Generative Processes

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

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
Multi-Agent Flow Matching with Decoupled Generative Guidance
Sep 29, 2026Ruoyu Lin, Magnus Egerstedt, Fabio PasqualettiConditional Flow Matching Generative Processes
Department of Electrical Engineering and Computer Science, University of California, Irvine, Irvine, CA 92697 USA · University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA
Anguinus Sculpturae: Compositional Synthesis of Peak-Enhancement Breast DCE-MRI Scans
Sep 27, 2026Benjamin Hamm, Nico Albert Disch, Maximilian Rokuss +3Magnetic Resonance Imaging Medical Image Generation
German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany · Medical Faculty, Heidelberg University, Germany · Faculty of Mathematics and Computer Science, Heidelberg University, Germany +3
Diffusion Trajectory Modeling for Semantic Correspondence
Sep 14, 2026Yusung ChoiDiffusion Models Generative Processes
Department of Computer Engineering Pukyong National University Busan, Republic of Korea
RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction
Sep 14, 2026Zilai LiDiffusion Inversion Watermarking
Independent Researcher
Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templates
Sep 12, 2026Shirong Yang, Bo Yang, Ying CaoLayouts Generative Processes
School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai, China
Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models
Sep 3, 2026Ross Tieman, Evan MarkouDiversity Generative Processes
Fenner School of Environment & Society · Australian National University · School of Computing
Process-Constituted Intelligence: A Shared Criterion for Humans and Machines
Aug 17, 2026Michael J. Richardson, Ayeh Alhasan, Cassandra Crone +5Generative Artificial Intelligence Generative Processes
School of Psychological Sciences, Macquarie University, Sydney, NSW 2109, Australia · Performance and Expertise Research Centre, Macquarie University · Frontier AI Research Centre, Macquarie University +3
Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion
Aug 13, 2026Van Khoa Nguyen, Alexandros KalousisCrystal Structure Crystal
HES-SO Geneva · University of Geneva
ArtMine: Discovering and Formalizing Artistic Processes
Jul 9, 2026Kaustubh Kumar, Ashutosh Ranjan, Vivek Srivastava +2Artistic Ownership Art
1TCS Research, Pune, India · 2Indian Institue of Technology, Patna, India.
An exact information theory of generalization phase transitions in Bayesian diffusion models
Jul 9, 2026Henry Hunt, Mason Kamb, Surya GanguliDiffusion Models Information-Theoretic Limits
Department of Applied Physics Stanford University Stanford, CA 94305
Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion
Jun 30, 2026Zhizhong Fu, Wei Zhou, Zhaoyang Jiang +5Uncertainty-Aware Fusion Visible Image Fusion
School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China. · Department of Radiology, Huzhou Maternity & Child Health Care Hospital, Huzhou 313000, China. · Department of Radiology, Huzhou Maternity & Child Health Care Hospital Affiliated to Huzhou Normal University,Huzhou 313000,China. +3
Attention Dynamics in Diffusion Models: A Visual Analytics Framework for Human-AI Collaboration
Jun 28, 2026Yiran Xiao, George LegradyText-To-Image Diffusion Models Diffusion Models
University of California, Santa Barbara
Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models
Jun 25, 2026Abrar Alotaibi, Moataz AhmedAttacker Large Language Model Adversarial Evaluation
Information and Computer Science Department, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia · College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Dammam, 31441, Saudi Arabia · SDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia
Distilling a Modular Reservoir Through a Genomic Bottleneck
Jun 20, 2026Mani Hamidi, Sina Khajehabdollahi, Charley M. Wu +1Reservoir Computing Recurrent Neural Networks
Department of Computer Science, University of Tübingen, Tübingen, Germany · Flowers Team Inria, Bordeaux, France · Max Planck Institute for Biological Cybernetics, Tübingen, Germany +3
ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
Jun 13, 2026Brian Nlong Zhao, Ozgur Kara, Junho Kim +1Generative Processes Camera Trajectories
University of Illinois Urbana-Champaign
Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Model
Jun 4, 2026Renjith Prasad, Chathurangi Shyalika, Anushka Pawar +2Multimodal Generation Generative Processes
University of South Carolina · Indian AI Research Organization
PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion
Jun 2, 2026Qingdong Xu, Jiajun Zhu, Shilin Zhu +4Lidar Scene Reconstruction
