No article text was recorded for this version.
cross-architecture generalization gap
Version 2 of 2191 papers234 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study
- Blog: Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation
- Blog: Dataset Distillation: A Comprehensive Review
- Blog: Data Distillation: A Survey
- Blog: Data Distillation: A Survey
- Blog: DC-BENCH: Dataset Condensation Benchmark
- Blog: Mixmix: All you need for data-free compression are feature and data mixing
- Blog: Mix, Don’t Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining
- Blog: Utility Boundary of Dataset Distillation: Scaling and Configuration-Coverage Laws
- Blog: MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalization
- Blog: Private Set Generation with Discriminative Information
- Blog: DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
- Blog: Mix, Don’t Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining
- Blog: Mirage: Model-Agnostic Graph Distillation for Graph Classification
- Blog: Dataset Distillation via Adversarial Prediction Matching
- Blog: Dataset Distillation by Automatic Training Trajectories
- Blog: Generative Dataset Distillation Based on Self-knowledge Distillation
- Blog: Learning from Dense Events: Towards Fast Spiking Neural Networks Training via Event Dataset Distillation
- Blog: Towards Model-Agnostic Dataset Condensation by Heterogeneous Models
- Blog: Video Set Distillation: Information Diversification and Temporal Densification
- Blog: A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation
- Blog: What is Dataset Distillation Learning?
- Blog: Improving Dataset Distillation
- Blog: Copyright-Certified Distillation Dataset: Distilling One Million Coins into One Bitcoin with Your Private Key
- Blog: Dataset Distillation using Neural Feature Regression
- Blog: The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions
- Blog: Generalizing Dataset Distillation via Deep Generative Prior
- Blog: Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
- Blog: MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
- Blog: MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
- Blog: Utility Boundary of Dataset Distillation: Scaling and Coverage Laws
- Blog: Distributional Dataset Distillation with Subtask Decomposition
- Blog: ATOM: Attention Mixer for Efficient Dataset Distillation
- Blog: Does Graph Distillation See Like Vision Dataset Counterpart?
- Blog: Self-Supervised Dataset Distillation for Transfer Learning
- Blog: Heavy Labels Out! Dataset Distillation with Label Space Lightening
- Blog: Distilling EEG representations via capsules for affective computing
- Blog: Graph Condensation via Eigenbasis Matching
- Blog: Mirage: Model-agnostic Graph Distillation for Graph Classification
- Blog: Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalization
- Blog: Towards Pre-trained Graph Condensation via Optimal Transport
- Blog: Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation
- Blog: Dataset Quantization
- Blog: Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
- Blog: The Devil in the Details: Simple and Effective Optical Flow Synthetic Data Generation
- Blog: Dataset Distillation for Super-Resolution without Class Labels and Pre-trained Models
- Blog: Dataset Distillation as Pushforward Optimal Quantization
- Blog: OPTICAL: Leveraging Optimal Transport for Contribution Allocation in Dataset Distillation
- Blog: Dataset Distillation in Large Data Era
- Blog: Neural Spectral Decomposition for Dataset Distillation
- Blog: Dataset Distillation Using Parameter Pruning
- Blog: FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
- Blog: Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning
- Blog: SecDD: Efficient and Secure Method for Remotely Training Neural Networks
- Blog: Generative Conversational Networks
- Blog: Generalizing Dataset Distillation via Deep Generative Prior
- Blog: GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
- Blog: EDITS: Enhancing Dataset Distillation with Implicit Textual Semantics
- Blog: Training-free Heterogeneous Graph Condensation via Data Selection
- Blog: Dataset Distillation for Pre-Trained Self-Supervised Vision Models
Showing 60 of 191 papers.
History & citation
Current · Permanent link
- Scaling Dataset Distillation with Decoupled Pipelines merged into this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_architecture_generalization_gap_e920e673,
title = {cross-architecture generalization gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-generalization-gap/rdr_e920e67334eb4bb788ac8e71968ca653},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_cross_architecture_generalization_gap_e920e673_v2,
title = {cross-architecture generalization gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-generalization-gap/rdr_e920e67334eb4bb788ac8e71968ca653/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}