No article text was recorded for this version.
architectural generalization
Version 1 of 11,176 papers1,181 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE
- Blog: LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation
- Blog: The Master Key Filters Hypothesis: Deep Filters Are General
- Blog: IDSNN: Towards High-Performance and Low-Latency SNN Training via Initialization and Distillation
- Blog: Frequency-Dynamic Attention Modulation For Dense Prediction
- Blog: Event USKT : U-State Space Model in Knowledge Transfer for Event Cameras
- Blog: Examining the Combination of Multi-Band Processing and Channel Dropout for Robust Speech Recognition
- Blog: Robust Nonlinear Component Estimation with Tikhonov Regularization
- Blog: A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation
- Blog: Mapping the Multiverse of Latent Representations
- Blog: Neural Architecture Search as Program Transformation Exploration
- Blog: Domain-independent Dominance of Adaptive Methods
- Blog: Learning to Re-Rank with Contextualized Stopwords
- Blog: Understanding Neural Networks Through Deep Visualization
- Blog: DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
- Blog: A Principle of Least Action for the Training of Neural Networks
- Blog: Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport
- Blog: Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks
- Blog: Adaptive Transfer Learning: a simple but effective transfer learning
- Blog: End-to-End Speech Separation Using Orthogonal Representation in Complex and Real Time-Frequency Domain
- Blog: Towards Generalizable Medical Image Segmentation with Pixel-wise Uncertainty Estimation
- Blog: $\mu$PC: Scaling Predictive Coding to 100+ Layer Networks
- Blog: With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization
- Blog: Block Switching: A Stochastic Approach for Deep Learning Security
- Blog: Mixup-Based Deep Metric Learning Approaches for Incomplete Supervision
- Blog: Spatio-Temporal Filter Analysis Improves 3D-CNN for Action Classification
- Blog: Dynamic Network Adaptation at Inference
- Blog: Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
- Blog: Do deep nets really need weight decay and dropout?
- Blog: Predicting CNN Learning Accuracy Using Chaos Measurement
- Blog: EnResNet: ResNet Ensemble via the Feynman-Kac Formalism.
- Blog: BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
- Blog: Multi-view and Multi-source Transfers in Neural Topic Modeling with Pretrained Topic and Word Embeddings
- Blog: Symmetric block-low-rank layers for fully reversible multilevel neural networks
- Blog: Conditional Deformable Image Registration with Convolutional Neural Network
- Blog: Embeddings for Numerical Features Using tanh Activation
- Blog: Fast Trainable Projection for Robust Fine-Tuning
- Blog: Invariant Feature Learning for Sensor-Based Human Activity Recognition
- Blog: Stress and Adaptation: Applying Anna Karenina Principle in Deep Learning for Image Classification
- Blog: Exploiting Deep Representations for Neural Machine Translation
- Blog: The art of selecting the ECG input in neural networks to classify heart diseases: a dual focus on maximizing information and reducing redundancy
- Blog: TCCT: Tightly-coupled convolutional transformer on time series forecasting
- Blog: Efficient Training of BERT by Progressively Stacking
- Blog: Dual Contradistinctive Generative Autoencoder
- Blog: Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation
- Blog: Alignment of auditory artificial networks with massive individual fMRI brain data leads to generalizable improvements in brain encoding and downstream tasks
- Blog: Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
- Blog: Continual Learning with Strong Experience Replay
- Blog: Defensive approximation: securing CNNs using approximate computing
- Blog: WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting
- Blog: Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
- Blog: FedLE: Federated Learning Client Selection with Lifespan Extension for Edge IoT Networks
- Blog: Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks Under Latency Constraint
- Blog: Are Convolutional Neural Networks or Transformers more like human vision?
- Blog: Drawing early-bird tickets: Towards more efficient training of deep networks
- Blog: AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning
- Blog: Representation Shift: Unifying Token Compression with FlashAttention
- Blog: Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
- Blog: Capacity Bounds for the DeepONet Method of Solving Differential Equations
- Blog: UniForensics: Face Forgery Detection via General Facial Representation
Showing 60 of 1,176 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_generalization_6e8adfef,
title = {architectural generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-generalization/rdr_6e8adfef57b24ca1b19b929c14be4c5f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_architectural_generalization_6e8adfef_v1,
title = {architectural generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-generalization/rdr_6e8adfef57b24ca1b19b929c14be4c5f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}