Spectral

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 67% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 156

All topics

Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation
May 13, 2026Minyoung Oh, Najeong Chae, Jae-Young SimDiffusion-Based Dataset Distillation Multimodal Domain Generalization
Graduate School of Artificial Intelligence Ulsan National Institute of Science and Technology (UNIST) Ulsan, Republic of Korea
Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations
May 12, 2026Tomasz Dądela, Adam Kania, Maciej Rut +1Neural Representations Spectral
Jagiellonian University IDEAS Kraków, Poland
The Routing and Filtering Structure of Attention
May 12, 2026Shafayeth Jamil, Rehan KapadiaKimi Delta Attention Decomposition
Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles, CA 90089
STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
May 12, 2026Joshua OpriaMelody Keystroke Dynamics
Independent Researcher
Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
May 12, 2026Alexander Yukhimchuk, Mladen Kolar, Martin Takáč +1Gradient Clipping Stochastic Gradient Descent
MBZUAI · University of Southern California
Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
May 11, 2026Nikolaos Nakis, Panagiotis Promponas, Konstantinos Tsirkas +4Graph Edge Sparsification Graph Representation Learning
Human Nature Lab, Yale University · Department of Electrical and Computer Engineering, Yale University · Department of Statistics and Data Science, Yale University +1
SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecasting
May 10, 2026Mingrui Zhang, Hanchen Yang, Wengen Li +4Time Series Forecasting Spatial Encoding
Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
May 8, 2026Clarissa Lauditi, Cengiz Pehlevan, Blake BordelonDeep Network Neural Network
John A. Paulson School of Engineering and Applied Sciences, Harvard University · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University · Center for Mathematical Sciences and Applications, Harvard University +1
Diagnosing Spectral Ceilings in Equivariant Neural Force Fields
May 8, 2026Hyunmog KimSpectral Neural Fields
Independent Researcher.
bispectrum: Selective $G$ -Bispectra Made Practical
May 8, 2026Johan Mathe, Adele Myers, Simon Mataigne +1Global Average Pooling Spherical Latent Space
Atmo, Inc. San Francisco, CA · UC Santa Barbara Santa Barbara, CA · UCLouvain Louvain-la-Neuve, Belgium
Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization
May 7, 2026Ruotong Sun, Ermin WeiSpectral Preconditioning Orthogonality
†Department of Industrial Engineering & Management Sciences, Northwestern University · ∗Department of Electrical & Computer Engineering, Northwestern University
Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization
May 7, 2026Andy Zeyi Liu, Elliot Paquette, John SousModel Activations Large Language Model Training
Department of Applied Physics, Yale University, New Haven, CT 06511, United States · Department of Mathematics and Statistics, McGill University · Department of Applied Physics, Yale University, New Haven, Connecticut 06511, USA +1
Distributional Spectral Diagnostics for Localizing Grokking Transitions
May 7, 2026Ziyue Wang, Yufeng Ying, Takafumi KanamoriGrokking Transformer Residual Streams
Institute of Science Tokyo · University of Science and Technology of China
Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics
May 6, 2026Dominik Dahlem, Diego Maniloff, Mac MisiuraLinear Attention Spectral
Red Hat AI
On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants
May 5, 2026Brian Keith-Norambuena, Juan Bekios-CalfaMulti-Label Classification Discriminative Models
Department of Computing & Systems Engineering, Universidad Cat´olica del Norte, Antofagasta, Chile.
Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal Representations
May 4, 2026Cameron Berg, Susan L. Schneider, Mark M. BaileyCoalition Formation Artificial Intelligence Agents
Reciprocal Research · New York, NY, USA · Center for the Future of AI, Mind, and Society +5
Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models
May 4, 2026Jose Vinicius Ribeiro, Rafael Figueira Goncalves, Fabio Luiz Melquiades +1Xai Explainability
Applied Nuclear Physics Laboratory · State University of Londrina · Dept. of Engineering and Architecture +2
How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse
May 3, 2026Xiaoxuan Ma, Yixuan Yang, Song Li +1Multi-Label Classification Neural Collapse
Department of Mathematics, Zhejiang University, Hangzhou, China.
Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations
May 2, 2026Pratyush Acharya, Nuraj Rimal, Habish DhakalToken Embeddings Spectral
An Efficient Metric for Data Quality Measurement in Imitation Learning
May 2, 2026Noushad Sojib, Momotaz BegumImitation Learning Imitation
Authors are with the Department of Computer Science, University of New Hampshire, USA
Spectral- and Energy-efficient Multi-BS Multi-RIS Pinching-antenna Systems: A GNN-based Approach
May 2, 2026Changpeng He, Yang Lu, Wei Chen +3Reconfigurable Intelligent Surfaces Beamforming
State Key Laboratory of Advanced Rail Autonomous Operation, and also with the School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China · School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, China · School of Electronic Engineering and Computer Science, Queen Mary University of London, London +2
SpecVQA: A Benchmark for Spectral Understanding and Visual Question Answering in Scientific Images
Apr 30, 2026Jialu Shen, Han Lyu, Suyang Zhong +5Textvqa Multimodal Large Language Models
DP Technology
Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model
Apr 27, 2026Maixent ChenebauxSmall Large Language Models Small Reasoning Model
Trickstr
Spectral Analysis of Fake News Propagation
Apr 18, 2026Weibin Cai, Reza ZafaraniFake News Detection Spectral
Data Lab, Department of EECS, Syracuse University, New York, USA.
Hyperspectral Unmixing Hierarchies
Apr 18, 2026Joseph L. Garrett, P. S. Vishnu, Pauliina Salmi +4Hyperspectral Image Two-Level Spatial-Frequency Fusion Strategy
Department of Engineering Cybernetics, Norwegian University of Science and Technology · Department of Biology, Norwegian University of Science and Technology · Department of Automatic Control and Systems Engineering, University Politehnica Bucharest +1
From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales
Mar 31, 2026Ivan Viakhirev, Kirill Borodin, Grach MkrtchianSpectral Attractors
Information Technologies, Mechanics and Optics University, Russia · lab260, Moscow Technical University of Communications and Informatics, Russia · BitmanagerAI, UAE
Spectral Hierarchy of the Cosmic Web
Mar 16, 2026Francisco-Shu Kitaura, Francesco SinigagliaHierarchical Spectral
Instituto de Astrofísica de Canarias, s/n, E-38205, La Laguna, Tenerife, Spain · Departamento de Astrofísica, Universidad de La Laguna, E-38206, La Laguna, Tenerife, Spain · Institute for Fundamental Physics of the Universe, Via Beirut 2, I-34151 Trieste, Italy +3
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
Mar 6, 2026Jingkai Wang, Yixin Tang, Jue Gong +6Real-World Image Super-Resolution Diffusion Transformers
Shanghai Jiao Tong University, China · Shenzhen Transsion Holdings Co., Ltd., China
Regular Fourier Features for Nonstationary Gaussian Processes
Feb 26, 2026Arsalan Jawaid, Abdullah Karatas, Jörg SeewigGaussian Process Kernel Method
Institute of Measurement and Sensor Technology, University of Kaiserslautern-Landau, Kaiserslautern, Germany · Independent Researcher, Mannheim, Germany
Grounded Laplacians of Directed Signed Matrix-Weighted Networks: Spectral Properties and Applications to Non-Trivial Consensus
Feb 12, 2026Tianmu Niu, Bing Mao, Hao Liao +2Graph Laplacians Lyapunov Function
Spectral Embedding via Chebyshev Bases for Robust DeepONet Approximation
Dec 9, 2025Muhammad Abid, Omer SanFourier Neural Operators Spectral Representation Method
Department of Mechanical and Aerospace Engineering, University of Tennessee, Knoxville, TN 37996, USA.
Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans
Oct 12, 2025Theo Di Piazza, Carole Lazarus, Olivier Nempont +1Cone-Beam Computed Tomography Cnn-Transformer Tradeoff
INSA Lyon, University of Lyon, CNRS, INSERM, CREATIS UMR 5220, U1294, Villeurbanne, France · Hospices Civil de Lyon, Lyon, France · Philips Clinical Informatics, Innovation Paris, France
Panorama: Fast-Track Nearest Neighbors
Oct 1, 2025Vansh Ramani, Alexis Schlomer, Akash Nayar +3Approximate Nearest-Neighbor Search Behavioral Embeddings
IIT Delhi & CMU & UCPH · Carnegie Mellon University · Indian Institute of Technology Delhi +1
Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
Sep 25, 2025Qiyu Chen, Guozhang ChenState Space Models Inductive Bias
School of Computer Science, National Key Laboratory for Multimedia Information Processing, Peking University, China · School of Physics, Peking University, China
Diffract: Spectral View of LLM Domain Adaptation
Date pendingNikita Borodin, Maria Krylova, Artem Zabolotnyi +6Large Language Model Adaptation Pretraining
Risk AI Research Lab · Applied AI Institute
SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models
Date pendingXingyan Li, Jordan A. Caraballo-Vega, Jie Gong +2Geospatial Foundation Models Parameter-Efficient Fine-Tuning Methods
University of Maryland, Baltimore County Baltimore, Maryland, USA · NASA Goddard Space Flight Center Greenbelt, Maryland, USA

