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233 results for “keyword:"activation steer"” in ICLR 2027. 51 withdrawn or desk rejected listed apart.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]One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering▲5103.00
[PDF]Constitutional Value Potentials: Reading Priority Margins and Steering Value Trade-offs in Language-Model Activations▲3.0k2.33
[PDF]Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering▼4.3k2.00
[PDF]Transformers develop separable posterior and value representations in a simple decision task▼4.3k2.00
[PDF]Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models▼4.3k2.00
[PDF]Multi-Dimensional Featurizers Yield Fine-Grained Steering and Data Shaping in Robot Foundation Models▼5.1k2.60
[PDF]Same Data, Different Target: How the Prediction Target Can Separate Probing from Steering▼1.2k1.67
[PDF]MultiUS : Unsupervised Persona Mixture and Norm-Bounded Latent Steering for User Simulation▼1361.33
[PDF]Prompt-Adapted Transport Control: Contextual Tokenwise LLM Behaviour Steering via Flow Matching▼4.5k2.67
[PDF]Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation▲3972.67
[PDF]Emotion Interpretability in Multimodal Models: Disentangling Behavioral, Representational, and Interventional Evidence▼5.8k2.33
[PDF]Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?▼4.3k2.00
[PDF]StiefelSteer: Invertible Refusal Steering via Low-Dimensional Rotations of the Residual Stream▼1.2k1.67
[PDF]Rethinking Activation Steering for Mathematical Reasoning: What Actually Drives Its Reasoning Gains?▼4.3k2.00
[PDF]EvidenceFlow: Inference-Time Suppression of Confounder Evidence in Vision-Language Models▲6.1k2.00
Withdrawn or desk rejected (51)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