Counterfactual Learning

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 58

All topics

WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds
Jun 9, 2026Fabio RovaiStructural Causal Models Causal World Models
Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
Jun 7, 2026Abdul Moeed, Stefan Schrod, Martin Rohbeck +4Spatial Transcriptomics Disentangled Representation Learning
Division of Computational Genomics and Systems Genetics, German Cancer Research Center (DKFZ), Heidelberg, Germany · Helmholtz Information & Data Science School for Health, Germany · Genome Biology Unit, European Molecular Biology Laboratory, Heidelberg, Germany +4
Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generation
Jun 5, 2026Raphael C Kim, Jingsen Zhu, Ramin Zabih +1Reinforcement Learning Causal Counterfactual Generation
Cornell Tech, Cornell University, New York, NY · Department of Biostatistics, Department of Population Health, New York University Grossman School of Medicine, New York, NY
Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction
Jun 4, 2026Amirhossein Zare, Amirhessam Zare, Herlock Rahimi +2Structural Causal Models Counterfactual Prediction
School of Medicine, Tehran University of Medical Sciences, Tehran, Iran. · Department of Electrical and Computer Engineering, Yale University, New Haven, CT, USA. · School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran. +2
Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions
Jun 4, 2026Wenhao Mu, Facundo Yan, Anik Mumssen +2Forecasting Benchmarks Counterfactual Prediction
University of Michigan · Computer Science and Engineering · Ann Arbor, Michigan, USA +1
Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents
Jun 3, 2026Renwei MengCredit Assignment in RL Long-Horizon Agent Evaluation
Ahu
CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection
May 28, 2026Suhang Li, Osamu Yoshie, Yuya IeiriSelective Prediction Object Hallucination in VLMs
The authors are with the Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan.
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
May 26, 2026Xiaotian Ye, Xiaohan Wang, Mengqi Zhang +1Knowledge Conflicts in Language Models Hallucination in Language Models
Beijing University of Posts and Telecommunications · Huazhong University of Science and Technology · Shandong University +1
Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing
May 25, 2026Kwangho KimSemiparametric Inference Causal Inference
Department of Statistics, Korea University
Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
May 21, 2026Dazhao Du, Jian Liu, Jialong Qin +7Counterfactual Evaluation Video-Language Models
Hong Kong University of Science and Technology · Tencent
COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking
May 14, 2026Shukun Jia, Shiyu Hu, Yipei Wang +3Counterfactual Learning Multi-Object Tracking
School of Automation, Southeast University, Nanjing, China · Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, China · School of Physical & Mathematical Sciences, Nanyang Technological University, Singapore +1
COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning
May 14, 2026Xudong Chen, Yixin Liu, Hua Wei +1Multi-Agent System Optimization Multi-Agent Orchestration
Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
May 11, 2026Jianzhu Bao, Haozhen Zhang, Kuicai Dong +5Data Visualization VLM Adaptation
1Nanyang Technological University · 2Aumovio Singapore Pte. Ltd.
Debiased Counterfactual Generation via Flow Matching from Observations
May 8, 2026Hugh Dance, Johnny Xi, Peter Orbanz +1Flow Matching Causal Counterfactual Generation
Gatsby Computational Neuroscience Unit University College London · Department of Statistics University of British Columbia
Three-in-One World Model: Energy-Based Consistency, Prediction, and Counterfactual Inference for Marketing Intervention
May 8, 2026Junichiro NiimiCausal Effect Estimation World Model Learning
1Meijo University
ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection
May 6, 2026Minh Anh Nguyen, Quang Huy Tran, Bao Ngoc Le +3Counterfactual Learning Human-Object Interaction
Phenikaa University
SpecPL: Disentangling Spectral Granularity for Prompt Learning
May 6, 2026Jingtao Zhou, Xirui Kang, Feiyang Huang +1VLM Adaptation Frequency-Domain Feature Learning
Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR.
CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
May 6, 2026Keyu Chen, Nanfei Ye, Yida Wang +4Reinforcement Learning Autonomous Driving Planning
School of Vehicle and Mobility, Tsinghua University · Li Auto Inc
Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal models
May 6, 2026Pengcheng Tan, Jiang Chen, Dehui DuStructural Causal Models Causal Counterfactual Generation
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University
Machine learning models for estimating counterfactuals in a single-arm inflammatory bowel disease study
Apr 25, 2026Dan Liu, Fida K. Dankar, Jennifer C. deBruyn +4Causal Effect Estimation Clinical Outcome Prediction
Children’s Hospital of Eastern Ontario Research Institute, Ottawa, Ontario, Canada · School of Epidemiology and Public Health, University of Ottawa, Ottawa, Ontario, Canada · Alberta Children’s Hospital, Calgary, Alberta, Canada +3
DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
Apr 24, 2026Youze Zheng, Jianyou Wang, Yuhan Chen +8LLM Fine-Tuning Counterfactual Reasoning in Language Models
Laboratory for Emerging Intelligence, University of California, San Diego · University of Chicago · Elsevier +1
A Probabilistic Consensus-Driven Approach for Robust Counterfactual Explanations
Apr 19, 2026Marcin Kostrzewa, Maciej Zięba, Jerzy StefanowskiCounterfactual Explanations Conditional Generative Modeling
Wrocław University of Science and Technology, Wrocław 50-347, Poland · Tooploox, Wrocław 53-601, Poland · Poznań University of Technology, Poznań 61-131, Poland
AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detection
Mar 9, 2026Zhishu Liu, Kaishen Yuan, Bo Zhao +2Facial Action Unit Detection Facial Expression Recognition
Great Bay University, Dongguan, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation
Jan 21, 2026Shovito Barua Soumma, Asiful Arefeen, Stephanie M. Carpenter +2Counterfactual Explanations LLM Fine-Tuning
College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA. · School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USA. · School of Nutritional Sciences and Wellness, University of Arizona, Tucson, AZ 85721, USA.
Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
Nov 15, 2025Yannan Chen, Ruoyu Chen, Wei Wang +6Adversarial Robustness OOD Generalization
School of Cyber Science and Technology, Sun Yat-Sen University, Guangdong Province, China · Institute of Perception, PC Laboratory, Guangdong Province, China · University of Chinese Academy of Sciences, Beijing, China +3
Semiparametric Inference for Counterfactual Regression under Intervention-Driven Shift
Apr 3, 2025Kwangho KimDistribution Shift Robustness Semiparametric Inference
Department of Statistics, Korea University
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
Dec 6, 2024Bowei Tian, Yexiao He, Ziyao Wang +3Debiased ML Algorithmic Fairness
University of Maryland, College Park, MD 20742, USA · Clemson University, Clemson, SC 29634, USA
Hierarchical Deep Counterfactual Regret Minimization
May 27, 2023Jiayu Chen, Xudong Wu, Zhekai Wang +1Imperfect-Information Games Hierarchical RL
The University of Hong Kong Hong Kong SAR · Peking University Beijing, China, 100871 · Purdue University2025 West Lafayette, IN 47907

