LGM-Net learns transferable prior knowledge for few-shot learning.
problem Few-shot classification with limited training data.
method Meta-learning approach with TargetNet and MetaNet modules.
result LGM-Net achieves competitive performance on unseen tasks.
Extends hyperparameter transfer across model sizes and modules, improving training speed.
problem Training stability and performance of large-scale models with optimal hyperparameters.
method Complete(d) Parameterisation, per-module hyperparameter optimisation and transfer. result Hyperparameter transfer holds even in the per-module hyperparameter regime, improving training speed.
We develop differential algebraic K-theory for rings of integers in number fields and we construct a cycle map from geometrized bundles of modules over such a ring to the differential algebraic K-theory. We also treat some of the foundational aspects of differential cohomology, including differential function spectra a…
New method estimates MTF from photos without expensive equipment.
problem Costly MTF measurement limits lens performance evaluation.
method Custom grid display for ground truth, CNN for MTF estimation.
result Estimates MTF from natural images, generalizes to unseen lenses.
Proves finiteness and holonomicity of skein modules for 3-manifolds.
problem Finiteness and holonomicity of skein modules for 3-manifolds.
method Defining skein transfer bimodules and using q-analogues of D-module theory.
result Internal skein modules are holonomic modules over the internal skein algebra of the boundary.
PICLE uses probabilistic models to efficiently evaluate and compose modules for continual learning.
problem Challenging search space of module compositions in continual learning.
method Probabilistic framework to cheaply compute module compositions' fitness.
result First modular CL algorithm to achieve perceptual, few-shot, and latent transfer.
A modular GP framework for efficient transfer learning.
problem Efficiently transfer knowledge across different tasks or datasets.
method Modular variational Gaussian processes (GPs) with a dictionary of well-fitted GPs.
result Reduces computational costs and allows the transfer of uncertainty metrics.
KM method reduces ConvNet parameters to 9% higher accuracy with minimal additional memory.
problem Expensive memory usage for training ConvNets on embedded devices.
method Kernel Modulation (KM) method that adapts all network parameters for each task.
result KM delivers up to 9% higher accuracy than other parameter-efficient methods.
Adapters add few trainable parameters per task, improving NLP performance.
problem Parameter inefficiency in fine-tuning large pre-trained models for multiple downstream tasks.
method Adapter modules that add only a few trainable parameters per task, allowing for high parameter sharing and task extensibility.
result Adapters achieve near state-of-the-art performance with minimal additional parameters.
Paper proposes a method to transfer semantic information between weather conditions for vehicle control.
problem Poor generalization of end-to-end supervised learning for self-driving cars under different weather conditions.
method Divide vehicle control into two modules: a control module trained on one weather condition and a perception module using GANs for new conditions.
result Proposed method achieves similar steering angle prediction results as an end-to-end model trained with 15 different weather conditions.
Skip connections make adversarial examples more transferable in ResNets.
problem Transferability of adversarial examples in ResNets with skip connections.
method Skip Gradient Method (SGM) to craft more transferable adversarial examples.
result SGM improves transferability of adversarial examples in various DNNs.
Modular deep learning framework using pairwise labels without backpropagation.
problem Efficiently training deep neural networks with limited supervision.
method Stacked linear models in feature spaces, provably optimal modular learning framework.
result High accuracy (94.88%) achieved with minimal labeled examples (1 per class).
This paper tackles continuous domain adaptation with a new approach.
problem Learning in non-stationary environments, especially domain drift.
method Variational domain-agnostic feature replay, composed of inference, generative, and solver modules.
result Demonstrates the effectiveness of the proposed approach for practical usage.
MAES architecture improves working memory task performance through multi-task and transfer learning.
problem Improving performance on complex working memory tasks.
method Memory-Augmented Encoder-Solver (MAES) architecture with dual recurrent neural network controllers and a shared memory module.
result MAES models achieve task-size generalization, handling inputs 50 times longer than training data.
JSCN improves cross-domain recommendation by learning domain-invariant user representations.
problem Cross-domain recommendation data sparsity and domain-incompatibility issues.
method JSCN uses multi-layer spectral convolutions on different graphs to learn domain-invariant user representations and domain adaptive user mappings.
result Significant improvement in cross-domain recommendation performance (9.2% recall, 36.4% MAP improvements).
Develops HMRL for sparse reward RL problems, improving meta policy efficiency and transferability.
problem Difficulty in learning meta policies for sparse reward RL problems.
method Hyper-Meta RL framework with cross-environment meta state embedding and shaped meta reward.
result Improves meta policy generalization and efficiency for sparse reward RL problems.
