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 Baseline reference
Learning multiple layers of features from tiny images
Baseline reference. 64% of citing Pith papers use this work as a benchmark or comparison.
57
Pith papers citing it
Baseline
64% of classified citations
hub tools
citation-role summary
dataset 8
other 2
background 1
citation-polarity summary
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.
Introduces an SDE-based framework for score-based generative modeling that unifies prior methods, enables predictor-corrector sampling and neural ODE likelihoods, and achieves SOTA unconditional image generation on CIFAR-10.
A hypothesis-testing framework with class-restricted Donsker-Varadhan estimators provides optimal non-asymptotic confidence intervals and minimax lower bounds for black-box auditing of Rényi DP guarantees.
Vector quantization induces a structured partition of the representation space for composing heterogeneous multiclass calibration maps via shared codeword-dependent Dirichlet factors.
RoSHAP is a robust feature-ranking metric that summarizes the distributional properties of SHAP values via bootstrap resampling and asymptotic normality to reward active, strong, and stable features.
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
SubPopMark embeds verifiable subpopulation biases into distilled datasets via CVM and USTM optimization stages, allowing provenance inference through comparison of model output signatures against a reference behavior bank.
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.
ROSU derives a closed-form retain-neutral perturbation for min-max unlearning that bounds retain damage via curvature and improves performance when gradients are aligned.
AS-LoRA adaptively chooses which LoRA factor to update per layer and round using a curvature-aware second-order score, eliminating reconstruction error floors and improving performance in DP federated learning.
Sparse Backdoor plants a provably undetectable backdoor in neural network weights via structured sparse perturbations and isotropic Gaussian dithering, with detection hardness reduced to Sparse PCA.
A hierarchical adversarial fine-tuning method for VLMs aligns image and text embeddings at multiple hierarchy depths with theoretical margin connections to boost robustness to leaf and superclass attacks while using multiple trees for semantic variety.
DPCP delivers end-to-end differentially private conformal prediction sets that are tighter than split-based private methods under the same privacy budget while maintaining coverage under regularity conditions.
DSBD distills a dual-aligned structural basis to adapt GNNs across graphs with structural distribution shifts, outperforming prior methods on benchmarks.
ROI coding enables backdoor triggers to survive lossy compression by embedding malicious information into binary bitstreams via sample-specific or customized masks for both learned and traditional codecs.
BadSNN injects backdoors into spiking neural networks by adversarially tuning LIF neuron hyperparameters and optimizing triggers, achieving higher attack success than prior data-poisoning methods while remaining robust to common defenses.
Presents SimA, a score-based single-query membership inference attack for diffusion models and LDMs that uses denoiser output norm to reveal training set proximity and outperforms multi-query baselines on eight datasets.
CoDiRe blends VLM and target model predictions via MSP-based weighting and Optimal Transport rectification to enable stable continual test-time adaptation, outperforming CoTTA by 10.55% on ImageNet-C at 48% of the compute cost.
CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
COCOCO is a conformal framework for NeSy-CBMs that jointly conformalizes concepts and labels, reconciles them via deduction-abduction revision, and satisfies consistency, coverage, and conciseness while retaining distribution-free guarantees.
A new post-hoc alignment technique uses learnable anchors to capture token-level relative similarities between modalities, outperforming global alignment baselines on zero-shot classification, retrieval, and segmentation with scarce paired examples.
DarkLLM trains an LLM to generate language-driven adversarial perturbations that unify targeted, untargeted, segmentation, and multi-model attacks on foundation models.
Extends influence functions with a second-order pairwise interaction term that improves group attribution accuracy over simple summation on multiple model-dataset pairs and instruction-tuning selection tasks.
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.
-
Score-Based Generative Modeling through Stochastic Differential Equations
Introduces an SDE-based framework for score-based generative modeling that unifies prior methods, enables predictor-corrector sampling and neural ODE likelihoods, and achieves SOTA unconditional image generation on CIFAR-10.
-
Optimal Guarantees for Auditing R\'enyi Differentially Private Machine Learning
A hypothesis-testing framework with class-restricted Donsker-Varadhan estimators provides optimal non-asymptotic confidence intervals and minimax lower bounds for black-box auditing of Rényi DP guarantees.
-
Divide et Calibra: Multiclass Local Calibration via Vector Quantization
Vector quantization induces a structured partition of the representation space for composing heterogeneous multiclass calibration maps via shared codeword-dependent Dirichlet factors.
-
RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution
RoSHAP is a robust feature-ranking metric that summarizes the distributional properties of SHAP values via bootstrap resampling and asymptotic normality to reward active, strong, and stable features.
-
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
-
From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation
SubPopMark embeds verifiable subpopulation biases into distilled datasets via CVM and USTM optimization stages, allowing provenance inference through comparison of model output signatures against a reference behavior bank.
-
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.
-
Retain-Neutral Surrogates for Min-Max Unlearning
ROSU derives a closed-form retain-neutral perturbation for min-max unlearning that bounds retain damage via curvature and improves performance when gradients are aligned.
