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
517 results for “keyword:"activation"” in ICLR 2027. 119 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Representation Without Disposition: Secret Loyalties Install as Preference but Not as Action, and What That Costs White-Box Audits▲3.0k2.33
[PDF]Don't Ignore Them: Scaffold Features Matter for Stable SAE Steering in Diffusion Models▲3952.67
[PDF]Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics▼1361.33
[PDF]Holding the Answer Fixed: What Hidden-State Probes and Interventions Establish About Correctness▼4.3k2.00
[PDF]ACTIVATION-MASK STABILITY AND ADVERSARIAL VULNERABILITY: A MEASUREMENT-COUPLING CASE STUDY▼4.3k2.00
[PDF]SCAS: Symmetrical Concept-space Activation Steering for Joint Hallucination Mitigation and Capability Enhancement in VLMs▼12k1.67
[PDF]Replication Is Not Specificity: Negative Controls for Representation-Based Reward-Hacking Detection▼1361.33
[PDF]Beyond Task-Conditioned Importance: Head-Resolved Output Jacobians Separate Broad Response from Behavioral Relevance▼1.2k1.67
[PDF]When Backdoors Meet Selective State Spaces: Mechanisms and Attacks in Mamba Language Models▲15k3.50
[PDF]Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation▲3.0k2.33
[PDF]MxQBound: Efficient Mixed-Precision Quantization for MoE-LLMs Guided by Expert Importance and Error Bound Guarantees▲6.1k2.00
[PDF]Do We Need Handcrafted Corruptions? Context-Preserving Activation Perturbation in Representation Space▼4.5k2.67
[PDF]Learning Beyond the Endpoints: Benchmarking and Learning Transition-State-Informed Reaction Representations▼4.3k2.00
[PDF]Balanced Perturbation and Subspace Erasure Do Not Identify What an Activation Monitor Reads▼1.2k1.67
Withdrawn or desk rejected (119)
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00
[PDF]Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutWithdrawn