paper-with-me

홈 › Papers

Interactive Continual Learning: Fast and Slow Thinking

2024-03-05 · CVPR 2024 1 · Biqing Qi, Xingquan Chen, Junqi Gao, Dong Li, Jianxing Liu, Ligang Wu, BoWen Zhou

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.

📄 PDF Abstract BibTeX arXiv:2403.02628

Code (1)

biqing-qi/interactive-continual-learning-fast-and-slow-thinking 공식 구현 pytorch

Tasks

Continual LearningOutlier DetectionRetrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

MistyPilot: An Agentic Fast-Slow Thinking LLM Framework for Misty Social Robots

2026-03-04 · Xiao Wang, Lu Dong, Jingchen Sun, Ifeoma Nwogu 외 arxiv

With the availability of open APIs in social robots, it has become easier to customize general-purpose tools to meet users' needs. However, interpreting high-level user instructions, selecting and configuring appropriate…

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

2023-05-27 · NeurIPS 2023 11 · Bill Yuchen Lin, Yicheng Fu, Karina Yang, Faeze Brahman 외

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of …

Decoder

MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy

2026-06-26 · Zhiyuan Han, Beier Zhu, Wenwen Tong, Chengwei Qin 외 arxiv

We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for reasoning-based MLLMs, fast…

Multimodal Emotion RecognitionReinforcement Learning

Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning

2026-01-14 · Yang Li, Aming Wu, Zihao Zhang, Yahong Han arxiv

Vision-Language Navigation (VLN) aims to enable agents to navigate to a target location based on language instructions. Traditional VLN often follows a close-set assumption, i.e., training and test data share the same st…

Vision-Language Navigation

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

2024-10-31 · Ming Li, Yanhong Li, Tianyi Zhou

What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs), through the lens of gradient, when training with different responses and ini…