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
96 results for “keyword:"shortcut"” in ICLR 2027. 29 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VOICE OR LENGTH? COUNTERFACTUAL AUDITING OF TIMING SHORTCUTS IN AUDIO DEEPFAKE DETECTION▼1.2k1.67
[PDF]Quantum Feature Accessibility as a Mechanism for Shortcut Learning under Distribution Shift.▲6.1k2.00
[PDF]InvarFlow: Shortcut-Invariant Pre-training for Generalizable Encrypted Traffic Classification▼4.3k2.00
[PDF]Does Reward Select Interaction? Identifying and Steering Information Pathways in Multi-Agent Policies▼1.2k1.67
[PDF]CuE: A Cue Engineering Framework for Diagnosing and Mitigating Shortcut Effects on Zero-shot MLLM Recognition▲6.1k2.00
[PDF]HALT: Held-Out-Source Evaluation for Hallucination Detection in Forensic Video Reporting▼1.2k1.67
[PDF]Breaking the Historical Action Shortcut: Mitigating Visual Modality Collapse in Gaming VLA Models via Historical Action Noise Injection▼5.9k2.50
[PDF]Shared-Response Agreement Fabrication: A Model-Side Attack on Multi-Explainer Visual Explanations▼1.2k1.67
[PDF]When Aggregate AUROC Ranks the Shortcut: Trivial-Axis Headroom in Vision-Language Hallucination Detection▲5103.00
[PDF]The Spectral Shortcut: How a Fast Contextual Pathway Suppresses Spectral Learning in Serial Spectral–Spatial Models▼4.3k2.00
[PDF]Perfect Labels for Free? What Exact Answers and Exact Traces Teach a Small Language Model▼1.2k1.67
[PDF]Evaluating Causal Reasoning in LLMs: A Case Study in the Challenges of Procedural Generation▼4.3k2.00
[PDF]Rank Is Not Quality: Label-Free Model Selection Inverts under Instance-Private Nuisance▼4.3k2.00
[PDF]GC-NCE: Graph-Constrained Nuisance-Aware Clinical Evidence Bottleneck for Medical Image Classification under Domain Shift▼5.9k2.50
[PDF]EVIDENCE THAT CAN CONTRADICT: WHAT REPORT- AUDITING METRICS ACTUALLY MEASURE IN MEDICAL VLMS▲3.0k2.33
[PDF]Correct Reward, Costly Rule: Gradient Coherence Decides What Group-Relative RL Locks In▼1.3k1.75
[PDF]CausalMem: Counterfactually Validated Memory for Training-Free Visual Reasoning Agents▲5.4k3.00
[PDF]What Do Collapse Diagnostics Certify? Testing Alignment Objectives for Orthographic Shortcuts▼4.5k2.67
[PDF]Every Failure Is a Timeout: Failure-Mode Homogeneity Makes Robot Policy Evaluators Unverifiable▼1.2k3.00
[PDF]Accuracy Is Not Evidence: Measuring and Training Evidence Dependence in Video Temporal Grounding▲3952.67
[PDF]Progress Rates Can't Tell Shortcuts from Progress: Landmark Properties for Scoring Agents▼5.8k2.33
[PDF]Same Reward, Different Ability: A Single-Variable Intervention Shows Task Formulation Governs What Spatial RLVR Learns▲3952.67
[PDF]Constraining Shortcut Pathways: A Front-Door-Inspired Interaction Bottleneck for End-to-End Autonomous Driving▼5.8k2.33
[PDF]Counterfactual Twins and Executable Validity Gates for Diagnosing Spatial Reasoning in Multimodal LLMs▲11.00
Withdrawn or desk rejected (29)
[PDF]Faithful Is Not Forensic: Robust Intervention-based Forensic Testing (RIFT) for Auditing Deepfake DetectorsWithdrawn1.67
[PDF]Easier Said Than Done: Strangers, Impostors, and the Negatives That Teach a Small Learner to Say "I Don't Know"Desk rejected
[PDF]When Does a Benchmark Score License a Capability Claim? An Executable Three-State Identification CertificateWithdrawn1.00