NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
68 results for “keyword:"treatment"” in ICLR 2027. 12 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Equal Credit or Disease Priority? Dynamic Credit Routing in Offline Multi-Agent Reinforcement Learning for Comorbid Critical Care▼1.3k1.80
[PDF]Multi-perspective videos and 3D poses capturing multi-task Parkinson’s disease assessments and deep brain stimulation treatment effects▲5.4k3.00
[PDF]Generalization Bounds and Representation Learning for Distribution-Valued Potential Outcomes▼1.2k1.67
[PDF]The Orthogonality Frontier: Reliability-Adaptive Causal Decisions with Many Treatments▼4.5k2.67
[PDF]When Is It Safe to Borrow Across Treatments? Target-Aware Learning for Combinatorial Interventions▲6.6k3.33
[PDF]Causal Predict-Then-Optimize: Treatment Effect Estimation under Downstream Optimization▲6.1k2.00
Withdrawn or desk rejected (12)
[PDF]The Price of Hidden Assignments: Calibration and Minimax Rates in Pooled CATE LearningWithdrawn1.33
[PDF]Zero-Sum Bias Corrections for Confounding by Indication in Offline Reinforcement LearningWithdrawn
[PDF]Q-Loss: A Training Objective for Direct CATE Optimization Across Meta-Learner FamiliesWithdrawn1.33
[PDF]SMART: Sequential Monitoring with Adaptive Risk Testing for Dynamic A/B ExperimentsWithdrawn1.33
[PDF]CRA-PFN: Treatment Effect Prediction with Mixed-Role Covariates via Prior-Data Fitted NetworksDesk rejected