New model improves transfer learning and semi-supervised learning.
problem Improving transfer learning and semi-supervised learning performance.
method Developed a new conditional energy-based model (ICE-BeeM) based on nonlinear ICA.
result Identifiable representations learned by ICE-BeeM improve performance in transfer learning and semi-supervised learning tasks.
PTU learns fine-grained parameter transfer for deep networks.
problem Discrete transfer states and lack of principled approach to learn transfer strategies.
method PTU learns a fine-grained nonlinear combination of activations from source and target networks using two gates.
result PTU outperforms heuristic methods in most settings.
HOUDINI learns algorithms across domains using program synthesis.
problem Lifelong learning of algorithmic tasks mixing perception and reasoning.
method Combining gradient descent with combinatorial search over programs.
result HOUDINI transfers high-level concepts more effectively than traditional methods.
A framework for using auxiliary data to improve few-shot learning.
problem Few-shot learning with scarce labeled examples and abundant auxiliary data.
method Automatic pseudo-shot selection and masking module to adjust auxiliary features.
result Masking module improves accuracy by 4.68 and 6.03 percentage points.
AReLU uses attention-based rectification to improve neural network performance.
problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.
New method automates asymmetric choice for better skill transfer in reinforcement learning.
problem Improving sample efficiency and transferability of reinforcement learning agents.
method Attentive Priors for Expressive and Transferable Skills (APES) using hierarchical KL-regularization.
result APES automates asymmetric choice, leading to better skill transfer across sequential tasks.
Extends micro-price concept to RFQ markets for fair pricing.
problem Valuing securities in illiquid RFQ markets.
method Bidimensional Markov-modulated Poisson processes for liquidity.
result Introduces Fair Transfer Price for fair securities valuation.
FRA-Attack improves adversarial transferability for closed-source MLLMs by aligning visual focus across models.
problem Improving adversarial transferability for closed-source MLLMs, especially with high accuracy.
method Unified frequency-domain regularization approach: high-pass DCT objective for feature alignment and Frequency-domain Gradient Regularization (FGR) for gradient optimization.
result FRA-Attack achieves superior cross-model transferability, especially on GPT-5.4, Claude-Opus-4.6, and Gemini-3-flash.
TAP transfers knowledge from unlabeled data to improve cross-modal learning.
problem Improving supervised learning performance using unlabeled data from a different modality.
method Probabilistic approach for missing information estimation, kernel regression, cross-attention module, TAP neural network.
result TAP significantly improves generalization across different domains and neural network architectures.
Fused Encoder Networks improve momentum strategies on crypto data.
problem Deploying momentum strategies on crypto data with limited samples leads to over-fitted models.
method Hybrid transfer learning model combining source and target datasets.
result Fused Encoder Networks outperform classical momentum strategies and benchmarks.
Defines super projective modules and explores their properties.
problem Exploring the geometric-algebraic link in super geometry.
method Defined and explored super projective modules over supersmooth functions.
result Module of vector fields over a supersphere is a super projective module.
Paper proposes a time-frequency analysis method for blind modulation classification in MIMO systems.
problem Blind modulation classification in MIMO systems with overlapping signals and unknown channel parameters.
method Time-frequency analysis using windowed short-time Fourier transform, conversion to RGB spectrogram images, convolutional neural network for classification, decision fusion.
result Proposed scheme achieves high classification accuracy at different SNRs, outperforming existing methods.
FedCONST adapts update magnitudes to enhance feature generalization in FL.
problem Heterogeneous client data in FL leads to overfitting and distorted transferable features.
method FedCONST uses linear convex constraints to stabilize training and preserve generalization.
result FedCONST enhances feature transferability and robustness, achieving state-of-the-art performance.
SA-GAN improves HAR model performance across new users.
problem Poor performance of HAR models on new user data.
method Generative Adversarial Network (GAN) for cross-subject transfer learning.
result SA-GAN outperformed other methods in HAR tasks.
A deep learning subsampling technique improves modulation classification accuracy.
problem Improving modulation classification accuracy in wireless communication systems.
method Proposes a data-driven subsampling strategy using deep neural networks to simulate signal removal.
result Improves classification accuracy to higher levels than traditional methods.
Vision transformers benefit from non-smooth components in adaptation.
problem Understanding the role of non-smoothness in vision transformer adaptation.
method Theoretical analysis and extensive experiments on large-scale vision transformers.
result High plasticity of attention modules and feedforward layers leads to better finetuning performance.
