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
49 results for “keyword:"model interpretability"” in ICLR 2027. 10 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Hidden States as States: Discretizing Hidden-State Geometry in Language Model Computation▼4.5k2.67
[PDF]An Empirical Evaluation Framework for Auditing Explainable AI in Network Intrusion Detection▲3.9k1.67
[PDF]Residual Geometry Separates State Motion from Predictive Change in Weight-Tied Iterative Refinement▼1.2k1.67
[PDF]Where Does the Verbalizable Workspace Band Begin? An Audit of the Jacobian-Lens Instruments Across Open-Weight Families▲14k3.00
[PDF]When Does Decodable Task Information Constitute Agent State? Dissociating Information, Currentness, and Behavioral Use in Live Coding Agents▼4.3k2.00
[PDF]Bounded Integration Windows Gate Hybrid Continuous–Sparse Readouts in a Spike-Converted Transformer Aligned with Language Cortex▼5.8k2.33
[PDF]Readable Constraints, Unreliable Decisions: A Constraint-Instantiation Lens on Language Model Errors▼1351.33
[PDF]SAM: Rethinking Object Hallucination Detection through Visual-Evidence Reliability and Semantic-Update Consistency▲4012.67
[PDF]Quantifying the Link Between Localization and Context Interventions in Long-Context QA▼1.2k1.67
[PDF]SelfShield: Unlocking LLMs' Self-Protective Capability Against Jailbreak Attacks via a Resilient Anchor Layer▼5.8k2.33
[PDF]What Spatial Cues Do Multichannel Replay Detectors Rely On? A Physically Interpretable Analysis via Relative Transfer Functions▼1.2k1.67
[PDF]Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models▼12k1.67
[PDF]Tracing Prompt-Conditioned Control from Allocation to Realized Actuation in Frozen VLMs▼1.2k1.67
[PDF]TARGEN: A STRUCTURAL SCORE BEYOND MOLECULAR EVIDENCE FOR CANCER TARGET GENE PREDICTION▲3.0k2.33
[PDF]Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series▲19k2.33
[PDF]RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback▲5103.00
[PDF]Hard to Remove, Cheap to Replace: Compact, Transferable Surrogates for Sensitive LLM Layers▲6.1k2.00
[PDF]When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders▼1.2k3.00
Withdrawn or desk rejected (10)
[PDF]Disentangled Counterfactual Diffusion for Identity-Preserving Explanations of Black-Box Medical Image ClassifiersWithdrawn1.00
[PDF]When Does Chain-of-Thought Hurt Spatial Answers? Length, Retrieval, and Content Controls in Vision-Language ModelsWithdrawn1.67
[PDF]Better Behavioral Prediction, More Faithful Model Ablations? Evidence from Sequential ChoiceWithdrawn1.33
[PDF]The Influence Spectrum: The Power of Layer-Wise Importance in Large Language ModelsWithdrawn1.67
[PDF]Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot PoliciesDesk rejected2.33
[PDF]DO VISION-LANGUAGE MODELS SEE ILLUSIONS LIKE HUMANS DO? A PARAMETRIC PSYCHOPHYSICS BENCHMARK FOR VLM VISUAL BIASWithdrawn1.33