Vector Fields

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 30

All topics

Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
Sep 30, 2026Simone Facchiano, Jan Eric Lenssen, Bernt Schiele +3Text-To-Image Diffusion Models Steering
Max Planck Institute for Informatics · Sapienza University of Rome
Riemannian Simultaneous Inference for Tangent Vector Field Regression
Sep 18, 2026Xiaotian Chang, Yangdi Jiang, Qirui HuVector Fields Covariance
Division of Mathematical Sciences, Nanyang Technological University. · School of Statistics and Data Science, Shanghai University of Finance and Economics.
Decoupling Physical Speed from Path Parameterization in Singularity-Free Guiding Vector Fields
Sep 17, 2026Zhouru Xiao, Sha Luo, Yang Lu +5Vector Fields Singularity
School of Artificial Intelligence and Robotics, Hunan University, Changsha, China · College of Information Science and Engineering, Hunan Normal University, Changsha, China · College of Systems Engineering and the State Key Laboratory of Digital Intelligent Modeling and Simulation, National University of Defense Technology, Changsha, China +2
Distributed Safe Cooperative Vector Field for Trajectory Curvature Constrained Multi-Robot Systems
Sep 14, 2026Zhouru Xiao, Tao Teng, Weijia Yao +3Multi-Robot Systems Collision Avoidance
School of Artificial Intelligence and Robotics, Hunan University, Changsha 410082, China · College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410082, China
Singularity-Free Guiding Vector Fields on SO(3) with Designer-Specified Progression Behavior
Sep 7, 2026Jesus Bautista, Hector Garcia de MarinaVector Fields Geometric Guidance
Department of Computer Engineering, Automation and Robotics, and Institute of Mathematics (IMAG), University of Granada, Granada, Spain
Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision
Aug 5, 2026Grzegorz Gruszczynski, Pawel Olszowiec, Michal Byra +2Self-Supervised Vision Transformers Vision Transformer
Samsung AI Center, Warsaw, Poland · Institute of Fundamental Technological Research, Polish Academy of Sciences, Warsaw, Poland
Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework
Jul 30, 2026Tianen Shen, Zhengyu Li, Yutong Li +4Multivariate Time-Series Time Series
ScaleResfusion: Residual Rectified Flow based on Residual Vector Field
Jul 28, 2026Zhenning Shi, Chen Xu, Junhao Zhang +4Image Restoration Rectified Flow
College of Computer Science, Nankai University, Tianjin, China · Faculty of Information Science and Computing, University of Macau, Macau, China · CSIRO Data61, Australia +1
Perturbative-NeuSA: A Structured Spectral Framework for Time-Dependent PDEs
Jul 27, 2026Xianli Zhu, Jia YinNeural Partial Differential Equation Solvers Partial Differential Equations
School of Mathematical Sciences, Fudan University Shanghai, China
Finite-Time Curvature-Constrained Vector Field for Saturation-Free Motion Planning of Nonholonomic Robots
Jul 20, 2026Zhouru Xiao, Sha Luo, Yang Lu +5Vector Fields Motion Planning
School of Artificial Intelligence and Robotics, Hunan University. China. · College of Information Science and Engineering, Hunan Normal University, China. · College of Systems Engineering and the State Key Laboratory of Digital Intelligent Modeling and Simulation, National University of Defense Technology, China. +1
Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
Jul 15, 2026Laurin Lux, Alexander H. Berger, Moritz Knolle +23D Medical Image Segmentation Loss Function
School of Computation, Information and Technology, TUM, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · Department of Radiology, Weill Cornell Medicine, New York City, USA +3
Advances in Neural Controlled Differential Equations
Jul 6, 2026Benjamin WalkerNeural Ordinary Differential Equations Learning-Based Control
Balliol College, University of Oxford
Central limit theorem for the averaged Adam optimizer
Jun 19, 2026Steffen Dereich, Arnulf JentzenStochastic Approximation Large Deviation Principle
Institute for Mathematical Stochastics, University of Münster, Germany · School of Data Science and School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China · Applied Mathematics: Institute for Analysis and Numerics, University of Münster, Germany
TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
Jun 18, 2026Haoxuan Li, Ziya Erkoç, Daniele Sirigatti +4Mesh Generation 3D Generation
Technical University of Munich · AUDI AG · University of Virginia
Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversion
Jun 12, 2026Chen Min, Zheng MaDiffusion Priors Full Waveform Inversion
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China · CMA-Shanghai, Shanghai Jiao Tong University, Shanghai, China
Efficient Computation of Distance Functions for Navigation Vector Fields in Lie Groups
Jun 3, 2026Vinicius M. Gonçalves, João Baião, Felipe Bartelt +4Lie Group Vector Fields
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
May 31, 2026Zemin Yang, Yaoyu He, Yiming Zhong +5Temporally Coherent Imitation Learning Imitation Learning
ShanghaiTech University · Shanghai Jiao Tong University · The Chinese University of Hong Kong +1
Parameter-Efficient Generative Modeling with Controlled Vector Fields
May 27, 2026Peyman MortezaGenerative Flow Networks Generative Models
Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
May 25, 2026Junseok Ko, Jungwoo Kim, Jong-Seok LeeConcept Erasure Text-To-Image Diffusion Models
Department of Artificial Intelligence, Yonsei University · School of Integrated Technology, Yonsei University
Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
May 24, 2026Jules Berman, Tobias Blickhan, Benjamin PeherstorferWasserstein Gradient Flows Vector Fields
Courant Institute of Mathematical Sciences, New York University, New York, NY 10012, USA.
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
May 22, 2026Junru Zhang, Lang Feng, Jinbo Wang +6Time-Series Generation Multiscale Dynamics
Zhejiang University, China · Nanyang Technological University, Singapore · I2R, Agency for Science, Technology and Research (A*STAR), Singapore
A Unified Framework for Structured Flow Modeling: From Representation to Verification and Model Discovery
May 18, 2026Diego CasadeiVector Fields Flow Models
Fly High Engineering AG, Badenerstrasse 13, 5200 Brugg AG, Switzerland
Path-independent Flow Matching for Multi-parameter Generative Dynamics
May 13, 2026Francisco Téllez, AmirHossein Zamani, Philippe Martin +5Conditional Flow Matching Latent Transport
Université de Montréal, Mila · Concordia University, Mila · Concordia University +2
Generative Modeling with Flux Matching
May 8, 2026Peter Pao-Huang, Xiaojie Qiu, Stefano ErmonGenerative Models Vector Fields
Department of Computer Science, Stanford University · Department of Genetics, Stanford University
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
May 8, 2026Kim Yong Tan, Yueming Lyu, Ivor Tsang +1Generative Flow Networks Flow Models
College of Computing and Data Science, Nanyang Technological University, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore
A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models
May 7, 2026Aditya Ranganath, Mukesh SinghalScore-Based Diffusion Model Generative Models
Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore, CA 94551, USA · Department of Electrical Engineering University of California Merced, CA 95343, USA
Guiding Vector Field Generation via Score-based Diffusion Model
Apr 27, 2026Zirui Chen, Shiliang Guo, Shiyu ZhaoVector Fields Diffusion Planning
College of Computer Science and Technology, Zhejiang University, Hangzhou, China. · WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China.
Multi-UAV Path Following using Vector-Field Guidance
Apr 20, 2026Gautam Kumar, Amit Shivam, Ashwini RatnooMulti-Uav Unmanned Aerial Vehicles
Department of Aerospace Engineering, Indian Institute of Science Bangalore, India 560012 · Department of Electrical and Computer Engineering, University of Porto, Porto, Portugal
Planning Smooth and Safe Control Laws for a Unicycle Robot Among Obstacles
Apr 19, 2026Aref Amiri, Basak Sakcak, Steven M. LaValleRobust Control Obstacle Avoidance
Faculty of Information Technology and Electrical Engineering, University of Oulu · Department of Advanced Computing Sciences, Maastricht University
ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
Apr 3, 2026Jiekai Wu, Rong Fu, Chuangqi Li +10Remote Sensing Image Segmentation Learnable Prototypes
Independent Researcher · The Institute of Collaborative Innovation, University of Macau, Macau 999078, China · Department of Information and Computing Sciences, Faculty of Science, Utrecht University, Utrecht 3584 CC, Netherlands +10

