5 citations · 6 across the 18 of their papers we have counts for
23 papers
World Modeling through Spectral Alignment
Holger Molin, William Peng, Marco Bagatella +1
How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce SpecWM, a JEPA framework that e…
The a-number of the Serre-type maximal curves of Abdón-Bezerra-Quoos
Mahyar Shafighi
For every prime power , we determine the -number of the Serre-type maximal curves : over , odd, introduced…
LeWAM: End-to-End World and Action Modeling with JEPAs
Minghao Fu, Tavis Siebert, Eryk Halicki +1
Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically train visual representations and…
GeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction
Zhao Meng, Yinan Cai, Siru Zhong +2
Reconstructing fine-resolution column-averaged dry-air CO2 (XCO2) fields from sparse satellite observations requires models to infer spatial structure that is only weakly constrain…
H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
Wancong Zhang, Basile Terver, Michael Rabbat +2
Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models predict and plan at a single…
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Markus Karmann, Shile Li, Christian Internò +10
Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA train…
Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
Andy Zeyi Liu, Haoran Sun, Lucas Baker +2
Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning, but their capability to learn…
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
Lukas Kuhn, Lucas Maes, Giuseppe Serra +4
Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing self-supervised methods either p…
LpWM: A Case for Sparse Representations in World Models
Yilun Kuang, Yash Dagade, Quentin Le Lidec +3
Joint-embedding predictive architectures (JEPAs) learn latent dynamics for planning and avoid representation collapse by matching features to maximum-entropy distributions such as…
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
Haiyu Wu, Randall Balestriero, Morgan Levine
Regulating the latent space to an isotropic Gaussian distribution provides a stable and information-maximized landscape for world model planning. However, the latent space property…
Latent Actions from Factorized Transition Effects under Agent Ambiguity
Heejeong Nam, Chandradithya S Jonnalagadda, Harshit Aggarwal +2
Latent Action Models (LAMs) learn action-like proxies from observation. However, in multi-object or distractor-rich scenes, observations contain not only agent motion but also dist…
OctoSense: Self-Supervised Learning for Multimodal Robot Perception
Anthony Bisulco, Jeremy Wang, Kostas Daniilidis +2
We present OctoSense, an open-source sensor platform with stereo RGB and event cameras, LiDAR, a thermal camera, an inertial measurement unit, RTK-corrected global positioning syst…
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
Pratyaksh Rao, Wancong Zhang, Randall Balestriero +2
Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertainty. Neural network dynamics m…
Sensorimotor World Models: Perception for Action via Inverse Dynamics
Petr Ivashkov, Randall Balestriero, Bernhard Schölkopf
Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions. At the same time, latent JEPA-st…
Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring
Jiaqi Zhang, Ashton Lee, Anthony Wong +3
Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentatio…
When Does LeJEPA Learn a World Model?
David Klindt, Yann LeCun, Randall Balestriero
A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaus…
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
Lucas Maes, Quentin Le Lidec, Luiz Facury +9
World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with dispar…
Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
Chia-Hong Hsu, Randall Balestriero
Classifier-free Guidance (CFG) lets practitioners trade-off fidelity against diversity in Diffusion Models (DMs). The practicality of CFG is however hindered by DMs sampling cost.…
Hierarchical Planning with Latent World Models
Wancong Zhang, Basile Terver, Artem Zholus +8
World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, multi-stage tasks: prediction err…
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Lucas Maes, Quentin Le Lidec, Damien Scieur +2
Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on co…
Temporal Straightening for Latent Planning
Ying Wang, Oumayma Bounou, Gaoyue Zhou +4
Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to…
Causal-JEPA: Learning World Models through Object-Level Latent Masking
Heejeong Nam, Quentin Le Lidec, Lucas Maes +2
World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not…
Why and How Auxiliary Tasks Improve JEPA Representations
Jiacan Yu, Siyi Chen, Mingrui Liu +5
Joint-Embedding Predictive Architecture (JEPA) is increasingly used for visual representation learning and as a component in model-based RL, but its behavior remains poorly underst…