Domain Invariance

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 22

All topics

Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases
Sep 28, 2026Jiangtao Lin, Bangyang Wei, Yihang Ding +2Atlas Domain Invariance
Tsinghua Shenzhen International Graduate School, Tsinghua University · School of Vehicle and Mobility, Tsinghua University · SZ DJI Technology Co., Ltd. +1
PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics
Sep 21, 2026Henry KvingePretraining Permutation
Pacific Northwest National Laboratory · University of Washington
Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates
Sep 17, 2026Yuhei Fujioka, Daitaro Misawa, Shingo FukumaMedical World Model Electronic Health Records
Cancerscan Inc., Tokyo, Japan · Kyoto University, Graduate School of Medicine, Kyoto, Japan · Hiroshima University, Graduate School of Biomedical and Health Sciences, Hiroshima, Japan
Predicting Train Delays in Finland Using Machine Learning and Weather Data
Sep 12, 2026Vinicius Pozzobon Borin, Jean Michel de Souza Sant'Ana, Nurul Huda MahmoodRelighting Weather Prediction
Centre for Wireless Communications, University of Oulu, Oulu, Finland
When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations
Sep 7, 2026Quentin Telnoff, Emanuela Boros, Mickaël Coustaty +3Interpretability Document
1L3i, University of La Rochelle · 2Itesoft
CoRCi: Cross-Reconstruction of Coherent Interests Modeling in Cross-Domain Sequential Recommendation
Aug 10, 2026Qingtian Bian, Tieying Li, Marcus de Carvalho +3Domain Invariance Domain-Specific Language
Nanyang Technological University Singapore · Northeastern University China · Shanghai University of Finance and Economics China
RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents
Jul 30, 2026Sihyung Yoon, Minjong Yoo, Sanghyun Ahn +2Robocasa Action Prediction
Department of Computer Science and Engineering, Sungkyunkwan University
FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection
Jul 24, 2026Md Redwanul Haque, Manzur Murshed, Manoranjan Paul +1Ai-Generated Image Detection Domain Invariance
Deakin University, Burwood, VIC, Australia · Charles Sturt University, Bathurst, NSW, Australia
WARP: Weight-Space Analysis for Recovering Training Data Portfolios
Jul 2, 2026Tzu-Heng Huang, Aditya Goyal, John Cooper +1Weight-Space Training Data
University of Wisconsin-Madison
Domain Generalization via Text-Anchored Information Bottleneck
Jul 2, 2026Eunyi Lyou, Yunjeong Choi, Junho Lee +1Multimodal Domain Generalization Domain Invariance
Seoul National University, Seoul, Republic of Korea
Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA
Jun 26, 2026Yicheng RuiDomain Invariance Spatiotemporal Representations
Tsung-Dao Lee Institute, Shanghai Jiao Tong University, Shanghai 201210, China
Selective Time Series Forecasting via Metalearning
Jun 22, 2026Ricardo Inácio, Vitor Cerqueira, Marília Barandas +1Time Series Forecasting Time Series
Faculdade de Engenharia da Universidade do Porto, Porto, Portugal · University of Coimbra, Portugal · Fraunhofer Portugal AICOS, Portugal
When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
May 28, 2026Vahideh ZolfaghariDeception Layer-Wise
Algoverse AI Research, Algoverse AI Research Mentorship Program, USA. · Medical Sciences Education Research Center, Mashhad University of Medical Sciences, Mashhad, Iran. · Student Research Committee, Department of Health Information Technology and Management, Medical Informatics, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Domain-Informed Representation for Evolutionary Sieving in Integral and Module Lattices
May 27, 2026Ahmad Tashfeen, Qi ChengDiffie-Hellman Post-Quantum Cryptography
University of Oklahoma, Norman OK 73019, USA
The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty
May 23, 2026Volodymyr OvcharovSubword Tokenization Natural Language Processing
LEX AI Platform, legal.org.ua · Kyiv, Ukraine
LLM Sparsity Prior for Robust Feature Selection
May 21, 2026Caleb Skinner, Yihan Guo, Meng LiLasso Feature Selection
Department of Statistics, Rice University, Houston, TX 77005 · Department of Computer Science, Rice University, Houston, TX 77005
GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery
May 21, 2026Zhiqing Hong, Zelong Li, Xiubin Fan +5Human Activity Recognition Domain Invariance
HKUST (GZ) Guangzhou, China · JD Logistics Beijing, China · Beijing Normal–Hong Kong Baptist University Zhuhai, China +2
Continual Learning of Domain-Invariant Representations
May 15, 2026Pascal Janetzky, Tobias Schlagenhauf, Stefan FeuerriegelReplay-Based Continual Learning Domain Invariance
LMU Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · Bosch Center for Artificial Intelligence, Renningen, Germany +1
TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection
May 9, 2026Farid Hazratian, Ali Zia, Hien Duy NguyenOut-Of-Distribution Domain Invariance
University of Tehran · Tehran, Iran · La Trobe University +3
Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning
May 9, 2026Zhen-Hao Xie, Yan Wang, Hao Sun +3Class-Incremental Learning Multimodal Domain Generalization
School of Artificial Intelligence and the State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China
Learning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognition
Sep 1, 2025Guangli Li, Canbiao Wu, Zhehao Zhou +3Electroencephalography Emotion Recognition
School of Biological Science and Medical Engineering, Hunan University of Technology, Zhuzhou 412008, China · School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China · Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, Shenzhen 518060, China +1
Generative Classifier for Domain Generalization
Apr 3, 2025Shaocong Long, Qianyu Zhou, Dexuan Zhang +1Multimodal Domain Generalization Domain Invariance
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China · College of Computer Science and Technology and the Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, China

Sep 28, 2026, cs.LGJ/K move · Enter open · S save

Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases

Jiangtao Lin, Bangyang Wei, Yihang Ding, Siyi Liu+1

Tsinghua Shenzhen International Graduate School, Tsinghua University · School of Vehicle and Mobility, Tsinghua University · SZ DJI Technology Co., Ltd.+1

Atlas Domain Invariance Plasticity

Open paper AskPDF arXiv

Task-specific fine-tuning can rewrite a language model's answers beyond the training task, complicating updates that must preserve existing behavior. We introduce ATLAS, which turns retained-domain representations into an input-dependent rule for task adaptation. An activation atlas supplies local reference centers and directional filters to a shared low-rank residual. Target supervision learns the residual, while retained geometry shapes its action throughout training and inference. On Qwen3-8B, ATLAS achieves lower mean retained-output Kullback-Leibler (KL) divergence than all seven published baselines at shared coding-performance requirements, with consistent advantages across multiple training seeds. Structural comparisons identify the contributions of retained reference states and directional conditioning, and answer-level analyses show fewer rewritten mathematical answers and more stable commonsense choices. Experiments spanning five backbones and two retained domains further demonstrate coding gains with reduced retained-output movement. With compact storage and modest decoding overhead, ATLAS provides a practical mechanism for acquiring specialized skills while maintaining continuity in existing responses.

Momentum

Related topics

Latest papers 22