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
375 results for “keyword:"steering"” in ICLR 2027. 78 withdrawn or desk rejected listed apart.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]Steering Vectors Can Control What Models Learn in Supervised Fine-Tuning: An Analysis of Behavior Offloading▼1.2k1.67
[PDF]SCAS: Symmetrical Concept-space Activation Steering for Joint Hallucination Mitigation and Capability Enhancement in VLMs▼12k1.67
[PDF]SAE Interventions Can Be Unreliable: Post-Intervention Recovery of Suppressed Behavior▼4.3k2.00
[PDF]Topology Before Steering: Localising and Gating Cyclic Concepts with Persistent Homology▲3.9k1.67
[PDF]BRIDGE: Bi-subspace Residual Guidance for Spectral Representation Editing towards Truthful LLMs▲6.1k2.00
[PDF]Behavior and Self-Report Are Differentially Controllable: A Within-Model Causal Test in Ten Instruction-Tuned LLMs▼1.2k1.67
[PDF]Position, Not Content: What Repairs Question-First Prompting in Vision-Language Models▼1.2k1.67
Withdrawn or desk rejected (78)
[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