PAPT uses adversarial prompt tuning on diffusion models to generate domain-style images while preserving category features, claiming superior single-domain generalization performance.
Surrogate gap minimization improves sharpness-aware training
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
MICViT outperforms CNN and transformer baselines on brain age prediction from multimodal 3D MRI by combining modality-specific and cross-modal local/global attention across three heterogeneous datasets.
FRPO applies a max-min robust optimization over KL-bounded policy neighborhoods during RLHF to reduce catastrophic forgetting of safety and accuracy under subsequent SFT or RL fine-tuning.
UniAlign improves robustness of deep learning NTC models under distribution shifts via domain alignment fine-tuning and stable ensembling, yielding 2.51% accuracy and 2.71% F1 gains over standard training on three public datasets.
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.
citing papers explorer
-
Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization
PAPT uses adversarial prompt tuning on diffusion models to generate domain-style images while preserving category features, claiming superior single-domain generalization performance.
-
Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI
MICViT outperforms CNN and transformer baselines on brain age prediction from multimodal 3D MRI by combining modality-specific and cross-modal local/global attention across three heterogeneous datasets.
-
Robust Policy Optimization to Prevent Catastrophic Forgetting
FRPO applies a max-min robust optimization over KL-bounded policy neighborhoods during RLHF to reduce catastrophic forgetting of safety and accuracy under subsequent SFT or RL fine-tuning.
-
UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts
UniAlign improves robustness of deep learning NTC models under distribution shifts via domain alignment fine-tuning and stable ensembling, yielding 2.51% accuracy and 2.71% F1 gains over standard training on three public datasets.
-
A Faster Path to Continual Learning
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.
-
Sharpness-Guided Group Relative Policy Optimization via Probability Shaping
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.