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517 results for “keyword:"activation"” in ICLR 2027. 119 withdrawn or desk rejected listed apart.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]EvoSteer: Restoring Safety in Experience-Driven Agentic Evolution via Activation Steering▲2.0k4.00
[PDF]SteerCheck: Attribution Specificity and Alignment Leakage in Activation-Steering Audits▼4.3k2.00
[PDF]Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors▼5.8k2.33
[PDF]Directional Linear Separability of Neural Representations: Geometry and Transformations▼1361.33
[PDF]Frequency, Direction, and Feature Sharing: Dissecting Co-activation in Sparse Autoencoders▲13k2.33
Withdrawn or desk rejected (119)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