Representation Alignment

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 82

All topics

HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning
May 8, 2026Jiseok Youn, You Rim Choi, Goodsol Lee +3Meta-Learning OOD Generalization
Department of ECE and INMC, Seoul National University, Seoul, South Korea · Graduate School of Data Science, Seoul National University, Seoul, South Korea · Department of Computer Science, University of Colorado Boulder, CO, USA
Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment
May 7, 2026Fred Zhangzhi Peng, Alexis Fox, Anru R. Zhang +1Masked Diffusion Models Diffusion Language Models
Duke University · AITHYRA
Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models
May 7, 2026Izaldein Al-Zyoud Abdulmotaleb El SaddikVision Foundation Models Representation Alignment
MCRLab, School of Electrical Engineering and Computer Science University of Ottawa, Ottawa, ON, Canada
From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
May 7, 2026Xinghao Wu, Jianwei Niu, Guogang Zhu +3Representation Alignment Federated Learning
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100091, China · Zhongguancun Laboratory, Beijing 100194, China · Center for AI Business Innovation, Department of Management Science and Systems, School of Management, University at Buffalo, NY 14260 USA
Enabling Federated Inference via Unsupervised Consensus Embedding
May 7, 2026Yui Hashimoto, Takayuki Nishio, Yuichi Kitagawa +1Ensemble Learning Privacy-Preserving ML
School of Engineering, Institute of Science Tokyo, Tokyo 152-8550, Japan · Research & Development Group, Hitachi Ltd., Tokyo 185-8601, Japan
Beyond Activation Alignment: The Geometry of Neural Sensitivity
May 4, 2026Amirhossein Yavari, Farnaz Zamani EsfahlaniNeural Representation Geometry Neural Decoding
Stephenson School of Biomedical Engineering, University of Oklahoma · Data Science and Analytics Institute, University of Oklahoma
SRA: Span Representation Alignment for Large Language Model Distillation
May 2, 2026Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi +4Cross-Tokenizer Knowledge Distillation Language Model Distillation
Hanoi University of Science and Technology · VNU University of Engineering and Technology · Monash University
Cross-Subject Generalization for EEG Decoding: A Survey of Deep Learning Methods
Apr 29, 2026Taida Li, Yujun Yan, Fei Dou +2Cross-Subject EEG Decoding EEG Decoding
Department of Computer Science, University of North Carolina at Charlotte, Charlotte, United States · Department of Computer Science, Dartmouth College, Hanover, United States · School of Computing, University of Georgia, Athens, United States +1
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
Apr 29, 2026Yanyun Wang, Qingqing Ye, Li Liu +2Adversarial Training Neural Network Robustness
1HK PolyU · 2HKUST (GZ) · 2HKUST (GZ
Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
Apr 27, 2026Shun Shao, Binxu Wang, Shay B. Cohen +2LLM Interpretability Mechanistic Interpretability
University of Cambridge · Kempner Institute, Harvard University · University of Edinburgh +1
Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference
Apr 21, 2026François RemyInterpretable ML Multi-Vector Retrieval
Parallia AI
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
Apr 20, 2026A. Sophia Koepke, Daniil Zverev, Shiry Ginosar +1Cross-Modal Learning Cross-Modal Representation Learning
UC Berkeley · Technical University Munich, MCML · University of Tübingen, Tübingen AI Center +1
Aligning Backchannel and Dialogue Context Representations via Contrastive LLM Fine-Tuning
Apr 17, 2026Livia Qian, Gabriel SkantzeSpeech Language Models Multimodal Contrastive Learning
Department for Speech, Music and Hearing KTH Royal Institute of Technology, Sweden
Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
Apr 17, 2026Chi Liu, Xin Chen, Xu Zhou +2LLM Compression Language Model Distillation
PayPal AI
RefAlign: Representation Alignment for Reference-to-Video Generation
Mar 26, 2026Lei Wang, YuXin Song, Ge Wu +5Diffusion Model Alignment Video Diffusion Models
1PCA Lab, VCIP, College of Computer Science, Nankai University, China · Baidu Inc., China · College of Artificial Intelligence, Jilin University, China +1
Logit Distance Bounds Representational Similarity
Feb 17, 2026Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele +2Representational Similarity Analysis Representation Learning
IT University of Copenhagen, Denmark · University of Trento, Italy · University of Copenhagen, Denmark +2
Modeling The Object Representations Underlying Human Physical Reasoning
Feb 12, 2026Andrey Gizdov, Andrea Procopio, Lorenzo Caputi +4Physical Reasoning Computational Cognitive Modeling
Harvard University · Weizmann Institute of Science · Bocconi University
Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
Feb 5, 2026Kevin Lu, Jannik Brinkmann, Stefan Huber +4Protein Structure Prediction AI-Assisted Scientific Research
1Northeastern University · 2TU Clausthal · 3Harvard University +2
Are Whitepaper Claims Reflected in Market Structure? A Contamination-Aware Pipeline and a Power-Limited Null
Jan 28, 2026Murad FarzullaData Contamination Representation Alignment
Dissensus, London, UK · King’s College London, London, UK
Uncovering the Computational Ingredients of Human-Like Representations in LLMs
Oct 1, 2025Zach Studdiford, Timothy T. Rogers, Kushin Mukherjee +1LLM Evaluation LLM Fine-Tuning
University of Wisconsin–Madison · Stanford University
The Platonic Universe: Do Foundation Models See the Same Sky?
Sep 23, 2025UniverseTBD, :, Trinidad Borrell +11Cross-Modal Alignment Multimodal Model Evaluation
Independent Researcher · AstroAI · Harvard-Smithsonian CfA +4
From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning
Aug 7, 2025Jinda Liu, Yi Chang, Yuan WuMulti-Task Learning Low-Rank Adaptation
School of Artificial Intelligence, Jilin University · 2Southern University of Science and Technology · 3International Center of Future Science, Jilin University +1

May 8, 2026, cs.LGJ/K move · Enter open · S save

HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning

Jiseok Youn, You Rim Choi, Goodsol Lee, Sangtae Ha+2

Department of ECE and INMC, Seoul National University, Seoul, South Korea · Graduate School of Data Science, Seoul National University, Seoul, South Korea · Department of Computer Science, University of Colorado Boulder, CO, USA

Meta-Learning OOD Generalization Split Federated Learning Representation Alignment Federated Learning On-Device Inference+1

Open paper AskPDF arXiv

Mobile devices face diverse resource constraints and non-IID data class distributions, requiring fast on-device inference for local in-distribution (ID) classes and on-demand remote support for client-specific out-of-distribution (OOD) classes. Hybrid split federated learning (Hybrid SFL) couples personalized client-side front ends (supporting early exit) with a generalized server-side backend for fallback inference, balancing accuracy and cost. However, under client architectural heterogeneity, the existing hybrid SFL suffers from representation skew, where features from customized extractors fail to align in the shared space, leading to a sharp degradation in the server model responsible for OOD prediction. We propose HARMONY, the first hybrid SFL framework to support heterogeneous client architectures. HARMONY modifies meta-learning to simulate diverse extractors across parameters and architectures, and to learn to personalize. To mitigate representation skew, HARMONY conducts server-side contrastive learning to align extracted features, neither sacrificing clients' personalization nor sharing raw labels. Compared to the state of the art across multiple datasets and model families, HARMONY improves test accuracy by up to 43.0%/28.3% without/with OOD, respectively, while maintaining acceptable latency.

Momentum

Related topics

Latest papers 82