Latent Variable

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 163% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 160

All topics

Continuous Latent Contexts Enable Efficient Online Learning in Transformers
May 11, 2026Emile Anand, Abdullah Ateyeh, Xinyuan Cao +1In-Context Learning Transformer Architectures
Georgia Institute of Technology · University of California, Berkeley · Columbia University
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
May 10, 2026Taekhyun Park, Yongjae Lee, Dohee Kim +1Latent Variable Upsampling
Department of Data Science Pusan National University Busan, Republic of Korea · Department of Industrial Engineering Pusan National University Busan, Republic of Korea · Department of Artificial Intelligence Engineering Changwon National University Changwon, Republic of Korea
Higher-Order Equilibrium Tracking for EM-Compressible Online Estimation
May 9, 2026ZhiMing Li, Yue SongState Estimation Latent Variable
School of Computer Science and Technology TianJin University Tianjin 300350, China · College of AI Tsinghua University Beijing 100084, China
Belief or Circuitry? Causal Evidence for In-Context Graph Learning
May 8, 2026Katharine Kowalyshyn, Timothy Duggan, Daniel Little +1In-Context Learning In-Context
Department of Computer Science, Tufts University, Medford, United States
Structured Coupling for Flow Matching
May 8, 2026Xavier Sumba, Carles Balsells-Rodas, Yingzhen LiConditional Flow Matching Latent Variable
Imperial College London
When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
May 8, 2026Wenjie Guan, Jelena BradicSymbol-Transformer Architectures
Department of Statistics and Data Science, Cornell University
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
May 7, 2026Adhiraj Banerjee, Vipul AroraAudio Tokenizers Autoregressive Token Prediction
Department of Electrical Engineering Indian Institute of Technology, Kanpur
Topological Signatures of Grokking
May 7, 2026Yifan Tang, Qiquan Wang, Inés García-Redondo +1Persistent Homology Neural Network Representations
Imperial College London · Queen Mary University of London · University of Fribourg
Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow
May 7, 2026Bowen Zheng, Yihong Luo, Tianyang HuVisual Tokenizers Autoregressive Image Generation
The Chinese University of Hong Kong, Shenzhen · Hong Kong University of Science and Technology
Causal Probing for Internal Visual Representations in Multimodal Large Language Models
May 7, 2026Zehao Deng, Tianjie Ju, Zheng Wu +5Multimodal Large Language Models Visual Representations
School of Computer Science, Shanghai Jiao Tong University · Ant Group
MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
May 6, 2026Shicheng Fan, Nour Elhendawy, Jianle Sun +4Causal Representation Learning Causal Discovery Methods
University of Illinois Chicago · Case Western Reserve University · Carnegie Mellon University +1
Transformed Latent Variable Multi-Output Gaussian Processes
May 6, 2026Xiaoyu Jiang, Xinxing Shi, Sokratia Georgaka +2Gaussian Process High-Dimensional
Department of Computer Science, University of Manchester, Manchester, UK · Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
Proximal Projection for Doubly Sparse Regularized Models
May 6, 2026Jia Wei He, R. Ayesha Ali, Gerarda DarlingtonProbabilistic Graphical Models Proximal Operators
Department of Mathematics & Statistics , University of Guelph
Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
May 4, 2026Yudong Liu, Yuan Li, Zijia Tang +12Robotic Manipulation Latent Variable
1Duke University · 2Qualcomm AI Research · University of Florida
Calibration of the underlying surface parameters for urban flood using latent variables and adjoint equation
May 3, 2026Yongfu Tian, Shan Ding, Guofeng Su +1Sen1Floods11 Surrogate Models
School of Safety Science, Tsinghua University, Beijing, 100084, China
Adaptive Querying with AI Persona Priors
May 1, 2026Kaizheng Wang, Yuhang Wu, Assaf ZeeviArtificial Intelligence Personas Elicitation
Department of Industrial Engineering and Operations Research and Data Science Institute, Columbia University. · Decision, Risk, and Operations Division, Columbia Business School.
Scaling Video Understanding via Compact Latent Multi-Agent Collaboration
May 1, 2026Kerui Chen, Jinglu Wang, Jianrong Zhang +3Fine-Grained Video Understanding Multimodal Large Language Models
Microsoft Research Asia · Zhejiang University · Guanming Lab.
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
Apr 30, 2026Arnaud ZinflouImputation Accurate Short-Term Electricity Load Forecasting
Hydro-Québec Research Institute Canada
Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection
Apr 29, 2026Ahyoung Oh, Wonseok Shin, Songkuk KimOut-Of-Distribution Detection Vision Transformer
School of Integrated Technology, BK21 Graduate Program in Intelligent Semiconductor Technology Yonsei University
LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images
Apr 28, 2026James Flora, Kowshik Thopalli, Akshay R. Kulkarni +2Vision Encoders Latent Variable
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA · Lawrence Livermore National Laboratory, Livermore, California, USA · University of California San Diego, California, USA
