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
231 results for “keyword:"activation steering"” in ICLR 2027. 51 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Improving the Robustness of VLAs to Spatial Object Perturbation via Attention-Head Amplification▼3.7k2.25
[PDF]JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vectors Manipulation▼1611.50
[PDF]A Steerable Internal Direction Links Distinct Mental-Accounting Biases in Large Language Models▼4.3k2.00
[PDF]Trajectory-Guided Rotation Steering for Jailbreak Defense in Audio Large Language Models▼5.8k2.33
[PDF]Amplification Without Repair: Causal Limits of Activation Steering in Abstract Reasoning▼5.9k2.50
[PDF]Diagnosing and Mitigating Sycophancy in LLMs via Attribution-Guided Activation Steering▼1.2k1.67
[PDF]Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation▲4.6k3.00
[PDF]DeCoS: Decoding by Contrasting Steered Features Reduces Hallucinations in Large Language Models▼4.5k2.67
Withdrawn or desk rejected (51)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