LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
hub
Learning multiple layers of features from tiny images
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
Backdoors can be realized as statistically natural latent directions in modern neural networks, achieving high attack success with negligible clean accuracy loss and resisting existing defenses.
Classification fields are infinite recursive hierarchical cluster structures generated by a local refinement rule, and a ReLU network predictor learned from finite prefixes can approximate the generator and extend it to deeper levels with exponential convergence in the completed cell metric.
DSBD distills a dual-aligned structural basis to adapt GNNs across graphs with structural distribution shifts, outperforming prior methods on benchmarks.
DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.
Spatial Prediction pretext task learns spatial structure in self-supervised learning by regressing relative position and scale between image views, yielding more structured representations and better generalization.
A bilevel method learns composite pretraining loss weights online via gradient alignment with a downstream objective, matching tuned baselines at roughly 30% extra cost over one training run.
R-SGD-Mini achieves O(1/T) convergence of expected squared gradient norm to a noise-dependent neighborhood in heavy-tailed settings by selecting the medoid gradient from M data chunks.
HDSD decouples parameter subspaces in vision-language models via a Feature Modulation Module, General Fusion Module with adaptive thresholds, and Hierarchical Learning Module with SVD scaling to minimize cross-task interference and achieve state-of-the-art class-incremental learning performance.
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
TINS improves OOD detection by learning negative semantics at test time with ID-prototype separation, cutting average FPR95 from 14.04% to 6.72% on the Four-OOD benchmark with ImageNet-1K.
citing papers explorer
-
LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
-
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
-
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
Backdoors can be realized as statistically natural latent directions in modern neural networks, achieving high attack success with negligible clean accuracy loss and resisting existing defenses.
-
Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
Classification fields are infinite recursive hierarchical cluster structures generated by a local refinement rule, and a ReLU network predictor learned from finite prefixes can approximate the generator and extend it to deeper levels with exponential convergence in the completed cell metric.
-
DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
DSBD distills a dual-aligned structural basis to adapt GNNs across graphs with structural distribution shifts, outperforming prior methods on benchmarks.
-
Understanding Generalization through Decision Pattern Shift
DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.
-
Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning
Spatial Prediction pretext task learns spatial structure in self-supervised learning by regressing relative position and scale between image views, yielding more structured representations and better generalization.
-
When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
A bilevel method learns composite pretraining loss weights online via gradient alignment with a downstream objective, matching tuned baselines at roughly 30% extra cost over one training run.
-
Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling
R-SGD-Mini achieves O(1/T) convergence of expected squared gradient norm to a noise-dependent neighborhood in heavy-tailed settings by selecting the medoid gradient from M data chunks.
-
Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
HDSD decouples parameter subspaces in vision-language models via a Feature Modulation Module, General Fusion Module with adaptive thresholds, and Hierarchical Learning Module with SVD scaling to minimize cross-task interference and achieve state-of-the-art class-incremental learning performance.
-
A Composite Activation Function for Learning Stable Binary Representations
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
-
TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection
TINS improves OOD detection by learning negative semantics at test time with ID-prototype separation, cutting average FPR95 from 14.04% to 6.72% on the Four-OOD benchmark with ImageNet-1K.