Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation
"模型泛化" 相关文章
Partial Domain Adaptation via Importance Sampling-based Shift Correction
Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms
Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
Why do Mechanistic Interpretability?
Narrow Misalignment is Hard, Emergent Misalignment is Easy
Single-Domain Generalization for Multimodal Cross-Cancer Prognosis via Dirac Rebalancer and Distribution Entanglement
ICML 2025 | Entropy不灵了？北大港中文用“区域置信”重新定义模型的不确定性
Mitigating Shortcut Learning with InterpoLated Learning
Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization
英伟达笑到最后！训练2000步，1.5B逆袭7B巨兽，Scaling真来了
TTS和TTT已过时？TTRL横空出世，推理模型摆脱「标注数据」依赖，性能暴涨
The Overlap Paradigm: Rethinking Data's Role in Weak-to-Strong Generalization (W2SG)
Enhancing Language Model Performance and Diversity Through Multiagent Fine-Tuning
Researchers from CMU and Bosch AI Introduce New Insights on Test-Time Adaptation for Distribution Shifts
让模型预见数据分布变化，东京大学等提出时态域泛化全新框架
MOS-Bench: A Comprehensive Collection of Datasets for Training and Evaluating Subjective Speech Quality Assessment (SSQA) Models
【机器学习】深入理解机器学习中的欠拟合与过拟合
NeurIPS 2024 | FaceChain团队新作，开源拓扑对齐人脸表征模型TopoFR
Learning by Self-Explaining (LSX): A Novel Approach to Enhancing AI Generalization and Faithful Model Explanations through Self-Refinement
