Preprint compares Banach, Hilbert and Euclidean domain adaptation
An L1 density regularizer beats an identical L2 ablation on every reported task, including 92.44% versus 89.80% on USPS to MNIST.
Stories per day · 30 days
Relatedadversarial-attacks1aime1auxiliary-rewards1banach1bosch1dataset-similarity1deep-learning1density-estimation1domain-adaptation1efficientnet1fine-tuning1forecasting1generalization1high-dimensional-statistics1indoor-localization1industrial-iot1manifold-learning1medical-image-classification1
17 stories, newest first · one card per story
Stories tagged #transfer-learning
EfficientNet variants evaluated for retinal disease classification from OCT images
B1 EfficientNet achieves highest accuracy for four-class SD-OCT classification, outperforming larger variants.
Dissertation explores bad minima in transfer learning via adversarial attacks
Adversarial attacks on transfer learning reveal a strong link between source generalization and successful transfer.
Auxiliary Rewards Improve Small-Language-Model Self-Improvement
UID-Conj. auxiliary rewards boost online adaptation and offline SFT by 2.08 and 1.93 points over baselines on AIME math tasks.
DISC combines time-series similarity metrics to predict transfer
After calibration, DISC scores pairs from metric values and tracks forecasting error better than any single metric.
Transfer learning improves VLC indoor localization on Bosch data
The authors report 47 percent better accuracy than a non-transfer model and model efficiency up to 67.5 percent in high noise.
Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning
Transfer from ridge-regression pretraining can achieve minimax-optimal scaling under power-law covariance shift.
Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training
Instrument-anchored LLM judges transfer counseling-quality ratings across domains and beat in-domain training.
Transfer Learning for Edge Classification on Dynamic Text-Attributed Graphs
Researchers show dynamic graph models transfer poorly and propose STSA for cross-domain edge classification.
Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
Sequential LoRA transfer from English PHQ-8 interviews to Chinese HAMD-17 consultations improves depression-score prediction with Qwen3.
Cross-sector generalization of accident-process role classification in occupational accident narratives
Task-adapted models classify French accident narratives across sectors at about 86% balanced accuracy.
BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings
BrainWideBench tests whether pretrained neural representations transfer across mice, behavior, dynamics, and anatomy.
How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?
Study shows pretraining gains for neural PDE surrogates depend on distribution shift type, target data budget, and whether source-target physics differ.
Transfer Learning for Evolving Domains
TrED formalizes transfer learning for domains whose data availability evolves over time, arguing classical settings are regimes along one trajectory, and remains unsolved.
Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness Modeling
Multi-task RNN architectures pooling sparse cultivar data improve grape cold-hardiness and budbreak prediction over single-task and scientific baselines.
Cross-modal learning for SAR target recognition using optical vision foundation models
Frozen DINOv3 optical prototypes supervise SAR target recognition without EO/SAR pairs, improving classification on the heavily imbalanced UNICORNv2 dataset.
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
Researchers introduce StudyBench, a physics benchmark showing self-evolution gains on textbook problems rarely transfer to olympiad-level questions.