supervised learning that categorizes existing methods. We then offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences.
  arXiv  Detail & Related papers  (2021-02-28T16:22:58Z)
• Unsupervised Discovery of Interpretable Directions in the GAN Latent Space [39.54530450932134]
  latent spaces of GAN models often have semantically meaningful directions. We introduce an unsupervised method to identify interpretable directions in the latent space of a pretrained GAN model. We show how to exploit this finding to achieve competitive performance for weakly-supervised saliency detection.
  arXiv  Detail & Related papers  (2020-02-10T13:57:14Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.