Transition Learning

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 24

All topics

Shaping Persistent Representations from Independent Interactions
Sep 28, 2026Ji Dai, Quan Fang, Junyu Gao +4Transition Learning In-Context Learning
Beijing University of Posts and Telecommunications · Institute of Automation, Chinese Academy of Sciences · Shenzhen University +1
Response-state Learning for Transferable Vibrational Spectroscopic Characterization with Electron Prior
Sep 24, 2026Zetong Li, Zhuosong Xie, Hengyu Fan +6Laser-Induced Breakdown Spectroscopy Quantum Chemistry
Innovation Center for AI and Drug Discovery, School of Pharmacy, East China Normal University, Shanghai 200062, China.
Simulating Disengaged Students to Evaluate LLM-based Tutors
Sep 14, 2026Xianghui Meng, Jionghao LinTutors Student
The University of Hong Kong, Hong Kong SAR, China
Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems
Sep 8, 2026Zhihao Wang, Ruichen Wang, Ruohan Li +6Transition Learning Case Study
University of Maryland · Rutgers University · University of Texas at Austin +1
Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study
Sep 7, 2026Aayush Patel, Andrzej RuszczyńskiMarkov Decision Processes Robot Navigation
Department of Management Science and Information Systems, Rutgers University
From Optimal Actions to World Models: Identifiability of Transition Kernels in Discounted MDPs
Aug 7, 2026Neal BatraMarkov Decision Processes Transition Learning
Dovetail Research · University of Warwick
UNVaMP: Neural Knowledge Tracing with Variational Regularization of Latent Knowledge Dynamics
Aug 4, 2026Carson J. Cook, Ahmed J. Zerouali, Anthony Schmidt +3Transition Learning Latent Variable
Amplify Education, Inc.
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
Jul 9, 2026Jakob Suchan, Julius Monsen, Salim Baloch +1Answer Set Programming Neuro-Symbolic Framework
Constructor University Bremen, Bremen, Germany · CoDesign Lab > Cognitive Vision · Örebro University, Örebro, Sweden
Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures
Jun 29, 2026L. U. Abdullaev, F. Herrera, U. A. Rozikov +1Gibbs Transition Learning
National University of Singapore, Singapore · Department of Computer Science and Artificial Intelligence, University of Granada, E-18071 Granada, Spain · V.I. Romanovskiy Institute of Mathematics, Uzbekistan Academy of Sciences, 9, Universitet str., 100174, Tashkent, Uzbekistan +3
Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems
Jun 8, 2026Xingji CuiDynamical Systems Recurrent Neural Networks
Xi’an Jiaotong University, China
Graph Transfer Learning via Shared Latent Geometry: Theory and Applications
May 30, 2026Tong Wu, Andrew Campbell, Anna ScaglioneDiscriminative Congruence Transform Physics-Informed Learning
University of Central Florida, USA · Cornell University, USA
MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability
May 25, 2026Barsat KhadkaMechanistic Interpretability Circuits
School of Computing Sciences and Engineering The University of Southern Mississippi
State commitment learning: training language models to distinguish computation from memory
May 22, 2026Fei Ding, Yongkang Zhang, Runhao Liu +3Transition Learning Language Modeling
Alibaba Group · Tsinghua University
Estimating Learners' Skill Acquisition Without Temporal Information
May 22, 2026Ryosuke Nagai, Kyohei Atarashi, Koh Takeuchi +2Unsupervised Skill Discovery Transition Learning
SODA · Kyoto University, Kyoto, Japan · Inria, France
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
May 21, 2026Romil V. Sonigra, P. R. KumarLatent Dynamics Latent World Models
Texas A&M University · Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843
Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning
May 10, 2026Siyu Wu, Cong Xu, Wei ZhangInterpretability Transition Learning
1Shanghai Institute of AI Education, East China Normal University, Shanghai, 200241, China · 2Shool of Computer Sicence and Technology, East China Normal University, Shanghai, 200241, China
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
May 8, 2026Mingyu Liu, Sihan Huang, Yijia Fan +4Zero-Shot Composed Image Retrieval Query Image
1Sun Yat-sen University · 2Guangdong Province Key Laboratory of Information Security Technology, China · 3Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China
LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations
May 8, 2026Qixin Xiao, Maani GhaffariLong-Horizon Inference Transition Learning
University of Michigan
Interpretable experiential learning based on state history and global feedback
May 1, 2026Anton KoloninTransition Learning Behavioral Foundation Models
1The Artificial Intelligence Research Center, Novosibirsk State University, Russia · 2Aigents, Russia.
SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation
Apr 30, 2026Pengna Li, Kangyi Wu, Shaoqing Xu +7Vision-Language Navigation Navigation
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · The State Key Laboratory of Internet of Things for Smart City, Centre for Artificial Intelligence and Robotics, University of Macau · Xiaomi EV +2
The Nonverbal Syntax Framework: An Evidence-Based Tiered System for Inferring Learner States from Observable Behavioral Cues
Apr 28, 2026Sherzod Turaev, Mary John, Jaloliddin Rustamov +4Nonverbal Cues Transition Learning
Department of Computer Science & Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain, Abu Dhabi, United Arab Emirates · Academic Support Department, Abu Dhabi Polytechnic, Abu Dhabi, United Arab Emirates · Department of Information Systems and Security, College of Information Technology, College of Information Technology, United Arab Emirates University, Al Ain, Abu Dhabi, United Arab Emirates
Deep Clustering for Climate: Analyzing Teleconnections through Learned Categorical States
Apr 24, 2026Lívia Meinhardt, Dário OliveiraClimate Clustering
FGV EMAp
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
Apr 20, 2026Vin Bhaskara, Haicheng WangPrediction Error Transition Learning
Department of Computer Science, University of Toronto, Toronto, Canada.
State-Change Learning for Prediction of Future Events in Endoscopic Videos
Oct 14, 2025Saurav Sharma, Chinedu Innocent Nwoye, Didier Mutter +1Surgical Videos Future Video Prediction
University of Strasbourg, CNRS, INSERM, ICube, UMR7357, France · IHU Strasbourg, Strasbourg, France · University Hospital of Strasbourg, France