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond

Simone Facchiano, Jan Eric Lenssen, Bernt Schiele, Wolfgang Stammer+2

Max Planck Institute for Informatics · Sapienza University of Rome

Text-To-Image Diffusion Models Steering Vector Fields Generative Processes Prior Knowledge Integration

Open paper AskPDF arXiv

As state-of-the-art text-to-image flow models achieve near-photorealistic quality, controlling their outputs, e.g., suppressing harmful content while promoting benign alternatives, has become a central challenge. The current steering paradigm consists of adding a global steering vector to selected activations. While functional, a fixed and example-agnostic vector applied uniformly along the entire trajectory cannot adapt to the changing state of the generation and often causes unintended global changes. We introduce Steering Fields, a generalization of steering vectors that adaptively re-estimates the steering direction at each step of the generative process. Steering Fields operate on the noisy states of flow models, expose a continuous trade-off between steering strength and content preservation, and are compositional, enabling the simultaneous induction and inhibition of concepts, setting a new state of the art on safety steering benchmarks. Despite using no explicit spatial masks or object priors, the trajectory-adaptive estimation naturally preserves local structure, in a manner reminiscent of image editing. In fact, Steering Fields can serve as a structure-preserving image-editing technique that achieves state-of-the-art semantic fidelity (CLIP, VQAScore), while remaining model-agnostic and inversion-free.

Momentum

Related topics

Latest papers 30