6 papers · 1 filter
Outcome-Guided On-Policy Self-Distillation
ZheXu Wang, Mao-Lin Luo, Yankun Hong +6
On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiable Rewards (RLVR). However,…
RL Forgets! Towards Continual Policy Optimization
Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou +4
Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to for…
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
Hao Gu, Mao-Lin Luo, Zi-Hao Zhou +3
Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continu…
Weakly-Supervised Contrastive Learning for Imprecise Class Labels
Zi-Hao Zhou, Jun-Jie Wang, Tong Wei +1
Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. How…
Personalized Federated Learning via Learning Dynamic Graphs
Ziran Zhou, Guanyu Gao, Xiaohu Wu +1
Personalized Federated Learning (PFL) aims to train a personalized model for each client that is tailored to its local data distribution, learning fails to perform well on individu…
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Zi-Hao Zhou, Siyuan Fang, Zi-Jing Zhou +3
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-ar…