SiamJEPA uses Siamese student encoders to improve JEPA-based representation learning.
problem Improving self-supervised representation learning in JEPA models.
method Proposes SiamJEPA with masked Siamese student encoders and EMA teacher network.
result Siamese student encoders improve representation separability and learning speed.
JEPAs learn data density by predicting perturbed samples, enabling density estimation.
problem Representation collapse in latent spaces.
method Combines latent-space prediction and anti-collapse terms to estimate data density.
result JEPAs can estimate sample probabilities efficiently and in closed-form.
UWM-JEPA predicts future scenarios in belief space, improving accuracy in partially observed environments.
problem Predicting future scenarios in partially observed environments with uncertainty.
method Introduces UWM-JEPA, a JEPA world model with a density-matrix latent and learned unitary predictor.
result UWM-JEPA achieves 0.77 accuracy on a hidden-velocity indicator task, outperforming LSTM-JEPA.
T-JEPA learns tabular data representations without augmentations, outperforming traditional methods.
problem Challenges in self-supervised learning for tabular data due to lack of data augmentations.
method T-JEPA uses a Joint Embedding Predictive Architecture (JEPA) to predict latent representations of different subsets of features within the same sample.
result Significant improvement in classification and regression tasks, outperforming traditional methods.
JEPA fails to improve language model performance when fine-tuning.
problem Improving language model performance through latent representation learning.
method Testing various training-time auxiliaries on natural-language-to-regex generation.
result No auxiliary improves cross-entropy gradient cosine with decoder visibility.
A new approach to protein language models combines latent space prediction with masked language modeling.
problem Improving protein language models by predicting amino acid identities at masked positions.
method A variant of masked language modeling that predicts latent targets only at masked positions, retaining the MLM cross-entropy.
result The new approach outperforms pure masked language modeling on 11 out of 16 downstream tasks.
SPLICE generates accurate time-series imputations with reliable prediction intervals.
problem Lack of reliability guarantees in time-series imputation models.
method Modular framework combining latent generative imputation with distribution-free prediction intervals.
result SPLICE achieves lowest mean Load-only MSE and best CRPS on various datasets.
LeJEPA provides a scalable, theory-driven approach to self-supervised learning.
problem Lack of practical guidance and theory in JEPAs.
method Identified optimal Gaussian distribution and introduced SIGReg objective.
result LeJEPA achieves state-of-the-art performance with minimal hyperparameters and heuristics.
This work improves AI's ability to solve physical tasks by optimizing world models in abstracted spaces.
problem Developing AI agents capable of solving diverse physical tasks and generalizing to new environments.
method Investigates and optimizes a family of joint-embedding predictive world models (JEPA-WMs) for efficient planning in abstracted spaces.
result Proposes a model that outperforms two established baselines in both navigation and manipulation tasks.
Future autonomous systems need reliable world models and complex action sequences.
problem Current automated systems lack reliable world models and complex action sequences.
method Introduce energy-based and latent variable models combined in a hierarchical joint embedding predictive architecture (H-JEPA).
result Combining energy-based and latent variable models in H-JEPA can lead to reliable world models and complex action sequences.
LaT-PFN model predicts time series with zero-shot capability.
problem Zero-shot time series forecasting.
method In-context latent space learning with JEPA and PFN integration.
result Superior zero-shot predictions compared to baselines.
Symbolic grounding in causal dynamics achieves near-infinite temporal consistency.
problem Achieving linear identifiability in non-Gaussian physical systems.
method Physics-Grounded Symbolic Architecture (PGSA)
result PGSA achieves exact linear identifiability for all physical regimes.
Proposes a new neural network architecture inspired by biology to improve learning and information flow.
problem Improving artificial neural networks to match biological neuron properties like multidirectional propagation and probabilistic modeling.
method Extends KAN approach with joint distribution neurons that can propagate values and distributions, including variance and higher-order moments.
result Proposed architecture can predict and propagate distributions, including expected values and variances.
ST-STORM separates semantic and appearance features for robust representation learning.
problem Traditional SSL methods fail to capture appearance cues in critical applications.
method Hybrid SSL framework with two latent streams, Content and Style, disentangled through gating mechanisms.
result The Style branch effectively isolates complex appearance phenomena without degrading semantic performance.