Unsupervised Learning

Follow this topic Ask about this topic

Momentum

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

Jul 13Week of Sep 28

Latest papers 41

All topics

Reason in Style: Discovering and Controlling Style in Language Models
Sep 30, 2026Ioana Marinescu, Eric Karl Oermann, Kyunghyun ChoUnsupervised Learning Language Model Steering
NYU · NYU & NYU Langone Health
TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception
Sep 25, 2026Quinlan Sykora, Sourav Biswas, Christopher Diehl +3Unsupervised Learning Autonomous Driving Perception
Waabi · University of Toronto
Generative Retrieval for Unsupervised Text-Based Person Search
Sep 14, 2026Mang Ye, Yucheng Ji, Yang Bai +4Unsupervised Learning Image-Text Retrieval
School of Computer Science, Wuhan University, Wuhan, China · School of Computer Science and Technology, Soochow University, SuZhou, China · Zhipu AI, Beijing 100089, China +1
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning
Sep 2, 2026Dong LaoUnsupervised Learning Self-Supervised Learning
Division of Computer Science and Engineering, Louisiana State University, Louisiana, USA.
Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes
Aug 2, 2026Aoting Zeng, Kai Wang, Jianwei Wang +3Unsupervised Learning Interpretable ML
Shanghai Jiao Tong University Shanghai, China · University of New South Wales Sydney, Australia
RAMP: Recognition parametrisation by Amortised Message Passing
Jul 21, 2026Lior Fox, Kai Biegun, James Heald +3Unsupervised Learning Latent Variable Models
1Gatsby Computational Neuroscience Unit · Centre for Artificial Intelligence University College London
AMICA-Python: Adaptive Mixture Independent Component Analysis with Anderson Acceleration
Jul 20, 2026Scott Huberty, Christian O'ReillyUnsupervised Learning Independent Component Analysis
University of Southern California, Los Angeles, CA, USA · University of South Carolina, Columbia, SC, USA
Converge to Surprise: Evolutionary Self-supervised Image Clustering
Jul 8, 2026Canlin Zhang, Xiuwen LiuUnsupervised Learning Self-Supervised Learning
Independent Researcher · Department of Computer Science Florida State University
On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other species?
Jul 7, 2026Ramon Ferrer-i-Cancho, Catherine Hobaiter, Thore Bergman +1Unsupervised Learning Reference-Free Evaluation
Universitat Politècnica de Catalunya, Department of Computer Science · University of St Andrews, School of Psychology and Neuroscience · University of Michigan, Departments of Psychology and Ecology and Evolutionary Biology +1
Unsupervised Pixel-Level Semantic Left-Right Understanding of In-the-Wild Images
Jul 6, 2026Weikang Wang, Tobias Weißberg, Florian BernardUnsupervised Learning
University of Bonn, Germany · Lamarr Institute, Germany
Neural Certificate Pricing for Combinatorial Optimization Problems
Jul 1, 2026Jingyi Chen, Xinyuan Zhang, Xinwu QianPrimal-Dual Optimization Unsupervised Learning
Department of Civil and Environmental Engineering, Rice University, Houston, TX
Cohort Organized Learning: Clustering Through Agreement
Jun 19, 2026Finn Henry O'Shea, Maria Elena MonzaniUnsupervised Learning Clustering
SLAC National Accelerator Laboratory, 2575 Sand Hill Road, Menlo Park, CA 94025-7015, USA · Kavli Institute for Particle Astrophysics and Cosmology, Stanford University, Stanford, CA 94305-4085 USA
Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
Jun 19, 2026Mathieu Cyrille Simon, Pascal Frossard, Christophe De VleeschouwerUnsupervised Learning Disentangled Representation Learning
1UCLouvain, ICTEAM, Louvain-la-Neuve, Belgium · 2EPFL, LTS4 laboratory, Lausanne, Switzerland.
Connecting Speech to Words through Images
Jun 15, 2026Gabriel Pirlogeanu, Dan Oneata, Horia Cucu +1Multimodal Grounding Unsupervised Learning
Speech and Dialogue Research Laboratory · POLITEHNICA Bucharest, Romania · Electrical and Electronic Engineering +1
Unsupervised Learning for Missing Modalities in Multimodal Learning
Jun 14, 2026Hassan Ismkhan, Hamid BouchahciaMissing-Modality Learning Unsupervised Learning
Bournemouth University Bournemouth, UK
A solvable model for unsupervised federated learning
Jun 11, 2026Giovanni Catania, Aurélien Decelle, Gianluca Manzan +2Statistical Physics of Learning Unsupervised Learning
Institute for Cross-disciplinary Physics and Complex Systems IFISC (CSIC-UIB), Campus Universitat Illes Balears, 07122 Palma de Mallorca, Spain. · Escuela Técnica Superior de Ingenieros Industriales, Universidad Politécnica de Madrid, Calle de José Gutiérrez Abascal 2, Madrid 28006, Spain. · GISC - Grupo Interdisciplinar de Sistemas Complejos 28040 Madrid, Spain. +5
Anchor PCA
Jun 4, 2026Benedikt Seiter, Anya Fries, Julius von Kügelgen +1Unsupervised Learning Principal Component Analysis
ETH Zürich
SURF: Separation via Unsupervised Remixing Flow
Jun 3, 2026Henry Li, Robin Scheibler, Efthymios Tzinis +3Unsupervised Learning Flow Matching
Google · Google DeepMind
Flexible Online Representation Learning Based on Similarity Matching
Jun 1, 2026Shagesh Sridharan, Yanis Bahroun, Anirvan M. SenguptaUnsupervised Learning Representation Learning
Physics and Astronomy Rutgers University New Brunswick, NJ, USA · CCM, CCN Flatiron Institute, Simons Foundation New York, NY, USA
SmartIterator: Visual Analytics Workflows for Supervising Unsupervised Data Grouping
May 27, 2026Gennady Andrienko, Natalia AndrienkoScientific Visualization Data Visualization
Fraunhofer Institute IAIS, Sankt Augustin, Germany, the Lamarr Institute for Machine Learning and Artificial Intelligence, Sankt Augustin, Germany, and City St George’s, University of London, UK.
Machine learning enables experimental access to photon-by-photon arrival times in scintillation detectors
May 27, 2026Yuya Onishi, Ryosuke Ota, Fumio Hashimoto +4Unsupervised Learning
Central Research Laboratory, Hamamatsu Photonics K.K. · Graduate School of Science and Engineering, Chiba University · Department of Advanced Nuclear Medicine Sciences, National Institutes for Quantum Science and Technology +1
Learn from your own latents and not from tokens: A sample-complexity theory
May 26, 2026Daniel J. Korchinski, Alessandro Favero, Matthieu WyartUnsupervised Learning Self-Supervised Learning
Department of Physics & Institute of Physics Johns Hopkins University & EPFL Baltimore, MD USA & Lausanne, VD Switzerland
SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
May 26, 2026Chengwei Zhang, Xueyi Zhang, Tao Jiang +4Unsupervised Learning Point Cloud Learning
National Key Laboratory of Microwave Imaging, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China · School of Computing, National University of Singapore, Singapore
Learning Permutation from Structure Without Supervision
May 25, 2026Ran Eisenberg, Ofir LindenbaumUnsupervised Learning Optimal Transport
Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel. · Faculty of Engineering, Bar-Ilan
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
May 21, 2026Muhammad Rajabinasab, Michael E. Houle, Oussama Chelly +1Unsupervised Learning Random Feature Methods
University of Southern Denmark, Odense, Denmark · New Jersey Institute of Technology, Newark, NJ, United States · oratio Technologies, Tunis, Tunisia
Efficient coding along the visual hierarchy
May 18, 2026Ananya Passi, Brian S. Robinson, Michael F. BonnerUnsupervised Learning Neural Processes
Department of Cognitive Science, Johns Hopkins University, Baltimore, MD, USA · Applied Physics Laboratory, Johns Hopkins University, Baltimore, MD, USA
PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
May 17, 2026Michael Arbel, Basile Terver, Jean PonceUnsupervised Learning Visual Representation Learning
Univ. Grenoble Alpes, Inria · CNRS, Grenoble INP, LJK · Ecole Normale Supérieure / PSL +2
Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version
May 15, 2026Hong-Phuc Phan, Tuan-Anh Vu, Tung Kieu +3Model Selection Unsupervised Learning
Department of Software Engineering, FPT University, Vietnam · Department of Information Technology, Can Tho University of Technology, Vietnam · Department of Computer Science, Aalborg University, Denmark +2
From Generalist to Specialist Representation
May 12, 2026Yujia Zheng, Fan Feng, Yuke Li +3Unsupervised Learning Disentangled Representation Learning
1CMU · 2UIUC · 3UCSD +3
FastUMAP: Scalable Dimensionality Reduction via Bipartite Landmark Sampling
May 12, 2026Hongmin LiUnsupervised Learning Manifold Learning
School of Life Science and Technology, Institute of Science Tokyo · 2-12-1 Ookayama, Meguro-ku, Tokyo 152-8550, Japan 2Department of Computational Biology and Medical Sciences Graduate School of Frontier Sciences, The University of Tokyo