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Apr 26, 2026Haosen Li, Wenshuo Chen, Lei Wang +3Diffusion Alignment Text-To-Image Diffusion Models
1The Hong Kong University of Science and Technology (Guangzhou) · 2Griffith University & Data61/CSIRO
From Local to Cluster: A Unified Framework for Causal Discovery with Latent Variables
Apr 24, 2026Zongyu LiCausal Discovery Methods Causal Inferences
An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models
Apr 24, 2026Juan Manuel ContrerasPsychometric Properties Latent Variable
Independent Researcher
Language as a Latent Variable for Reasoning Optimization
Apr 23, 2026Linjuan Wu, Haoran Wei, Jialong Tang +4LLM Reasoning Strategies Latent Variable
Zhejiang University · Tongyi Lab, Alibaba Grou.
Pairing Regularization for Mitigating Many-to-One Collapse in GANs
Apr 22, 2026Kuan-Yu Lin, Yu-Chih Huang, Tie LiuGenerative Adversarial Network Regularization
Institute of Communications Engineering, National Yang Ming Chiao Tung University · Department of Electrical & Computer Engineering, Texas A&M University
Sparse Network Inference under Imperfect Detection and its Application to Ecological Networks
Apr 20, 2026Aoran Zhang, Tianyao Wei, Maria J. Guerrero +1Restricted Bernoulli Matrix Factorization Sparsity
Department of Electrical and Computer Engineering and the Ken Kennedy Institute, Rice University · Department of Computational and Applied Mathematics, Rice University
Diverse Dictionary Learning
Apr 19, 2026Yujia Zheng, Zijian Li, Shunxing Fan +2Unsupervised Dictionary Learning Identifiability
CMU · MBZUAI · NYU
Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports
Mar 12, 2026Liangkai Zhou, Susu Xu, Shuqi Zhong +1Urban Environments Latent Variable
Stony Brook University Stony Brook, New York, United States · Johns Hopkins University Baltimore, Maryland, United States
Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Feb 17, 2026Xiaoze Liu, Ruowang Zhang, Weichen Yu +7Multi-Agent Communication Latent Variable
Purdue University · Contextual AI · Carnegie Mellon University +1
LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigms
Feb 4, 2026Dario Paape, Tal Linzen, Shravan VasishthSurprisal Readability
Department of Linguistics, University of Potsdam · Department Linguistik, Universität Potsdam, Karl-Liebknecht-Straße 24–25, D-14476, Germany. · Center for Data Science/Department of Linguistics, New York University
Self-Supervised Learning from Structural Invariance
Feb 2, 2026Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee +3Self-Supervised Learning Latent Representation Alignment
Mila - Qu´ebec AI Institute · Universit´e de Montr´eal · CHU Sainte-Justine +2
Diffusion Models in Simulation-Based Inference: A Tutorial Review
Dec 22, 2025Jonas Arruda, Niels Bracher, Ullrich Köthe +2Score-Based Diffusion Model Diffusion Models
Bonn Center for Mathematical Life Sciences, Life & Medical Sciences Institute, University of Bonn, Germany · Center for Modeling, Simulation, & Imaging in Medicine (CeMSIM), Rensselaer Polytechnic Institute, NY, USA · Computer Vision and Learning Lab, Heidelberg University, Germany
Understanding the Staged Dynamics of Transformers in Learning Latent Structure
Nov 24, 2025Rohan Saha, Farzane Aminmansour, Alona FysheTransformer Architectures Language Modeling
Department of Computing Science University of Alberta Edmonton, Canada · Department of Computing Science and Psychology University of Alberta Edmonton, Canada
Learning Latent Graph Geometry via Fixed-Point Schrödinger-Type Activation: A Theoretical Study
Jul 27, 2025Dmitry Pasechnyuk-Vilensky, Martin TakáčDiscriminative Congruence Transform Differentiable Optimization
MBZUAI, UAE
Bayesian Invariance Modeling of Multi-Environment Data
Jun 27, 2025Luhuan Wu, Mingzhang Yin, Yixin Wang +2Bayesian Posterior
Department of Applied Mathematics and Statistics, Johns Hopkins University. · Warrington College of Business, University of Florida. · Department of Statistics, University of Michigan. +2
Temporal Variational Implicit Neural Representations
Jun 2, 2025Batuhan Koyuncu, Rachael DeVries, Ole Winther +1Multivariate Time-Series Imputation
Department of Computer Science, Saarland University · Department of Biology, University of Copenhagen · Novo Nordisk A/S +1
The observational partial order of causal structures with latent variables
Feb 11, 2025Marina Maciel Ansanelli, Elie Wolfe, Robert W. SpekkensCausal Discovery Methods Equivalence
Perimeter Institute for Theoretical Physics, 31 Caroline Street North, Waterloo, Ontario Canada N2L 2Y5 · Department of Physics and Astronomy, University of Waterloo, Waterloo, Ontario, Canada, N2L 3G1
Delta-AI: Local objectives for amortized inference in sparse graphical models
Oct 3, 2023Jean-Pierre Falet, Hae Beom Lee, Esmeralda S. Whitammer +6Probabilistic Inference Probabilistic Graphical Models
Mila – Qu´ebec AI Institute, Universit´e de Montr´eal · Mila – Québec AI Institute, Université de Montréal
Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning
Date pendingXuyang Wang, Zhenyu Li, Jian Ding +4Geometric Reconstruction Object Articulation
Australian National University, Canberra, Australia · King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text
Date pendingSungjune Lee, Myungjoo KangLarge Language Model Evaluation Correctness
Seoul National University

