# Interactive Continual Learning: Fast and Slow Thinking

arXiv: https://arxiv.org/abs/2403.02628 · HTML: https://mlsanity.com/paper/2403.02628/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 53 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)

## Built on by (most cited first, 23 of 23)

- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM](https://mlsanity.com/paper/2410.15549/) (2024)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs](https://mlsanity.com/paper/2510.16062/) (2025)
- [Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding](https://mlsanity.com/paper/2406.12295/) (2024)
- [Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking](https://mlsanity.com/paper/2407.13188/) (2024)
- [An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2411.06659/) (2024)
- [Towards Building Specialized Generalist AI with System 1 and System 2 Fusion](https://mlsanity.com/paper/2407.08642/) (2024)
- [Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning](https://mlsanity.com/paper/2403.04140/) (2024)
- [DSADF: Thinking Fast and Slow for Decision Making](https://mlsanity.com/paper/2505.08189/) (2025)
- [Towards Incremental Learning in Large Language Models: A Critical Review](https://mlsanity.com/paper/2404.18311/) (2024)
- [SMR: State Memory Replay for Long Sequence Modeling](https://mlsanity.com/paper/2405.17534/) (2024)
- [T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval](https://mlsanity.com/paper/2508.01680/) (2025)
- [Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback](https://mlsanity.com/paper/2505.09925/) (2025)
- [Asynchronous Perception Machine For Efficient Test-Time-Training](https://mlsanity.com/paper/2410.20535/) (2024)
- [SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning](https://mlsanity.com/paper/2601.01392/) (2026)
- [SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning](https://mlsanity.com/paper/2408.01970/) (2024)
- [Cognitive Duality for Adaptive Web Agents](https://mlsanity.com/paper/2508.05081/) (2025)
- [Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations](https://mlsanity.com/paper/2512.08548/) (2025)
- [ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing](https://mlsanity.com/paper/2604.21280/) (2026)
- [Learning Dynamic Representations via An Optimally-Weighted Maximum Mean Discrepancy Optimization Framework for Continual Learning](https://mlsanity.com/paper/2501.12121/) (2025)
- [Ken Utilization Layer: Hebbian Replay Within a Student's Ken for Adaptive Exercise Recommendation](https://mlsanity.com/paper/2507.00032/) (2025)

## Abstract (arXiv)

Advanced life forms, sustained by the synergistic interaction of neural cognitive mechanisms, continually acquire and transfer knowledge throughout their lifespan. In contrast, contemporary machine learning paradigms exhibit limitations in emulating the facets of continual learning (CL). Nonetheless, the emergence of large language models (LLMs) presents promising avenues for realizing CL via interactions with these models. Drawing on Complementary Learning System theory, this paper presents a novel Interactive Continual Learning (ICL) framework, enabled by collaborative interactions among models of various sizes. Specifically, we assign the ViT model as System1 and multimodal LLM as System2. To enable the memory module to deduce tasks from class information and enhance Set2Set retrieval, we propose the Class-Knowledge-Task Multi-Head Attention (CKT-MHA). Additionally, to improve memory retrieval in System1 through enhanced geometric representation, we introduce the CL-vMF mechanism, based on the von Mises-Fisher (vMF) distribution. Meanwhile, we introduce the von Mises-Fisher Outlier Detection and Interaction (vMF-ODI) strategy to identify hard examples, thus enhancing collaboration between System1 and System2 for complex reasoning realization. Comprehensive evaluation of our proposed ICL demonstrates significant resistance to forgetting and superior performance relative to existing methods. Code is available at github.com/ICL.