4 papers
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Song Lai, Haohan Zhao, Rong Feng +9
Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to ever-evolving downstream tasks. While exi…
Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
Song Lai, Zhe Zhao, Fei Zhu +3
Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stabili…
From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
Zhe Zhao, Haibin Wen, Pengkun Wang +8
Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization. However, current methods such as EoH and FunSearch mainly rely on pre…
FuXi-: Scaling Recommendation Model with Feature Interaction Enhanced Transformer
Yufei Ye, Wei Guo, Jin Yao Chin +8
Inspired by scaling laws and large language models, research on large-scale recommendation models has gained significant attention. Recent advancements have shown that expanding se…