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
60 results for “keyword:"linear probing"” in ICLR 2027. 16 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Does a Probe Identify a Representation? Semantic Counterfactual Validation in Language Models▼4.3k2.00
[PDF]Utility-Preserving Relabeling Reveals Semantic Sensitivity in Language-Model Decision Making▼1.2k1.67
[PDF]Right on Average, Wrong per Respondent: A Mechanistic Diagnosis of LLM-Simulated Choice▼1.2k1.67
[PDF]Evidence States Survive Where Answers Fail: Decodability and Causal Access in Language Models▼4.3k2.00
[PDF]Emotion Interpretability in Multimodal Models: Disentangling Behavioral, Representational, and Interventional Evidence▼5.8k2.33
[PDF]CKA's Blind Spot: Why Representation Analysis Misses Policy Change in RLVR, and How to Fix It▼1.3k1.75
[PDF]HOW ERASED IS ERASED? QUANTIFYING AND IMPROVING THE RECOVERABILITY OF CONCEPT REMOVAL IN CLIP▼71.25
[PDF]Gains Stay Where the Loss Went: A Channel-by-Condition Map of Physical-Plausibility Training in Vision-Language Models▲3972.67
[PDF]Beyond Single Variants: A Benchmark for Regulatory Epistasis in Genomic Sequence Models▲5103.00
[PDF]Encoded but Unread: Locating and Recovering Within-Event Motion in Video Language Models▼12k1.67
[PDF]No Single Point Suffices: Reporting Regularization Landscapes in Frozen-Representation Evaluation▲11.00
[PDF]When Is Forgetting a Capacity Problem? Dissecting Catastrophic Forgetting under Controlled Capacity Pressure▼4.3k2.00
[PDF]Linear Readability Does Not Guarantee Writability: Evidence from Controlled Counterfactual Recomposition▼1.2k1.67
Withdrawn or desk rejected (16)
[PDF]Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion ModelsWithdrawn1.67
[PDF]Decodable Is Not Necessarily Used: Probe Regularization Controls the Causal Relevance of Belief-State Representations in TransformersDesk rejected