Causal

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

29 new papers

A weekly snapshot of new work published in Causal.

Period ending 2026-09-14

15 new papers

A weekly snapshot of new work published in Causal.

Period ending 2026-09-07

19 new papers

A weekly snapshot of new work published in Causal.

Inside this field

Focused directions

Focused topic

Causal Reasoning

Within Causal

354 papersExplore

Focused topic

Covariate Shift

Within Causal

122 papersExplore

Focused topic

Causal Foundation Models

Within Causal

109 papersExplore

Focused topic

Causal Inferences

Within Causal

105 papersExplore

Focused topic

Causal Graph

Within Causal

74 papersExplore

Focused topic

Structural Causal Model

Within Causal

70 papersExplore

Focused topic

Heterogeneous Treatment Effects

Within Causal

67 papersExplore

Focused topic

Latent Confounders

Within Causal

58 papersExplore

Focused topic

Treatment

Within Causal

49 papersExplore

Focused topic

Propensity

Within Causal

40 papersExplore

Focused topic

Causal Representation Learning

Within Causal

33 papersExplore

Focused topic

Causal Intervention

Within Causal

32 papersExplore

948 papers

Latest in Causal

Browse all topics →

Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models
May 24, 2026Farhad Nooralahzadeh, Benjamin Gundersen, Nicolas Deperrois +7Medical Vision-Language Models Steering
Towards a Universal Causal Reasoner
May 24, 2026Qirun Dai, Xiao Liu, Jiawei Zhang +3Large Language Model Reasoning Causal Reasoning
Hypothesis Generation and Inductive Inference in Children and Language Models
May 23, 2026Jeffrey Qin, Wasu Top Piriyakulkij, Zhuangfei Gao +4Inferring Hypothesis Generation
Multicalibration Boosting: Theory, Convergence, and Transferability
May 23, 2026Hanxuan Ye, Hongzhe LiConformal Prediction Multicalibration and Calibration
Treatment Effect Estimation with Differentiated Networked Effect on Graph Data
May 23, 2026Xiaofeng Lin, Han Bao, Hisashi KashimaHeterogeneous Treatment Effects Complex Networks
Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Application to Cross-National Cardiac Arrest Prediction
May 22, 2026Siqi Li, Chuan Hong, Ziye Tian +9Clinical Prediction Covariate Shift
Leveraging Foundation Models for Causal Generative Modeling
May 22, 2026Aneesh Komanduri, Xintao WuCausal Foundation Models Causal Reasoning
Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines
May 22, 2026Ernest FokouéCausal Inferences Trustworthy Artificial Intelligence
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
May 22, 2026Mingfang Zhang, Jingjing Pan, Ashutosh Kumar +7Video Temporal Grounding Visual Evidence
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
May 22, 2026Kewei Zhang, Jin Wang, Sensen Gao +9Autonomous Driving Efficient Vision-Language-Action Models
A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses
May 21, 2026Yan Jiang, Sihong Liu, Philip A. FisherTopic Modeling Survey
KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
May 21, 2026Stelios Boulitsakis Logothetis, Angela Wood, Pietro LiòSurvival Analysis Survival Predictions
FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data
May 21, 2026Maryam Moradpour, Jonas Harriehausen, Amirreza Aleyasin +3Random Forest Heterogeneity
A Martingale Kernel Independence Test
May 21, 2026Felix Laumann, Zhaolu Liu, Mauricio BarahonaGeneralized U-Statistics Conditional Independence
Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
May 21, 2026Ishita Darade, Sushrut ThoratArithmetic Intermediate Representations
From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models
May 21, 2026Caleb MunigetyCausal Reasoning
Learning Causal Orderings for In-Context Tabular Prediction
May 21, 2026Sascha Xu, Sarah Mameche, Jilles VreekenCausal Foundation Models Tabular Learning
Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?
May 21, 2026Luca Modica, Filip Landin, Mehrdad Farahani +3Multi-Modal Large Language Models Factual Recall
CausalGuard: Conformal Inference under Graph Uncertainty
May 21, 2026Vikash Singh, Weicong Chen, Debargha Ganguly +12Heterogeneous Treatment Effects Conformal Inference
A Causal Argumentation Method for Explainability of Machine Learning Models
May 20, 2026Henry Salgado, Meagan R. Kendall, Martine CeberioExplainability Explainable Artificial Intelligence
From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
May 20, 2026Nura Aljaafari, Danilo S. Carvalho, Andre FreitasMechanistic Interpretability Circuits
Robust Personalized Recommendation under Hidden Confounding in MNAR
May 20, 2026Zongyu Li, Wanting Su, Tianyu XiaLatent Confounders Selection Bias
Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
May 20, 2026Jinzong Dong, Zhaohui Jiang, Bo YangConfidence Estimation Architecture-Agnostic Loss Function
A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation
May 20, 2026Yan Li, Yuewen Sun, Shaoan Xie +4Causal Representation Learning Representation Learning
Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions
May 20, 2026Zeyu Liu, Zheng Li, Feng Xie +3Covariate Shift Latent Confounders
Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows
May 20, 2026Benedikt BolligLinear Temporal Logics Runtime Enforcement
Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health
May 20, 2026Donna Tjandra, Trenton Chang, Sonali Parbhoo +8Causal Inferences Causal Reasoning
The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study
May 20, 2026Victoria Lin, Taedong Yun, Maja Matarić +3User Simulation Causal Intervention
Score-Based Causal Discovery of Latent Variable Causal Models
May 19, 2026Ignavier Ng, Xinshuai Dong, Haoyue Dai +3Causal Foundation Models Causal Representation Learning
Exploiting Non-Negativity in DAG Structure Learning
May 19, 2026Samuel Rey, Madeline navarro, Gonzalo MateosGraph Representation Learning Lagrangian Methods
Set-Valued Policy Learning
May 19, 2026Laura Fuentes-Vicente, Mathieu Even, Gaëlle Dormion +3Treatment Effect Reinforcement-Learning Policies
Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
May 19, 2026Ferdinand Genans, Erwan ScornetMissing Data Imputation
What Makes a Representation Good for Single-Cell Perturbation Prediction?
May 19, 2026Wenkang Jiang, Yuhang Liu, Yichao Cai +5Single-Cell Perturbation Prediction Perturbations
A Unified Framework for Structure-Aware Clustering and Heterogeneous Causal Graph Learning
May 19, 2026Honglin Du, Muxuan Liang, Xiang ZhongCausal Graph Directed Acyclic Graph
Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
May 19, 2026Jinrui Jiang, Zhangtai Wu, Zhen Wu +1Hallucination Mitigation Hallucinations
CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
May 19, 2026Kavana Venkatesh, Jafar Isbarov, Saad Amin +2Multi-Agent Systems Adversaries
Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
May 19, 2026Nikhil Cherian Kurian, Victor Caquilpan Parra, Abin Shoby +2Medical Image Classification Latent Confounders
Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
May 18, 2026Manal Benhamza, Marianne Clausel, Myriam TamiCausal Representation Learning Identifiability
Learning Quantifiable Visual Explanations Without Ground-Truth
May 18, 2026Amritpal Singh, Andrey Barsky, Mohamed Ali Souibgui +2Xai Explainable Artificial Intelligence
GUT-IS: A Data-Driven Approach to Integrating Constructs and Their Relations in Information Systems
May 18, 2026Maximilian Reinhardt, Jonas Scharfenberger, Burkhardt FunkStructural Equation Models Data-Driven
OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models
May 18, 2026Chiara Maria Russo, Simone Carnemolla, Simone Palazzo +3Vision Foundation Models Image Classification
Adaptive Experimentation for Censored Survival Outcomes
May 18, 2026Yuxin Wang, Dennis Frauen, Jonas Schweisthal +3Survival Analysis Treatment Effect
Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows
May 18, 2026Dhairya Dalal, Endre Sara, Ben Yemini +2Root Cause Analysis Causal Reasoning
Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap
May 18, 2026Akash Kumar Panda, Olaoluwa Adigun, Bart KoskoCognitive Map Reasoning Graphs
Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
May 17, 2026Saksham Sahai SrivastavaLong-Term Memory Causal Intervention
Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework
May 17, 2026Yumeng Yao, Jingzhi Dong, Haowen Gu +43D Foundation Models Sequence
CasualSynth: Generating Structurally Sound Synthetic Data
May 17, 2026Zehua Cheng, Wei Dai, Jiahao Sun +1Synthetic Data Causal Reasoning
TriOpt: A Scalable Algorithm for Linear Causal Discovery
May 17, 2026Rafat Ashraf Joy, Elena ZhelevaCausal Foundation Models Causal Reasoning
Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
May 17, 2026Taesan Kim, Hyeongjun Yun, Jaegul Choo +1Linear Contextual Bandits Bandits
Scalable Bi-causal Optimal Transport via KL Relaxation and Policy Gradients
May 17, 2026Haoyang Cao, Jesse Hoekstra, Renyuan Xu +2Optimal Transport Stochastic Optimization
Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models
May 17, 2026Nicanor Mayumu, Xiaoheng Deng, Patrick MukalaAutonomous Driving Vision-Language-Action Models
Anytime PAC-Bayes for Constrained Density-Ratio Networks under Covariate Shift
May 17, 2026Paulo Akira F. Enabe, Rodrigo ProvasiCovariate Shift Distribution Shifts
Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection
May 16, 2026Tomàs Garriga, Alejandro Almodóvar, Axel Brando +3Treatment Effect Causal Inferences
From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction
May 16, 2026Pujun Feng, Xiaoyu Guo, Seyed Ehsan Saffari +10Clinical Prediction Clinical Decision Support
CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series
May 16, 2026Jiecheng Lu, Jieqi Di, Runhua Wu +1Time Series Causal Reasoning
Prediction-Intervention Games and Invariant Sets
May 16, 2026Linus Kühne, Felix Schur, Jonas PetersStructural Causal Model
SCOUT: Cyclic Causal Discovery Under Soft Interventions with Unknown Targets
May 15, 2026Alpar Turkoglu, Muralikrishnna G. Sethuraman, Faramarz FekriCausal Foundation Models Causal Graph
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
May 15, 2026Entang Wang, Yiwei Wang, Aleksandra Bakalova +1In-Context Learning Few-Shot Learning
Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds
May 15, 2026Shaojun Xu, Xiaoling Zhou, Yihan Lin +4Deepmind Control Suite Imagination
Testing properties of trees in graphical models with covariance queries
May 15, 2026Sofiya Burova, Francisco Calvillo, Gábor Lugosi +1Conditional Independence Trees

