Residual Learning

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 143% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 103

All topics

LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression
Oct 8, 2026Rahul Goswami, Aryan Bhambu, Bittu KarmakarTabular Regression Residual Learning
Indian Institute of Technology Guwahati · SAFIR, Sorbonne University Abu Dhabi · Indian Institute of Technology Bombay
Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher
Oct 8, 2026Bowen Zheng, Zhiguang Liu, Jiarong Ou +2Video Diffusion Models Video Generation
The Chinese University of Hong Kong, Shenzhen · Tencent Hunyuan
RISR: Residual-Informed Scientific Equation Discovery with Large Language Models
Oct 8, 2026Haobo Li, Wenshuo Zhang, Wenxiao Zhao +6Symbolic Regression Large Language Model-Guided Scientific Discovery
Shanghai AI Laboratory · The Hong Kong University of Science and Technology · University of California, Los Angeles
CARE: A Lightweight Plug-in Gated Correction and Uncertainty-aware Module for Long-term Time Series Forecasting
Oct 8, 2026Guo Cheng, Changlong Lv, Jingyi HouMultivariate Time Series Forecasting Long-Term Time Series Forecasting
School of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China · Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China · Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education, University of Science and Technology Beijing, Beijing 100083, China
Temporal Residual Bottleneck for Robust Asynchronous Collaborative Perception
Oct 7, 2026Melih Yazgan, Ahmed Abouelazm, J. Marius ZöllnerCooperative Perception Autonomous Driving Perception
FZI Research Center for Information Technology · Karlsruhe Institute of Technology
Residual Learning in Empirical Asset Pricing
Oct 7, 2026Dexin Peng, Xiaoyu WangQuantitative Finance Residual Learning
FinTech Thrust, Hong Kong University of Science and Technology (Guangzhou)
LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models
Sep 30, 2026Junyi Zou, Avrova DonzMeta-Learning Residual Learning
MMLA-org · Communication University of China (CUC), No. 1 Dingfuzhuang East Street, Chaoyang District, Beijing 100024, China
RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
Sep 30, 2026Hao-Nan Shi, Tong Wu, Chen-Cong Sun +3Residual Learning Time Series Forecasting
School of Artificial Intelligence, Nanjing University · National Key Laboratory for Novel Software Technology, Nanjing University · Nanjing, China
ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image Compression
Sep 30, 2026Qin Yan, Ruixiao Dong, Yutao Xie +5Learned Image Compression Residual Learning
University of Science and Technology of China · Alibaba Group
Task-Relevant Null-Space Residuals for Non-Injective Neural Mappings
Sep 29, 2026Bizu Feng, Zhimu Yang, Shuming Wang +4Residual Learning
Institute of Artificial Intelligence Innovation and Industry, Fudan University, Shanghai, China · Shanghai Academy of AI for Science, Shanghai, China · Human Phenome Institute, Fudan University, Shanghai, China +1
LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction
Sep 28, 2026Binbin Yong, Zhao Su, Lan Guo +3Invertible Neural Networks Residual Learning
Lanzhou University · Monash University · University of Wollongong
Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers
Sep 27, 2026Tongtong Liang, Siqi Kou, Ziqiao Xi +6Diffusion Transformer Residual Learning
UC San Diego · Shanghai Jiao Tong University · Aether AI
EPOC: Endpoint-Preserving Online Correction With Compressed Residual State for Multi-Horizon Time Series Forecasting
Sep 25, 2026Takumi Fujimoto, Hiroaki NishiMultivariate Time Series Forecasting Residual Learning
School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University, Yokohama 223-8522, Japan · Department of System Design, Faculty of Science and Technology, Keio University, Yokohama 223-8522, Japan
The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning
Sep 23, 2026Kareem M. Gameel, Ihor Neporozhnii, Sjoerd Hoogland +1Residual Learning Scientific ML
Department of Physical and Environmental Sciences, University of Toronto Scarborough Alliance for AI-Accelerated Materials Discovery (A3MD) Toronto, Ontario, Canada · Alliance for AI-Accelerated Materials Discovery (A3MD) Toronto, Ontario, Canada · Department of Chemistry, University of Toronto Department of Physical and Environmental Sciences, University of Toronto Scarborough Alliance for AI-Accelerated Materials Discovery (A3MD) Toronto, Ontario, Canada
M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
Sep 23, 2026Vinícius da Silva, Isabelle Melo, Matheus Bessa +8Implicit Neural Representations 3D Reconstruction
PUC-Rio · Universidade Federal de Santa Maria · Google DeepMind +2
Shaft-Configuration-Adaptive Catheter Tip Position Estimation via Motor-History Conditioned Residual Learning
Sep 22, 2026Peihan Zhang, Michael C. Yip, Ankur Kapoor +1Residual Learning Robotics
Digital Technology & Innovation, Siemens Healthineers, Princeton, NJ, USA. · Department of Electrical and Computer Engineering, University of California San Diego, United States.
Task-Oriented Active Learning of Residual Dynamics for Model Predictive Path Integral Control
