Task-Core Memory Management and Consolidation for Long-term Continual Learning

Documenti analoghi

• CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
  di: Huai, Tianyu, et al.
  Pubblicazione: (2025)
• Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
  di: Zhan, Bihao, et al.
  Pubblicazione: (2025)
• Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
  di: Yin, Jianghao, et al.
  Pubblicazione: (2026)
• Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback
  di: Yang, Yutao, et al.
  Pubblicazione: (2025)
• Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
  di: Cai, Yuxuan, et al.
  Pubblicazione: (2025)