May 24, 2026 · cs.CVJ/K move · Enter open · S save

Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models

Farhad Nooralahzadeh, Benjamin Gundersen, Nicolas Deperrois, Hidetoshi Matsuom+6

University of Zurich and University Hospital of Zurich, Switzerland · Zurich University of Applied Sciences, Switzerland · Kobe University, Japan · Stanford University, USA · ETH AI Center, Switzerland

Medical vision-language models (VLMs) often hallucinate findings when generating chest X-ray reports: they fabricate findings that are not present in the image, miss important ones, or locate them incorrectly. We mitigate this without weight updates by decoding-time residual steering on a per-token sparse autoencoder (SAE) basis: Top-

K

SAEs on late layers, causal steering against clinical errors, then combined suppress/boost intervention at inference time. On the MIMIC-CXR test split, our inference-only method improves the quality of generated reports for three radiology VLMs (RadVLM, LLaVA-Rad, and CheXOne), with relative improvements of +5.4%, +7.2%, and +17.0% in the clinical composite metric, and statistically significant GREEN gains on all backbones. A cross-model feature alignment shows that the quality-promoting (boost) directions overlap strongly across architectures, whereas hallucination-linked (suppress) directions are model-specific. Therefore, transferable steering must treat suppression per-backbone, rather than sharing a universal suppress list. The same recipe transfers zero-shot to IU-Xray (Green

+7.7\%

rel.) without retraining, confirming that the identified features are properties of the model, not of the training corpus. We release causal feature sets and an interactive feature dashboard: https://cxr-sparse-feature-dashboard.netlify.app/.

Medical Vision-Language Models Steering Causal Reasoning

Open paper Ask about it PDF