Latent-Space Regularization

Latest papers

15 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
Oct 18, 2026Thai-Khanh Nguyen, Nhi Y. Pham, Uyen N. B. Vo +3Latent-Space Regularization Neural Network Stability
Faculty of Information Technology 1, Posts & Telecommunications Institute of Technology · Center for AI Research, VinUniversity · Faculty of Artificial Intelligence, Posts & Telecommunications Institute of Technology +2
Directional Pullback Regularization for Long-Horizon Rollout of Latent World Models in Autonomous Driving
Oct 12, 2026Shatadal Mishra, Ahmadreza Moradipari, Nejib AmmarLatent-Space Regularization World Models for Autonomous Driving
Toyota Motor North America R&D - InfoTech Labs
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
Oct 2, 2026Mingyu Park, Samyeul Noh, Hyun Myung +1Latent-Space Regularization Generalization in RL
Robotics Program KAIST, ETRI · Electrical Engineering KAIST
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
Aug 11, 2026Haiyu Wu, Randall Balestriero, Morgan LevineRepresentation Learning World Models
Altos Labs · Brown University
QQWorld: Quantile-Quantile Matching for World Model Regularization
Jul 30, 2026Zhoushun Yu, Xiaoyu Hu, Xiangyu XuWorld Model Learning World Model-Based Planning
Xi’an Jiaotong University
Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method
Jul 29, 2026Chang Liu, Fei Suo, Yanzhou Jin +3World Model Learning Multi-Task Learning
Graduate School of Engineering, The University of Tokyo, Tokyo, Japan
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
Jul 15, 2026Fabio Arnez, Alexandra Gomez-VillaWorld Model Learning Active Inference
Université Paris-Saclay, CEA, List F-91120, Palaiseau, France · Computer Vision Center Barcelona, Spain
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Jul 1, 2026Adeel Yousaf, Soumik Ghosh, James Beetham +2Diffusion Model Alignment Representation Learning
Institute of Artificial Intelligence University of Central Florida, Orlando, United States
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
May 31, 2026Triet M. LeJoint-Embedding Predictive Architecture Geometric Representation Learning
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
May 10, 2026Kai Zhao, Dongliang Nie, Yuchen Lin +4Representation Learning Representation Collapse
1Shanghai University · 2The University of Manchester · 3Nankai University
JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning
Apr 22, 2026Ali Aghababaei-Harandi, Aude Sportisse, Massih-Reza AminiRepresentation Learning Geometric Representation Learning
Université Grenoble Alpes, CNRS, Computer Science Laboratory LIG, Grenoble, France
MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE
Apr 7, 2026Zixuan Chen, Heng Zhang, YuPeng Qin +5Latent-Space Regularization Cancer Survival Prediction
Binjiang Institute of Zhejiang University · Zhejiang University · School of Medicine, Zhejiang University
Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models
Mar 22, 2026Qifan Li, Xingyu Zhou, Jinhua Zhang +2Latent-Space Regularization Latent Diffusion Models
University of Electronic Science and Technology of China
Manifold-Matching Autoencoders
Mar 17, 2026Laurent Cheret, Vincent Létourneau, Isar Nejadgholi +3Multidimensional Scaling Autoencoders
Department of Computer Science, University of Ottawa, Ottawa, Canada · MILA, Montréal, Canada · National Research Council of Canada, Ottawa, Canada
SegReg: Latent Space Regularization for Improved Medical Image Segmentation
Feb 26, 2026Puru Vaish, Amin Ranem, Felix Meister +3Latent-Space Regularization Medical Image Segmentation
Department of Applied Mathematics, Technical Medical Centre, University of Twente, The Netherlands · Digital Technology and Innovation, Siemens Healthineers, Erlangen, Germany

Oct 18, 2026J/K move · Enter open · S save

ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss

Thai-Khanh Nguyen, Nhi Y. Pham, Uyen N. B. Vo, Thieu N. Vo+2

Faculty of Information Technology 1, Posts & Telecommunications Institute of Technology · Center for AI Research, VinUniversity · Faculty of Artificial Intelligence, Posts & Telecommunications Institute of Technology+2

Latent-Space Regularization Neural Network Stability

Open paper AskPDF arXiv

Next-token prediction leaves hidden-state trajectories largely unconstrained, while existing geometric regularizers primarily control the direction rather than the magnitude of trajectory deviations. We introduce ControlJEPA, a trajectory regularization framework based on a discrete-time Lyapunov contraction condition from practical Input-to-State Stability theory. Its Lyapunov Tube Loss penalizes violations of this condition on a normalized, scale-invariant measure of transversal deviation. When the contraction condition holds at every step, the hidden-state trajectory remains within an explicit tube around the reference secant. In the partial-ISS regime, we bound mean transversal energy, temporal variance, and average tube width using the Lyapunov loss and contraction parameters, with horizon-independent variance bounds under uniformly bounded violations. ControlJEPA requires no architectural modifications. Across six benchmarks and six model families, it consistently improves accuracy and data efficiency over standard fine-tuning and prior trajectory regularizers. The resulting smoother transversal profile also persists empirically during inference, when the regularizer is inactive. The code is publicly available at: https://github.com/t-khanusa/ControlJEPA