Gradient-guided diffusion sampling reduces extreme precipitation forecasts in data-driven weather models while producing more physically plausible changes than adversarial perturbations.
hub
An image is worth 16x16 words: Transformers for image recognition at scale
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
UMI enables zero-shot deployment of robot manipulation policies trained solely on portable human demonstrations captured with custom handheld grippers, supporting dynamic bimanual tasks across novel environments and objects.
Derives α^{-1/3} scaling for generalization error in online softmax classification from boundary layers in a teacher-student model.
GraphCBMs extend concept bottleneck models by building latent concept graphs to model correlations between concepts, yielding better image classification accuracy, more informative structure for interpretability, and stronger intervention results.
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
WCR is a new training regularizer that concentrates weight magnitudes onto few parameters to improve one-shot pruning robustness under aggressive sparsity.
Optimal softmax temperature is analytically determined by feature dimensionality, adjusted by fitted coefficients and batch norm for model- and domain-robust classification.
Standalone 16-bit precision neural network training matches the accuracy of 32-bit and mixed-precision training while increasing computational speed.
citing papers explorer
-
Guided Diffusion Sampling for Precipitation Forecast Interventions
Gradient-guided diffusion sampling reduces extreme precipitation forecasts in data-driven weather models while producing more physically plausible changes than adversarial perturbations.
-
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
-
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
UMI enables zero-shot deployment of robot manipulation policies trained solely on portable human demonstrations captured with custom handheld grippers, supporting dynamic bimanual tasks across novel environments and objects.
-
A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
Derives α^{-1/3} scaling for generalization error in online softmax classification from boundary layers in a teacher-student model.
-
Graph Concept Bottleneck Models
GraphCBMs extend concept bottleneck models by building latent concept graphs to model correlations between concepts, yielding better image classification accuracy, more informative structure for interpretability, and stronger intervention results.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
-
CoCa: Contrastive Captioners are Image-Text Foundation Models
CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.
-
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
-
Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity
WCR is a new training regularizer that concentrates weight magnitudes onto few parameters to improve one-shot pruning robustness under aggressive sparsity.
-
Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification
Optimal softmax temperature is analytically determined by feature dimensionality, adjusted by fitted coefficients and batch norm for model- and domain-robust classification.
-
Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning
Standalone 16-bit precision neural network training matches the accuracy of 32-bit and mixed-precision training while increasing computational speed.