Latent-Space Regularization

Latest papers

21 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Motion-guided Contrastive Regularization For Latent World Models
Nov 4, 2026Yiwen Chen, Qiqi Hou, Jisoo Jeong +3World Models for Robotics Latent World Models
Northeastern University · Qualcomm AI Research
Latent Projection for Latent Planning
Oct 19, 2026Yoo Sung Jang, Michael RyooLatent-Space Planning World Model-Based Planning
Stony Brook University
ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
Oct 18, 2026Thai-Khanh Nguyen, Nhi Y. Pham, Uyen N. B. Vo +3Input-to-State Stability Latent-Space Regularization
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: Embedding Data into Chosen Geometric Structures
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
Sculpting the Latent Space: Disentanglement with WAE-MMD and Programmable Priors
Oct 13, 2025Quentin Fruytier, Akshay Malhotra, Shahab Hamidi-Rad +3Disentangled Representation Learning Semantic Representation Learning
The University of Texas at Austin · InterDigital Communications, AI Lab
Latent Representation Learning from 3D Brain MRI for Latent Analysis and Prediction in Multiple Sclerosis
Sep 28, 2025Trinh Ngoc Huynh, Nguyen Duc Kien, Nguyen Hai Anh +8Medical Image Representation Learning Variational Autoencoders
VNU University of Engineering and Technology, Hanoi, Vietnam. · Bach Mai Hospital, Hanoi, Vietnam. · Department of Radiology, First Faculty of Medicine, Charles University, General University Hospital, Prague, Czech Republic. +3
Over-fitting Control in Deep Nonlinear Matrix Completion via Gradual Nonsmooth Regularization
Mar 15, 2024Sajad Faramarzi, Farzan Haddadi, Sajjad Amini +2Matrix Completion Latent-Space Regularization
School of Electrical Engineering, Iran University of Science & Technology, Tehran, Iran. · Electronics Research Institute (ERI) at Sharif University of Technology, Tehran, Iran. · College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA, USA. +2
Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
Jul 31, 2023M. M. Amaan Valiuddin, Christiaan G. A. Viviers, Ruud J. G. van Sloun +2Segmentation Uncertainty Estimation Medical Image Segmentation
Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, 5612 AZ, The Netherlands · Phillips Research, Eindhoven, The Netherlands

Nov 4, 2026J/K move · Enter open · S save

Motion-guided Contrastive Regularization For Latent World Models

Yiwen Chen, Qiqi Hou, Jisoo Jeong, Yinhao Zhu+2

Northeastern University · Qualcomm AI Research

World Models for Robotics Latent World Models World Model-Based Planning Latent-Space Regularization Representation Collapse Contrastive Learning

Open paper AskPDF arXiv

JEPA-style world models learn action-conditioned latent dynamics without reconstructing observations, but distributional regularization alone does not ensure that their representations preserve information needed for control. We identify static collapse, a failure mode in which the encoder preserves episode-specific static content while suppressing manipulation-relevant state changes. Because static content is temporally predictable yet diverse across episodes, this failure can persist despite regularizers such as SIGReg. A controlled study on OGBench-Cube shows that introducing randomized backgrounds substantially degrades planning performance while leaving the underlying manipulation task unchanged. To address this problem, we propose motion-guided contrastive regularization. Our approach compares predicted latent transitions with transitions to candidate observations from the same episode, reducing the usefulness of static background identity for distinguishing action outcomes. Optical-flow similarities provide soft contrastive targets, allowing candidates with similar motion to receive similar supervision. Combined with latent prediction and SIGReg, our objective encourages representations to preserve within-episode state distinctions and similarities between related transitions. Our method improves planning success over LeWorldModel (LeWM) from 52% to 78% on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while maintaining comparable performance on four other visual-control benchmarks.