UR-JEPA applies uniform rectifiability regularization via a smoothed Carleson square function to JEPA training, producing embeddings with 4-5 order PCA spectral drop at dimension 20-25 and lower seed variance than Gaussian regularization on Inet10, Galaxy10, and EuroSAT.
Title resolution pending
21 Pith papers cite this work. Polarity classification is still indexing.
21
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 21roles
background 3polarities
background 3representative citing papers
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
Creativity is defined as meta-learning where a frozen diffusion creator optimizes candidates for rapid improvement by an adapting appraiser such as an autoencoder or CLIP adapter.
NTM models each generative reverse step as a conditional normalizing flow with a hybrid shallow-deep architecture, enabling exact-likelihood training and strong four-step sampling performance on text-to-image tasks.
Masked-position MLM plus JEPA latent prediction outperforms MLM-only pretraining on 10-11 of 16 downstream tasks for 35M-150M protein models while JEPA alone fails.
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
ScaleAware-JEPA combines Constrained Diffusion Decomposition with a scale-tied JEPA objective to learn label-free latent coordinates that recover coherent morphology in multiscale fields such as MHD turbulence and interstellar gas.
LEASE achieves state-of-the-art unified performance on ImageNet-1K by combining masked token reconstruction and codebook contrast losses in a one-time precomputed discrete token space.
SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
IA-JEPA applies motion-centric masking in JEPA to focus on entity interactions, reporting 14.26% causal reasoning accuracy on CLEVRER versus 3.22% for standard baselines plus higher latent entropy and R²=0.43 energy linearization.
LeNEPA proposes a no-augmentation next-latent prediction recipe that maintains frozen-probe performance across ECG and synthetic diagnostic time-series datasets under fixed-recipe conditions where a tuned JEPA baseline degrades.
Video foundation models encode intuitive physics knowledge that is strongest in V-JEPA at intermediate-to-late layers and depends on pretraining type and probe design.
Self-supervised pre-training delivers large gains up to 375% on time series anomaly detection and classification but only marginal benefits for forecasting, driven by a precision-invariance trade-off in the learned representations.
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries visibly alter hidden-state geometry.
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
LLM agents use a Cartesian split between learned prediction and engineered control, enabling modularity but creating sensitivity and bottlenecks unlike integrated biological systems.
PANC augments Normalized Cut with anchor-augmented token graphs using priors to steer spectral partitions, yielding mIoU gains of 2.3-8.7% over baselines on DUTS-TE, DUT-OMRON, and CrackForest.
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
Survey summarizing performance metrics of fully connected QNNs, quantum CNNs, equivariant QNNs, quantum Hopfield networks, quantum Boltzmann machines, quantum reservoir computing, and composite networks for reinforcement, generative, and transfer learning.
citing papers explorer
-
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.