May 13, 2026, cs.LGJ/K move · Enter open · S save

Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation

Minyoung Oh, Najeong Chae, Jae-Young Sim

Graduate School of Artificial Intelligence Ulsan National Institute of Science and Technology (UNIST) Ulsan, Republic of Korea

Diffusion-Based Dataset Distillation Multimodal Domain Generalization Dataset Distillation Spectral

Open paper AskPDF arXiv

Dataset Distillation (DD) synthesizes a compact synthetic dataset that preserves the training utility of a full dataset. However, its standard formulation assumes that test data follow the same distribution as training data, an assumption that rarely holds in practice. A straightforward extension-applying post-hoc Domain Generalization (DG) techniques to distilled data-is ill-suited because existing DG methods rely on the natural diversity of real datasets, which compact synthetic sets inherently lack, while also incurring substantial augmentation overhead that conflicts with the efficiency objective of dataset distillation. To address this limitation, we introduce Domain Generalizable Dataset Distillation (DGDD), a new problem setting that explicitly targets out-of-distribution (OOD) generalization of distilled datasets. We study this problem through a widely adopted DD baseline of Distribution Matching (DM). We attribute the OOD vulnerability of DM to the entanglement of class-discriminative and domain-specific information within the compressed synthetic set, and propose Spectral Gradient Surgery (SGS) to disentangle the two. The key insight of SGS is that cross-domain agreement among domain-wise gradients in the spectral domain reveals which gradient components are shared across source domains-and are therefore class-discriminative-and which are domain-specific. Based on this observation, SGS augments the standard DM update with two complementary gradients: one that reinforces cross-domain shared components and another that explicitly promotes diversity within the distilled dataset. Extensive experiments on diverse-scale benchmarks demonstrate that SGS substantially improves OOD generalization while remaining plug-and-play compatible with existing DM methods.

Momentum

Related topics

Latest papers 156