Tag: Continual Learning

All the articles with the tag "Continual Learning".

• Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions

  Published: 7 May, 2025 |  at  09:31 AM

  

  85.11 🤔

  本文通过提出AI记忆系统的分类（参数、上下文结构化和非结构化）和六种基本操作（整合、更新、索引、遗忘、检索、压缩），系统化地综述了长期记忆、长上下文、参数修改和多源记忆等研究主题，并展望了未来方向。

• SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning

  Published: 11 May, 2025 |  at  11:16 AM

  

  79.36 🤔

  This paper introduces SEFE, a method combining Answer Style Diversification (ASD) to mitigate superficial forgetting and RegLoRA to address essential forgetting in Multimodal Continual Instruction Tuning, achieving state-of-the-art performance on the CoIN benchmark.

• Elastic Weight Consolidation for Full-Parameter Continual Pre-Training of Gemma2

  Published: 13 May, 2025 |  at  11:04 AM

  

  78.66 🤔

  This paper demonstrates that Elastic Weight Consolidation (EWC) applied to full-parameter continual pre-training of Gemma2 2B LLM mitigates catastrophic forgetting on English tasks while improving performance on Lithuanian language benchmarks during autoregressive pre-training on CulturaX data.

• The dynamic interplay between in-context and in-weight learning in humans and neural networks

  Published: 6 May, 2025 |  at  11:20 PM

  

  70.07 🤔

  本文通过神经网络中上下文学习（ICL）与权重学习（IWL）的动态交互，统一解释了人类学习中的组合性泛化、课程效应及灵活性与保留性权衡，为认知科学双过程理论提供了新视角。

• HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning

  Published: 13 May, 2025 |  at  11:21 AM

  

  65.63 🤔

  HINT proposes a continual learning framework using interval arithmetic in embedding space with a hypernetwork to generate target network weights, achieving improved scalability and non-forgetting guarantees over InterContiNet while outperforming several benchmarks, though struggling with complex datasets.