Jun 9, 2026, cs.AIJ/K move · Enter open · S save

WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds

Fabio Rovai

Structural Causal Models Causal World Models Causal Identifiability Causal Inference Counterfactual Reasoning Counterfactual Learning

Open paper AskPDF arXiv

A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices. We report a failure mode that contradicts it. Across hundreds of structural causal models, on identified quantities a strong predictor and a Bayesian baseline both succeed, but on unidentified quantities (the couplings between counterfactual worlds) the predictor collapses to a point, on 28% of models to one no valid model can produce, while the truth is an admissible interval more data never narrows. The gap is structural: prediction cannot represent uncertainty over counterfactual couplings. We cast a world model as a single positive semidefinite coupling kernel K(T,T') over admissible worlds, whose diagonal is the ordinary posterior (what a predictor recovers) and whose off-diagonal is the cross-world coupling it cannot, which every counterfactual reads. The paper is the theory of that off-diagonal. It is real: two states with identical posteriors differ on a cross-world query, and the off-diagonal is the coupling that fixes counterfactuals. It can be bounded: positive semidefiniteness is partial-identifying information the marginals lack, and enforcing it bounds counterfactuals in polynomial time where the exact response-type program is intractable. Logical structure sharpens it: ontology axioms tighten the bound by up to a third, propagating to couplings they never touch. It can be acquired: targeted scars, constraints learned from encountered infeasibilities, close the gap several times faster than untargeted ones. Its full reconstruction is approximate counting of the admissible worlds, tractable below the Sly-Sun threshold and inapproximable above; we do not claim to beat the worst case.

Momentum

Related topics

Latest papers 58