GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories

• URL: http://arxiv.org/abs/2609.02160v1
• Date: Wed, 02 Sep 2026 06:22:04 GMT
• Title: GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories
• Abstract summary: Diffusion models achieve high sample quality but remain expensive at inference time because sampling requires many neural function evaluations (NFEs)<n>We introduce GeoPRINT, a training-free framework for constructing non-uniform sampling schedules from the geometry of denoising trajectories.<n>GeoSPRINT consistently improves over uniform DDIM (Denoising Diffusion Implicit Models) schedules at matched NFE budgets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models achieve high sample quality but remain expensive at inference time because sampling requires many sequential neural function evaluations (NFEs). Existing acceleration methods either use fixed step-skipping schedules, adapt step sizes based on local numerical error, or require additional training. We introduce GeoSPRINT (Geometric Step Pruning for Inference in Trajectories), a training-free framework for constructing non-uniform sampling schedules from the geometry of denoising trajectories. GeoSPRINT detects geometrically redundant steps using a hyperplanarity test in latent space, implemented efficiently via QR factorization, and converts the resulting redundancy profile into a sampling schedule that allocates more steps to high-curvature regions of the trajectory. In addition, we introduce the trajectory projection score $α_{\mathrm{traj}}$, a residual-variance metric that quantifies trajectory straightness and serves as a model-free diagnostic for rectified flow quality. Across CIFAR-10 ($32{\times}32$), LSUN Church ($256{\times}256$), and Stable Diffusion v1.5 ($512{\times}512$ latent), GeoSPRINT consistently improves over uniform DDIM (Denoising Diffusion Implicit Models) schedules at matched NFE budgets. On CIFAR-10, GeoSPRINT improves FID (Fréchet Inception Distance) by 0.7-1.1 over DDIM across 49-89 NFEs and surpasses DPM-Solver++ at NFE${\geq}30$ despite using a first-order DDIM solver. On LSUN Church, it reduces FID from 1.48 to 1.26 at 52 steps, and on Stable Diffusion v1.5 it achieves up to 1.93 FID improvement over DDIM. These results show that trajectory geometry provides a useful global signal for allocating inference steps and that schedule quality can substantially improve diffusion sampling efficiency without retraining.

Related papers

• Rethinking Pixel Mean Flows via Interval Denoiser [95.11499828543344]
  We propose the Interval Denoiser, a framework for latent-free generation.<n>Our model achieves an FID of 4.55 in one step (1-NFE) and 3.98 in two steps (2-NFE) without perceptual losses.
  arXiv  Detail & Related papers  (2026-08-05T13:22:43Z)
• GeoRouteNet: Geometry-Enhanced Non-Autoregressive Neural Solver for the Traveling Salesman Problem [5.202950948929751]
  GeoRouteNet is a geometry-enhanced neural solver for Euclidean traveling salesman problem (TSP)<n>On the model side, GeoRouteNet incorporates centered node features, learnable radial distance basis functions, distance-aware graph attention, LayerNorm-SwiGLU feed-forward blocks, and cross-layer attentive residual encoder mixing.<n>On the training side, we design multi-candidate self-comparison reinforcement learning (MCS-RL), which samples multiple candidate tours per instance.
  arXiv  Detail & Related papers  (2026-06-22T02:31:22Z)
• Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry [64.61931485161833]
  Image generative models aim to sample data points from the underlying data manifold.<n>We propose the Data Manifold-aware Image diffusioN moDel (MIND)<n>MIND integrates discrete patch tokenization into the score function of a continuous diffusion model.
  arXiv  Detail & Related papers  (2026-05-25T08:43:14Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance [5.814544128372275]
  We propose Guided Path Sampling (GPS) as a new paradigm for iterative refinement.<n>GPS replaces unstable extrapolation with a principled, manifold-constrained, ensuring the sampling path remains on the data manifold.<n>GPS outperforms existing methods in both perceptual quality and complex prompt adherence.
  arXiv  Detail & Related papers  (2025-12-28T11:12:56Z)
• MRS-YOLO Railroad Transmission Line Foreign Object Detection Based on Improved YOLO11 and Channel Pruning [2.6795746856835785]
  We propose an improved algorithm MRS-YOLO based on YOLO11.<n>The mAP50 and mAP50:95 of the MRS-YOLO algorithm are improved to 94.8% and 86.4%, respectively.
  arXiv  Detail & Related papers  (2025-10-12T11:38:09Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs [54.08445874064361]
  We propose to solve a regularized distributionally robust learning problem in the decentralized setting. By adding a Kullback-Liebler regularization function to the robust min-max optimization problem, the learning problem can be reduced to a modified robust problem. We show that our proposed algorithm can improve the worst distribution test accuracy by up to $10%$.
  arXiv  Detail & Related papers  (2022-08-29T18:01:42Z)
• Enhanced Laser-Scan Matching with Online Error Estimation for Highway and Tunnel Driving [0.0]
  Lidar data can be used to generate point clouds for navigation of autonomous vehicles or mobile robotics platforms. We propose the Iterative Closest Ellipsoidal Transform (ICET), a scan matching algorithm which provides two novel improvements.
  arXiv  Detail & Related papers  (2022-07-29T13:42:32Z)

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.