Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization

• URL: http://arxiv.org/abs/2608.13037v2
• Date: Fri, 14 Aug 2026 08:06:25 GMT
• Title: Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization
• Abstract summary: Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality.<n>Fine-grained spatial controllability remains a significant challenge.<n>We present a novel training-free and gradient-free approach for precise spatial guidance.
• Score: 46.49480145234397
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality, yet fine-grained spatial controllability remains a significant challenge. While existing training-free methods produce solid overall results in spatially grounded generation, \ie, placing a specific object in a designated location, they rely on gradient-based optimization techniques that incur prohibitive computational overhead, a bottleneck amplified in modern large-scale architectures. To address this limitation, we present Gradient-free Analytical Trajectory Optimization Video Generation (GATO-Vid), a novel training-free and gradient-free approach for precise spatial guidance. Rather than relying on costly backward passes, we introduce an alternative cross-attention score and solve it analytically to obtain an exact, closed-form solution. To use our analytical solution, we propose an on-the-fly injection mechanism tailored to the topological manifold of the transformer's latent space. Our experiments demonstrate that GATO-Vid significantly outperforms existing baselines in localization accuracy while introducing minimal computational overhead.

Related papers

• Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation [3.881211374324378]
  Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.<n>We propose a gradient-free methodology reframing detection from binary classification to an out-of-distribution (OOD) anomaly measurement problem.
  arXiv  Detail & Related papers  (2026-06-03T13:04:23Z)
• Fitting Unknown Number of Hyperplanes with Manifold Optimization [57.48093263119306]
  Fitting unknown number of linearplanes to data is a fundamental yet challenging problem in machine learning.<n>Existing approaches often struggle with optimum optima or lack geometric consistency.
  arXiv  Detail & Related papers  (2026-05-27T14:02:20Z)
• Natural Functional Gradients for Smooth Trajectory Optimization [11.331190543795914]
  We propose a trajectory optimization framework that performs geometry-aware updates directly in function space using natural functional gradients.<n>We derive a practical Monte-Carlo estimator of the natural functional gradient that requires only black-box trajectory evaluations.<n> Experiments on constrained robotic manipulation tasks demonstrate that the proposed method improves trajectory feasibility and produces smoother motions.
  arXiv  Detail & Related papers  (2026-05-27T09:25:57Z)
• Parallel Diffusion Solver via Residual Dirichlet Policy Optimization [88.7827307535107]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face significant image quality degradation under a low-dimensional budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as EPD-EPr), a novel ODE solver that mitigates these errors by incorporating multiple gradient parallel evaluations in each step.
  arXiv  Detail & Related papers  (2025-12-28T05:48:55Z)
• Optimal Transport-Based Displacement Interpolation with Data Augmentation for Reduced Order Modeling of Nonlinear Dynamical Systems [0.0]
  We present a novel reduced-order Model (ROM) that exploits optimal transport theory and displacement to enhance the representation of nonlinear dynamics in complex systems. We show improved accuracy and efficiency in predicting complex system behaviors, indicating the potential of this approach for a wide range of applications in computational physics and engineering.
  arXiv  Detail & Related papers  (2024-11-13T16:29:33Z)
• Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation [44.03611131165989]
  We propose a novel generative parameterization method dubbed Hierarchical generative Distillation (H-PD)<n>The proposed H-PD achieves a significant performance improvement under various settings with equivalent time consumption.<n>It even surpasses current generative distillation using diffusion models under extreme compression ratios IPC=1 and IPC=10.
  arXiv  Detail & Related papers  (2024-06-09T09:15:54Z)
• Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching [55.28394191394675]
  We develop an adaptive inexact Newton method for equality-constrained nonlinear, nonIBS optimization problems. We demonstrate the superior performance of our method on benchmark nonlinear problems, constrained logistic regression with data from LVM, and a PDE-constrained problem.
  arXiv  Detail & Related papers  (2023-05-28T06:33:37Z)
• Robust Model-Based Optimization for Challenging Fitness Landscapes [96.63655543085258]
  Protein design involves optimization on a fitness landscape. Leading methods are challenged by sparsity of high-fitness samples in the training set. We show that this problem of "separation" in the design space is a significant bottleneck in existing model-based optimization tools. We propose a new approach that uses a novel VAE as its search model to overcome the problem.
  arXiv  Detail & Related papers  (2023-05-23T03:47:32Z)
• Accelerating Inverse Learning via Intelligent Localization with Exploratory Sampling [1.5976506570992293]
  solving inverse problems is a longstanding challenge in materials and drug discovery. Deep generative models are recently proposed to solve inverse problems. We propose a novel approach (called iPage) to accelerate the inverse learning process.
  arXiv  Detail & Related papers  (2022-12-02T08:00:04Z)
• The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations [0.0]
  In this work we approach the problem of automatically detecting the correct pre-processing transformation in a statistical learning framework. The purely data-driven method allowed us to generalise the existing approaches of linear subspace manipulation to non-linear hyperbolic problems with unknown advection fields. The proposed algorithm has been validated against simple test cases to benchmark its performances and later successfully applied to a multiphase simulation.
  arXiv  Detail & Related papers  (2021-08-14T15:13:35Z)
• Pushing the Envelope of Rotation Averaging for Visual SLAM [69.7375052440794]
  We propose a novel optimization backbone for visual SLAM systems. We leverage averaging to improve the accuracy, efficiency and robustness of conventional monocular SLAM systems. Our approach can exhibit up to 10x faster with comparable accuracy against the state-art on public benchmarks.
  arXiv  Detail & Related papers  (2020-11-02T18:02:26Z)

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.