Sep 16, 2026Nobuaki Aoki, Hojin Lee, Stefan Sosnowski +1Residual Learning Residual Dynamics Learning
Chair of Information-oriented Control (ITR), Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany · Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich, Munich, Germany
ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers
Sep 15, 2026Jim Berend, Reduan Achtibat, Daniel Schäffer +4Transformer Interpretability Residual Learning
Fraunhofer Heinrich Hertz Institute · DSC ScaDS.AI, Leipzig University · ICT Cluster, Singapore Institute of Technology, Singapore +3
Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations
Sep 14, 2026Vikram R. LakkavalliAudio Representation Learning Representation Learning
International Institute of Information Technology Bangalore, India
Rethinking Radiomap Blind Prediction with Limited Environment and Configuration Representations
Sep 10, 2026Xiaojie Li, Yu Han, Han Fang +3Residual Learning Cross-Domain Generalization
School of Information Science and Engineering, Southeast University, Nanjing 210096, China · National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China · School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China +2
Toward Reliable Railway-Bogie Response Prediction Using Multifidelity TDNN and Physics-Informed Residual Learning
Sep 10, 2026Gyeolhee Lee, Moosun Kim, Taewook Kwon +3Surrogate Modeling Residual Learning
Department of Automotive Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea · Korea Railroad Research Institute, 176 Cheoldobangmulgwan-ro, Uiwang-si, Gyeonggi-do 16105, Republic of Korea · Department of Future Mobility, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea
Structured Extrema Errors in Classical Surrogates for Viscous Burgers: A Physics-Consistent Interpretation
Sep 7, 2026Youssef OubariKernel Ridge Regression Surrogate Modeling
IMT Atlantique, France
ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality
Sep 7, 2026Yoga Suhas Kuruba Manjunath, Jie Gao, Lian ZhaoResidual Learning Encrypted Network Traffic Analysis
School of Information Technology, Carleton University, Ottawa, ON, K1S 5B6, Canada · Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON M5B 2K3, Canada
RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting
Sep 3, 2026Yuchen He, Yueyang Cang, Zhiyuan Ning +2Multivariate Time Series Forecasting Residual Learning
Department of Automation, Tsinghua University · State Key Laboratory of Hydroscience and Engineering, Tsinghua University
Residual neural networks overcome the curse of dimensionality for semilinear heat equations
Sep 3, 2026Ilkhom Mukhammadiev, Diyora SalimovaNeural PDE Solvers PDE Solving
Department of Applied Mathematics, University of Freiburg, Germany
Correlated initialization of deep residual networks
Sep 3, 2026Felix Benning, Ivan Nourdin, Giovanni PeccatiNeural Network Initialization Residual Learning
oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions
Sep 2, 2026Haoqiang Guo, Xuyi Chen, Bo Ke +5Hyper-Connections Transformer
The Hong Kong University of Science and Technology · Baidu Inc.
Residual Kalman Dynamics for Event-Based UAV Forecasting
Sep 1, 2026Per Nyblom, Hannes Ovrén, David GustafssonEvent-Based Vision Kalman Filtering
Swedish Defence Research Agency (FOI), Linköping, Sweden
PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert
Aug 31, 2026Heng Yao, Siyun Hou, Tianying Liu +8Residual Learning Gradient Interference
Ant Group · Henan Polytechnic University · Independent Researcher +1
Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting
Aug 11, 2026Kiran Madhusudhanan, Christian Klötergens, Lars Schmidt-Thieme +1Long-Term Time Series Forecasting Normalizing Flows
Institute of Computer Science University of Hildesheim Hildesheim, Germany

Oct 8, 2026, stat.MLJ/K move · Enter open · S save

LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression

Rahul Goswami, Aryan Bhambu, Bittu Karmakar

Indian Institute of Technology Guwahati · SAFIR, Sorbonne University Abu Dhabi · Indian Institute of Technology Bombay

Tabular Regression Residual Learning Neural Network Robustness

Open paper AskPDF arXiv

Deep randomized models fix hidden-layer parameters through random initialization and learn only closed-form readouts, typically adding depth by stacking random trans formations without target-aware control of hidden-state evolution. We propose LAIR Net, the Leaky Alignment-Impulse Residual Network, which mixes a shallow learned anchor into each hidden state through a leaky residual transition. We derive a depth uniform bound on input-perturbation sensitivity and use controlled simulations to attribute gains over a randomized baseline to the anchor rather than recursion or added capacity. Benefits emerge when a nonlinear target structure is learnable at the available noise level and diminish for nearly linear targets or dominant noise. Across 23 benchmark datasets, LAIR-Net achieves the best average rank among eight randomized networks and twelve conventional models, with relative performance associated with the same nonlinear-structure and noise quantities identified in simulation.

Momentum

Related topics

Latest papers 103