Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning

Documenti analoghi

• SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
  di: Qiu, Haomiao, et al.
  Pubblicazione: (2025)
• Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
  di: Zhao, Jiaqi, et al.
  Pubblicazione: (2025)
• GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
  di: Bai, Yuyang, et al.
  Pubblicazione: (2026)
• Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes
  di: Jiang, Mingxuan, et al.
  Pubblicazione: (2025)
• FedDRL: A Trustworthy Federated Learning Model Fusion Method Based on Staged Reinforcement Learning
  di: Chen, Leiming, et al.
  Pubblicazione: (2023)