May 11, 2026, cs.LGJ/K move · Enter open · S save

Continuous Latent Contexts Enable Efficient Online Learning in Transformers

Emile Anand, Abdullah Ateyeh, Xinyuan Cao, Max Dabagia

Georgia Institute of Technology · University of California, Berkeley · Columbia University

In-Context Learning Transformer Architectures Compact Latent Sensor Tokens Replay-Based Continual Learning Latent Variable Time-Series Generation

Open paper AskPDF arXiv

Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updates. However, many interactive settings go beyond static prediction to online decision-making, in which effective behavior demands adaptation over long multi-turn horizons in response to feedback, and efficient algorithms in these domains must use compact representations of what they have learned. Recently, continuous transformer architectures with latent chain of thought have shown promise for offline iterative tasks such as directed graph-reachability. Motivated by this, we study whether continuous latent context tokens equip transformers to more effectively realize online learning. We give explicit constructions of constant-depth transformers that implement two foundational online decision-making procedures -- the weighted majority algorithm and

Q

-learning -- by storing their algorithmic state as linear combinations of feature embeddings, using a small number of latent context tokens. We further train a small GPT-2-style transformer with latent contexts using a multi-curriculum objective that does not directly supervise the latent states. On long synthetic online prediction sequences, this model outperforms larger and more complex LLMs, including Qwen-3-14B and DeepSeek-V3. Our results suggest that continuous latent contexts provide a simple and effective persistent state for transformers to implement online learning algorithms.

Momentum

Related topics

Latest papers 160