KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models

• URL: http://arxiv.org/abs/2512.07437v1
• Date: Mon, 08 Dec 2025 11:13:15 GMT
• Title: KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models
• Authors: Chenwei Shi, Xueyu Luan,
• Abstract summary: Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-Arnold Perceptrons (MLPs)<n>This report serves as a preliminary study for future developments in KAN-based world models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: DreamerV3 is a state-of-the-art online model-based reinforcement learning (MBRL) algorithm known for remarkable sample efficiency. Concurrently, Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-Layer Perceptrons (MLPs), offering superior parameter efficiency and interpretability. To mitigate KANs' computational overhead, variants like FastKAN leverage Radial Basis Functions (RBFs) to accelerate inference. In this work, we investigate integrating KAN architectures into the DreamerV3 framework. We introduce KAN-Dreamer, replacing specific MLP and convolutional components of DreamerV3 with KAN and FastKAN layers. To ensure efficiency within the JAX-based World Model, we implement a tailored, fully vectorized version with simplified grid management. We structure our investigation into three subsystems: Visual Perception, Latent Prediction, and Behavior Learning. Empirical evaluations on the DeepMind Control Suite (walker_walk) analyze sample efficiency, training time, and asymptotic performance. Experimental results demonstrate that utilizing our adapted FastKAN as a drop-in replacement for the Reward and Continue predictors yields performance on par with the original MLP-based architecture, maintaining parity in both sample efficiency and training speed. This report serves as a preliminary study for future developments in KAN-based world models.

Related papers

• TruKAN: Towards More Efficient Kolmogorov-Arnold Networks Using Truncated Power Functions [0.5097809301149341]
  We propose TruKAN to address the trade-off between computational efficiency and adherence to Kolmogorov-Arnold Network (KAN) principles.<n>TruKAN replaces the B-spline basis in KAN with a family of truncated power functions derived from k-order theory.<n>Overall, TruKAN outperforms other KAN models in terms of accuracy, computational efficiency and memory usage on the complex vision task.
  arXiv  Detail & Related papers  (2026-02-02T19:33:02Z)
• Kolmogorov Arnold Networks and Multi-Layer Perceptrons: A Paradigm Shift in Neural Modelling [1.6998720690708842]
  The research undertakes a comprehensive comparative analysis of Kolmogorov-Arnold Networks (KAN) and Multi-Layer Perceptrons (MLP)<n>KANs utilize spline-based activation functions and grid-based structures, providing a transformative approach compared to traditional neural network frameworks.<n>The proposed study highlights the transformative capabilities of KANs in progressing intelligent systems.
  arXiv  Detail & Related papers  (2026-01-15T16:26:49Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• KANMixer: Can KAN Serve as a New Modeling Core for Long-term Time Series Forecasting? [17.96421618979159]
  We introduce KANMixer, a concise architecture integrating a multi-scale mixing backbone that fully leverages KAN's adaptive capabilities.<n>We show that KANMixer achieves state-of-the-art performance in 16 out of 28 experiments across seven benchmark datasets.
  arXiv  Detail & Related papers  (2025-08-03T04:03:13Z)
• Exploring Kolmogorov-Arnold Networks for Interpretable Time Series Classification [4.489167091323233]
  Kolmogorov-Arnold Networks (KANs) have been proposed as a more interpretable alternative to deep learning.<n>This paper explores the KAN architecture for time series classification utilising 117 datasets from UCR benchmark archive.
  arXiv  Detail & Related papers  (2024-11-22T13:01:36Z)
• KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter [49.85369344101118]
  We introduce KFD-NeRF, a novel dynamic neural radiance field integrated with an efficient and high-quality motion reconstruction framework based on Kalman filtering. Our key idea is to model the dynamic radiance field as a dynamic system whose temporally varying states are estimated based on two sources of knowledge: observations and predictions. Our KFD-NeRF demonstrates similar or even superior performance within comparable computational time and state-of-the-art view synthesis performance with thorough training.
  arXiv  Detail & Related papers  (2024-07-18T05:48:24Z)
• Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf Node [49.08777822540483]
  Fast feedforward networks (FFFs) exploit the observation that different regions of the input space activate distinct subsets of neurons in wide networks. We propose the incorporation of load balancing and Master Leaf techniques into the FFF architecture to improve performance and simplify the training process.
  arXiv  Detail & Related papers  (2024-05-27T05:06:24Z)
• Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt [103.58323875748427]
  This work offers a novel unsupervised pre-training solution for low-data regimes. Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models. Experimental results show that our method significantly boosts several QEIS models on three datasets.
  arXiv  Detail & Related papers  (2023-02-02T15:49:03Z)
• Edge-assisted Democratized Learning Towards Federated Analytics [67.44078999945722]
  We show the hierarchical learning structure of the proposed edge-assisted democratized learning mechanism, namely Edge-DemLearn. We also validate Edge-DemLearn as a flexible model training mechanism to build a distributed control and aggregation methodology in regions.
  arXiv  Detail & Related papers  (2020-12-01T11:46:03Z)
• FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining [65.39532971991778]
  We present an accuracy predictor that scores architecture and training recipes jointly, guiding both sample selection and ranking. We run fast evolutionary searches in just CPU minutes to generate architecture-recipe pairs for a variety of resource constraints. FBNetV3 makes up a family of state-of-the-art compact neural networks that outperform both automatically and manually-designed competitors.
  arXiv  Detail & Related papers  (2020-06-03T05:20:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.