Dynamic Neural Networks

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 56

All topics

Physics-Informed Neural Plasticity: PDE Solvers That Reshape Themselves
Oct 7, 2026Chun-Wun Cheng, Bingcheng Hu, Angelica I. Aviles-RiveroNeural PDE Solvers PDE Solving
Shanghai Normal University · YMSC, Tsinghua University
Stepped MoE: Segment-Level Routing with Configurable Inference Complexity
Oct 5, 2026Arnav Kundu, Zhaoyang Xu, Bairu Hou +3On-Device Language Model Inference Dynamic Neural Networks
Apple
Width Expansion as a Method for Class Incremental Learning
Sep 29, 2026A. L. S. Conde, Y. Elkhatib, C. M. RanieriClass-Incremental Learning Dynamic Neural Networks
Institute of Geosciences and Exact Sciences, São Paulo State University (UNESP), Av. 24-A, 1515, Rio Claro, 13506-692, SP, Brazil · School of Computing Science, University of Glasgow, Glasgow, G12 8QQ, Scotland, United Kingdom
NGN: Learning Neural Network Size as a Differentiable Count
Sep 23, 2026Lixing LiDynamic Neural Networks Neural Architecture Search
Cornell University Ithaca, NY 14853
HDND: Hierarchical Dynamic Neural Decoding for Multilingual Word/Character Retrieval from Non-Invasive Brain Recordings
Sep 21, 2026Yueyang Li, Shuran Chen, Wai Ting Siok +1Dynamic Neural Networks Neural Decoding
Department of Language Science and Technology, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China
Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation
Sep 9, 2026Sudaksh Kalra, Dolly SapraEfficient Neural Network Inference Dynamic Neural Networks
University of Amsterdam The Netherlands
Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models
Aug 27, 2026Frederik BerenzWorld Model Learning Dynamic Neural Networks
121-labs.com Remscheid, Germany
FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients
Aug 10, 2026Bostan Khan, Masoud DaneshtalabDynamic Neural Networks Communication-Efficient Distributed Training
Mälardalen University, Västerås, Sweden
Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers
Aug 9, 2026Yu Wang, Shengyao Zhuang, Xueguang Ma +4Model Compression Dynamic Neural Networks
University of Utah · 2The University of Queensland · University of Waterloo +1
Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks
Aug 5, 2026Sudip Laudari, Puspa Raj AdhikariDynamic Neural Networks Time Series Forecasting
Independent Researcher. · Advanced Materials Science and Engineering, Sungkyunkwan University.
NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning
Aug 5, 2026Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung +2Class-Incremental Learning Dynamic Neural Networks
Department of Computer Science Simon Fraser University · Department of Computer Science McGill Univeristy, Mila - Quebec AI Institute
The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections
Aug 4, 2026Marco Giunti, Fabrizia Giulia GaravagliaTransformer Inference Prompt Sensitivity
ALOPHIS – Applied Logic Philosophy and History of Science Università di Cagliari · Dip. di Pedagogia, Psicologia, Filosoﬁa Università di Cagliari
Plasticity of Growing and Elastic Neural Networks in Online Continual Learning
Aug 2, 2026Jeong Min Kong, Richard S. SuttonLoss of Plasticity Dynamic Neural Networks
Department of Electrical and Computer Engineering University of California, Los Angeles (UCLA) · Department of Computing Science University of Alberta Alberta Machine Intelligence Institute (Amii)
SILVA Networks as Structured Implicit Layers and Vector Attractors via Dynamic Interaction Fields
Jul 31, 2026Jose Luis Lima de Jesus SilvaGraph Neural Networks Implicit Neural Representations
Federal University of Bahia, Department of Geophysics, Salvador, BA 40170-115, Brazil · Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA), Federal University of Bahia, Salvador, BA 40170-115, Brazil
Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation
Jul 27, 2026Jyotiranjan Beuria, Amit ShuklaDynamic Neural Networks Reservoir Computing
AutoNorm: Understanding Adaptive Normalization in Transformers through Differentiable Gating
Jul 12, 2026Piyush Kaushik Bhattacharyya, Divyanshu Rai, Swastik Singh +3Dynamic Neural Networks Transformer
Scalable Perturbation Learning for Online Self-Supervised Echo State Networks
Jul 7, 2026Taiki Yamada, Kantaro FujiwaraDynamic Neural Networks Self-Supervised Learning
Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, 113-8656, Tokyo, Japan
Approximating velocity fields with planted attractors via Neural-ODEs for classification purposes
Jun 22, 2026Feliciano Giuseppe Pacifico, Duccio Fanelli, Lorenzo Buffoni +3Dynamic Neural Networks Classification
Department of Informatics and Computer Science, University of Pisa, Italy · Department of Physics and Astronomy, University of Florence, Sesto Fiorentino, Italy · INFN, Italy
Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks
Jun 19, 2026Jiacheng Wang, Xinjia He, Qi Ding +5Dynamic Neural Networks Continual Learning
East China Normal University · Fudan University · Ocean University of China
Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling
Jun 19, 2026Borui Cai, Yao ZhaoDynamical Systems Dynamic Neural Networks
Hangzhou International Innovation Institute, Beihang University, China · Victoria University, Melbourne, Australia
Explicit Interaction Architectures for Dynamical Learning: A Controlled Study of Structural Inductive Bias
Jun 17, 2026Augusto SartiDynamic Neural Networks Nonlinear System Identification
Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano, Piazza L. Da Vinci 32, 20133 Italy.
GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate
Jun 17, 2026Zirong LiDynamic Neural Networks Modular Neural Networks
Tiangong University
Scaling Adaptive Depth with Norm-Agnostic Residual Networks
Jun 15, 2026Tomás Figliolia, Beren MillidgeEfficient Neural Network Inference Dynamic Neural Networks
Zyphra San Francisco, CA
Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters
Jun 7, 2026Kohga Tanaka, Hiroaki NishiEfficient Neural Network Inference Dynamic Neural Networks
Graduate School of Science and Technology, Keio University, Kohoku-ku, Yokohama 223-8522, Japan · Department of System Design, Faculty of Science and Technology, Keio University, Kohoku-ku, Yokohama 223-8522, Japan
BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detection
Jun 4, 2026Wenlin Liu, Xikun Hu, Ping ZhongReinforcement Learning Dynamic Neural Networks
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Multi-Resolution End-to-End Deep Neural Network for Optimizing Latency-Accuracy Tradeoff in Autonomous Driving
May 27, 2026Qitao Weng, Heechul YunEfficient Neural Network Inference Adaptive Inference
University of Kansas Lawrence, KS, USA
Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
May 27, 2026Zhilong Zhang, Xinhui Zhang, Gongyu Jin +3Dynamic Neural Networks Semantic Communication
Beijing Laboratory of Advanced Information Network, and the Beijing Key Laboratory of Network System Architecture and Convergence, Beijing University of Posts and Telecommunications, Beijing 100876, China
Adaptive Reservoir Computing for Multi-Scenario Chaotic System Forecasting
May 27, 2026Shadmehr Zaregarizi, Khashayar YavariDynamic Neural Networks Forecasting Benchmarks
Politecnico di Torino Turin, Italy
ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion
May 25, 2026Sheng-Wei Chan, Hsin-Jui Pan, Chun-Po Shen +3Dynamic Neural Networks Convolutional Neural Networks
Department of Electrical and Computer Engineering, Tamkang University, No.151, Yingzhuan Rd., Tamsui Dist., New Taipei City,2026 251301, Taiwan.
Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning
May 24, 2026Tianwei Wang, Bryan Chen, Qian Zuo +3Dynamic Neural Networks Equivariant Neural Networks
School of Informatics University of Edinburgh · Bio-inspired Computing and Machine Learning (BCML) Lab · School of Mathematics University of Edinburgh +2

