COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

↘ Related papers

• Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
  Fei Wang56% match
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
  Zhenwen Liang49% match
• Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
  Jacob Morrison41% match
• MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment
  Andor Vári-Kakas39% match
• Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems
  Beining Wu37% match