1MEGVII Technology · 2Qianli Technology · 4Northeastern University, China +2
Why Do Time Series Models Need Long Context Windows?
Jun 1, 2026Luca Butera, Giovanni De Felice, Andrea Cini +1Time Series Deep Learning
1Università della Svizzera Italiana · 2EPFL · 3Politecnico di Milano
Flow-Transformed Implicit Processes for Function-Space Variational Inference
Jun 1, 2026Luis A. Ortega, Andrés R. Masegosa, Thomas D. NielsenVariational Inference Generative Processes
Aalborg University
JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions
Jun 1, 2026Jiashuo Yu, Yao Yao, Boyu Chen +1Audio-Video Generation Generative Music
Jen Music AI
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
Jun 1, 2026Keyue Qiu, Xintong Wang, Zhilong Zhang +2Molecular Design Generative Processes
Institute for AI Industry Research (AIR), Tsinghua University · Department of Computer Science and Technology, Tsinghua University · Qiuzhen College, Tsinghua University +1
Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models
May 29, 2026Haoxiang Cheng, Yunfei Wang, Chao Chen +5Knowledge Graph Completion Knowledge Graphs
Laboratory for Big Data and Decision, National University of Defense Technology · National Key Laboratory of Information Systems Engineering, National University of Defense Technology · Microsoft Corporation +2
Treatment-Conditioned Diffusion for Forecasting Neurodegenerative Disease Progression
May 28, 2026Danylo Boiko, Viktoriia MishkurovaMultimodal Neuroimaging Text-Conditioned Diffusion Model
Innoloft Inc. 701 Brazos Street, Austin, TX 78701, USA · Bogomolets National Medical University Beresteiskyi Avenue, 34, Kyiv, 03057, Ukraine
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
May 27, 2026Gabriel Moreira, Manuel Marques, João Paulo Costeira +1Diffusion Models Generative Processes
Institute for Systems and Robotics, Instituto Superior Técnico, Lisbon, Portugal · Carnegie Mellon University, Pittsburgh, PA, USA
Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection
May 24, 2026Zijie Cao, Weijie Tu, Yao Xiao +3Ai-Generated Image Detection Generative Artificial Intelligence
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · Australian National University, Canberra, Australia · Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China +1
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
May 20, 2026Benedict Quartey, Sebastian Castro, Eric Rosen +3Visuomotor Policy Action Generation
Brown University · Robotics & AI Institute
From Full and Partial Intraoral Scans to Crown Proposal: A Classification-Guided Restoration Assistance Pipeline
May 14, 2026Rabin Kunwar, Dikshya Parajuli, Rujal Acharya +12Intraoral Scans Occlusal Constraint
Accelerated Komputing Pvt. Ltd., Bhaktapur, Nepal. · University of Pittsburgh, Pittsburgh, PA, USA. · Emium Co. Ltd., Tokyo, Japan. +3
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
May 11, 2026Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2Generative Flow Networks Diffusion Models
1TU Munich, MCML · 2MIT CSAIL · 3King’s College London +2
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
May 11, 2026Gideon Popoola, John SheppardExplainable Artificial Intelligence Algorithmic Fairness
Montana State University, Bozeman, Montana, USA
Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation
May 8, 2026Amy Rafferty, Rishi Ramaesh, Ajitha RajanChest X-Ray Dermoscopic Concept Bottleneck Models
University of Edinburgh, UK · NHS Lothian, UK
Tracing Uncertainty in Language Model "Reasoning"
May 8, 2026Nils Grünefeld, Bertram Højer, Philipp Mondorf +5Large Language Model Uncertainty LLM Reasoning Strategies
Data Science Section, IT University of Copenhagen · Pioneer Centre for Artificial Intelligence · MaiNLP, Center for Information and Language Processing, LMU Munich +2
On the Robustness of Distribution Support under Diffusion Guidance
May 8, 2026Ruijia Cao, Yuchen Wu, Nisha ChandramoorthyGenerative Processes Distributions
Center for Applied Mathematics, Cornell University · School of Operations Research and Information Engineering, Cornell University · Department of Statistics, The University of Chicago
MetaOthello: A Controlled Study of Multiple World Models in Transformers
Feb 26, 2026Aviral Chawla, Galen Hall, Juniper LovatoTransformer Architectures World Models
Vermont Complex Systems Institute, University of Vermont, Burlington, VT · University of Michigan, Ann Arbor, MI
Is Generation Required for Data-Efficient Perception?
Dec 9, 2025Jack Brady, Bernhard Schölkopf, Thomas Kipf +2Generative Processes Visual Perception
Max Planck Institute for Intelligent Systems, Tübingen, Germany · Tübingen AI Center · ELLIS Institute, Tübingen +1

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 35