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

Physics-Informed Neural Plasticity: PDE Solvers That Reshape Themselves

Chun-Wun Cheng, Bingcheng Hu, Angelica I. Aviles-Rivero

Shanghai Normal University · YMSC, Tsinghua University

Neural PDE Solvers PDE Solving Physics-Informed ML Dynamic Neural Networks

Open paper AskPDF arXiv

Physics-informed neural PDE solvers adapt their parameters to satisfy governing equations, yet their representational structure typically remains fixed throughout training. This rigidity is poorly matched to PDE solutions with strongly heterogeneous complexity across space and space--time, leaving capacity insufficient where the physics is difficult and redundant where it is simple. We introduce physics-informed neural plasticity, a paradigm in which the representation itself reshapes during optimization in response to unresolved physics. We instantiate this principle with Representation Capacity Adaptation for PDEs (ReCAP), a Gaussian-localized solver that dynamically redistributes capacity through local enrichment, residual-directed splitting, gate-based pruning, and function-aware merging. ReCAP uses responsibility-weighted error indicators and the geometry of residual energy to determine where and how to refine. To limit the disturbance introduced by splitting, we introduce quiet-child refinement, which initializes new components by transporting the parent representation while controlling instantaneous functional perturbation. We further establish conditional a posteriori reliability and structural-stability guarantees linking localized physics residuals to solution error and stable refinement. Across five challenging 3D and 4D PDE benchmarks against 11 physics-informed solvers, ReCAP achieves the lowest relative

L^2

error on every problem, reducing error by

10.7\%

27.5\%

relative to the strongest competing result. These results suggest that physics-informed solvers need not merely learn their parameters---they can learn how their representational capacity should be organized.

Momentum

Related topics

Latest papers 56