Proposes GPCA module for channel attention in CNNs using Gaussian processes.
problem Improving performance in visual tasks through effective channel selection.
method Integrates Gaussian processes into channel attention mechanisms for probabilistic modeling of channel correlations.
result Demonstrates improved performance of GPCA module in end-to-end CNN training.
Study shows stress affects emotion recognition models, improving generalizability.
problem Stress affects emotion recognition models, reducing their generalizability.
method Used adversarial networks to control for stress effects on emotion recognition.
result Emotion recognition models that control for stress during training have better generalizability.
New method for analyzing multiparameter persistence modules from smooth functions.
problem Analyzing multiparameter persistence modules from smooth functions.
method Generalized Morse theory applied to cobordism and Cerf theory.
result Complete description of persistence modules as direct sums of indecomposables.
Shape adaptor learns flexible resizing factors for neural networks.
problem Fixed resizing layers limit network performance.
method Learnable reshaping factor for traditional resizing layers.
result Performance increases consistently across multiple datasets.
Functional transfer matrices replace weights in neural networks, achieving high accuracy.
problem Representing connections in neural networks with functions instead of weights.
method Developed functional transfer matrices, stacked them with bias vectors and activations, and trained them using back-propagation.
result Deep functional transfer neural networks can be trained to achieve high test accuracies on the MNIST database.
The paper uses information theory to analyze neural processing systems.
problem Understanding how neural systems process information with contextual inputs.
method Applied a new information theory concept to decompose neural processing.
result Contextual modulation has unique information processing properties.
Study shows skein module dimensions for surface times circle.
problem Understanding skein modules of surface times circle.
method Used Kauffman bracket skein module over rational functions.
result Dimension at least 2^{2g+1}+2g-1 for Sigma x S^1.
Let {T1,…,Tn} be a set of n commuting bounded linear operators on a Hilbert space H. Then the n-tuple (T1,…,Tn) turns H into a module over C[z1,…,zn] in the following sense: \[\mathbb{C}[z_1, \ldots, z_n] \times \mathcal{H} \raro \clh, \quad \quad …
Localized transfer learning improves nonparametric regression performance.
problem Improving nonparametric regression performance on target tasks.
method Localized transfer learning framework that models heterogeneity and partition covariate space into cells.
result Sharp minimax rates show local transfer mitigates the curse of dimensionality.
Algorithm recovers independent causal mechanisms from transformed data.
problem Learning independent causal mechanisms from data.
method Unsupervised algorithm based on competing experts.
result Learned mechanisms generalize to novel domains.
L2T learns to automatically decide what and how to transfer knowledge.
problem Optimal transfer learning algorithm selection is computationally intractable.
method L2T framework learns transfer learning skills through meta-cognitive reflection and optimizes them for new domains.
result L2T outperforms state-of-the-art transfer learning algorithms and discovers more transferable knowledge.
Proposes a new method to improve target annotation in ATR.
problem Challenges in annotating automatic target recognition due to lack of labeled data.
method Hybrid contrastive learning and cycle-consistency-based transductive transfer learning (C3TTL) framework.
result Significantly lower Fréchet Inception Distance (FID) score and improved performance in annotating civilian and military vehicles, as well as ship targets.
Paper proposes using logic networks to inject prior knowledge for better reinforcement learning.
problem Improving reinforcement learning agents with prior knowledge of object and event semantics.
method Integrates first-order logic grounded in deep neural networks as prior knowledge into reinforcement learning algorithms.
result Demonstrates that combining symbolic and image layers in a single decision module improves learning efficiency.
We show that for the Kauffman bracket skein module over the field of rational functions in variable A, the module of a connected sum of 3-manifolds is the tensor product of modules of the individual manifolds.
Deep learning animates objects from input images and videos.
problem Animating arbitrary objects from input images and videos.
method A deep learning framework with three modules: Keypoint Detector, Dense Motion prediction network, and Motion Transfer Network.
result Our method outperforms state-of-the-art image animation and video generation methods.
Study improves hypothesis transfer learning for functional linear models.
problem Incompatible TL techniques for high-dimensional FLR methods due to infinite-dimensional nature of functional data.
method Proposes two algorithms for hypothesis transfer learning in RKHS framework, leveraging RKHS distance and aggregation techniques.
result Establishes asymptotic lower bounds and matching upper bounds for the proposed algorithms, demonstrating their effectiveness.