Sep 30, 2026, cs.CLJ/K move · Enter open · S save

Reason in Style: Discovering and Controlling Style in Language Models

Ioana Marinescu, Eric Karl Oermann, Kyunghyun Cho

NYU · NYU & NYU Langone Health

Unsupervised Learning Language Model Steering Representation Disentanglement LLM Reasoning

Open paper AskPDF arXiv

Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recurring styles in model responses can be discovered without supervision and explicitly controlled. We design an algorithm that learns to separate representations of content and style from language models' outputs and validate its effectiveness on math questions in a controlled setting. By applying this method to over 100K verified traces from nine distinct teacher models, we discover six recurring yet imbalanced styles. We then fine-tune smaller student models to follow these styles when explicitly conditioned on them, using importance weighting to balance the contribution of the styles represented in the corpus. This approach improves Pass@

k

over standard fine-tuning on the same data across six math reasoning benchmarks, demonstrating that we can diversify the style of answers effectively. We confirm that this also results in strong correspondence between requested and realized styles. We find that style affects correctness: the probability of solving a problem depends on the style we condition on, and different problems benefit from different styles. In summary, our results show that stylistic variation in model-generated data can be discovered in an unsupervised way, and made explicit, providing a source of both control and improved reasoning performance.

Momentum

Related topics

Latest papers 41