-
Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning
AS-LoRA adaptively chooses which LoRA factor to update per layer and round using a curvature-aware second-order score, eliminating reconstruction error floors and improving performance in DP federated learning.
-
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
Sparse Backdoor plants a provably undetectable backdoor in neural network weights via structured sparse perturbations and isotropic Gaussian dithering, with detection hardness reduced to Sparse PCA.
-
Hierarchically Robust Zero-shot Vision-language Models
A hierarchical adversarial fine-tuning method for VLMs aligns image and text embeddings at multiple hierarchy depths with theoretical margin connections to boost robustness to leaf and superclass attacks while using multiple trees for semantic variety.
-
Differentially Private Conformal Prediction
DPCP delivers end-to-end differentially private conformal prediction sets that are tighter than split-based private methods under the same privacy budget while maintaining coverage under regularity conditions.
-
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.
-
Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
ROI coding enables backdoor triggers to survive lossy compression by embedding malicious information into binary bitstreams via sample-specific or customized masks for both learned and traditional codecs.
-
BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron
BadSNN injects backdoors into spiking neural networks by adversarially tuning LIF neuron hyperparameters and optimizing triggers, achieving higher attack success than prior data-poisoning methods while remaining robust to common defenses.
-
Score-based Membership Inference on Diffusion Models
Presents SimA, a score-based single-query membership inference attack for diffusion models and LDMs that uses denoiser output norm to reveal training set proximity and outperforms multi-query baselines on eight datasets.
-
Test-Time Distillation for Continual Model Adaptation
CoDiRe blends VLM and target model predictions via MSP-based weighting and Optimal Transport rectification to enable stable continual test-time adaptation, outperforming CoTTA by 10.55% on ImageNet-C at 48% of the compute cost.
-
Towards Generalized Certified Robustness with Multi-Norm Training
CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
-
Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
COCOCO is a conformal framework for NeSy-CBMs that jointly conformalizes concepts and labels, reconciles them via deduction-abduction revision, and satisfies consistency, coverage, and conciseness while retaining distribution-free guarantees.
-
Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data
A new post-hoc alignment technique uses learnable anchors to capture token-level relative similarities between modalities, outperforming global alignment baselines on zero-shot classification, retrieval, and segmentation with scarce paired examples.
-
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
DarkLLM trains an LLM to generate language-driven adversarial perturbations that unify targeted, untargeted, segmentation, and multi-model attacks on foundation models.
-
Interaction-Aware Influence Functions for Group Attribution
Extends influence functions with a second-order pairwise interaction term that improves group attribution accuracy over simple summation on multiple model-dataset pairs and instruction-tuning selection tasks.
-
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.
-
Detecting Adversarial Data via Provable Adversarial Noise Amplification
A provable adversarial noise amplification theorem under sufficient conditions enables a custom-trained detector that identifies adversarial examples at inference time using enhanced layer-wise noise signals.
-
CLion: Efficient Cautious Lion Optimizer with Enhanced Generalization
CLion achieves O(1/N) generalization error and O(√d / T^{1/4}) convergence for nonconvex stochastic optimization, improving on Lion's O(1/(N τ^T)) bound.
-
Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation
SAAD adaptively weights adversarial training samples by their transferability to the teacher, yielding higher AutoAttack robustness than prior distillation methods on CIFAR and Tiny-ImageNet without extra compute.
-
Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection
Cross-matrix Krylov projection reuses shared subspaces from seed matrices to accelerate score pre-computation in diffusion models, delivering 15.8-43.7% time savings and up to 115x speedup versus DDPM baselines.
-
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
NPN introduces a neural-network-based regularization that promotes reconstructions lying in a low-dimensional projection of the sensing operator's null-space, with claimed theoretical guarantees and improved empirical performance across compressive sensing, deblurring, super-resolution, CT, and MRI.
-
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.
-
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
-
2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
-
Why CNN Features Are not Gaussian: A Statistical Anatomy of Deep Representations
CNN feature activations follow long-tailed Weibull-like distributions with increasing tail dependence by depth rather than Gaussian, indicating a Matthew process that concentrates signal in tails.
-
Learning Color Equivariant Representations
Presents hue-, saturation-, luminance-equivariant GCNNs via a direct-image lifting layer that resolves invalid RGB issues in prior CEConv work and reports better OOD generalization plus sample efficiency.
-
ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and ImageNet-1K.
-
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
-
Axiomatizing Neural Networks via Pursuit of Subspaces
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
-
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
-
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.
-
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.
-
Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations
MEFA enables exact full-gradient white-box attacks on iterative stochastic purification defenses like diffusion and Langevin EBMs by trading recomputation for lower memory, revealing vulnerabilities missed by approximate-gradient methods.
-
BADiff: Bandwidth Adaptive Diffusion Model
BADiff introduces joint training of diffusion models with quality conditioning derived from bandwidth to enable adaptive early-stop sampling that preserves appropriate perceptual quality.
-
TOAST: Transformer Optimization using Adaptive and Simple Transformations
TOAST approximates full transformer blocks in pretrained models via lightweight closed-form mappings to cut parameters and FLOPs without retraining or finetuning.
-
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.