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
233 results for “keyword:"activation steer"” in ICLR 2027. 51 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Localization Does Not Guarantee Control: Gate Failure and Partial Activation Steering in a Causal Reasoning Model▼1.2k1.67
[PDF]Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering▼4.3k2.00
[PDF]Representing and Steering a Hypothesized Consciousness Spectrum: Manifold-Guided vs. Linear Directions▼4.3k2.00
[PDF]PersJEPA: Interpretable Language Model Personalization through Sparse Residual Prediction▼1.2k1.67
[PDF]Steer, Then Classify: Adaptive Document-specific Representation Steering for Text Classification▼1.2k1.67
[PDF]Why Do Language Models Take Shortcuts? A Mechanistic Account of Heuristic–Constraint Competition
[PDF]Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods▲1.7k3.33
[PDF]Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering▼4.5k2.67
[PDF]When Personalization Compromises Truth: Joint Control of User Alignment and Factuality in Large Language Models▲3.0k2.33
[PDF]Linear Readability Does Not Guarantee Writability: Evidence from Controlled Counterfactual Recomposition▼1.2k1.67
[PDF]You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model▲5.4k3.00
[PDF]ORBIT: Offset-based Activation Steering for Cross-lingual Multimodal Fact Verification▲5.4k3.00
[PDF]Programmable Semantic Interventions: Learning Causal Carriers from Behavioral Programs▲6.1k2.00
[PDF]A Manifold-Aware Activation Steering Method for Large Language Models via Geometric Safety Control▼3.7k2.25
[PDF]SteerGrounding: Instance-Adaptive Representation Steering for Reasoning Segmentation with Frozen LMMs▼4.3k2.00
[PDF]Label-Free Steering: Compressing Test-Time Reinforcement Learning into Bias-Only Subspaces▲6.1k2.00
[PDF]Viscot-steer: Disentangling and Transferring Visual Chain-of-Thought via Activation Steering▲3.0k2.33
[PDF]When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety▼5.8k2.33
[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▲3972.67
[PDF]Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics▼1361.33
[PDF]SCAS: Symmetrical Concept-space Activation Steering for Joint Hallucination Mitigation and Capability Enhancement in VLMs▼12k1.67
Withdrawn or desk rejected (51)
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutWithdrawn
[PDF]Meaning Beyond Language: Learning Complementary Semantics for Multimodal Metaphor DetectionWithdrawn1.33
[PDF]NuST: Null-Space-Constrained Activation Steering for Robust Concept Erasure in Diffusion ModelsWithdrawn1.67