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

Shaping Persistent Representations from Independent Interactions

Ji Dai, Quan Fang, Junyu Gao, Rongfeng Guo+3

Beijing University of Posts and Telecommunications · Institute of Automation, Chinese Academy of Sciences · Shenzhen University+1

Transition Learning In-Context Learning Persistence Ecosystems

Open paper AskPDF arXiv

World models learn environment dynamics from interaction experience. These dynamics depend on the current state and actions, as well as on properties that persist across interactions. Yet standard predictive training can reduce error using local evidence alone, without organizing persistent information into reusable context. We introduce SPRII, a training principle that uses relations between interactions as weak supervision for persistent context while retaining the learner's native objective. For example, different trajectories of the same system share persistent properties even when their states and actions differ. SPRII uses such relations to guide context learning without numerical property labels. Two composable components encourage contexts from related interactions to agree (Align) and use one interaction's context to predict another's future (Cross). Our analysis distinguishes three linked questions: what persistent information is accessible in the learned context (Formation), how that context influences a fixed predictor (Use), and whether it reduces task error (Value). Success at one stage does not guarantee success at the next. Controlled experiments show that more reliable relations improve representation organization, but adding a shared-property constraint can reduce access to a property that remains shared. Context substitutions change predictions at fixed model weights, while the benefit from history depends on prediction horizon and readout. Evaluations span thirteen settings, including controlled physical systems, public dynamics tasks, robotic and tactile data, and partner interaction, across multiple learner families. Relative to the corresponding baselines, SPRII yields average gains of over 10% in downstream task performance and over 15% in persistent-property readout. The project page is available at https://persistent-learning-review.netlify.app/interactive.html.

Momentum

Related topics

Latest papers 24