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517 results for “keyword:"activation"” in ICLR 2027. 119 withdrawn or desk rejected listed apart.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]What the Nonnegative Lens Misses: Energy-Matched Causal Tests of the J-Space in Open Language Models▲11.00
[PDF]Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation▲4.6k3.00
[PDF]Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache▲3.0k2.33
[PDF]QuTab: A Single Mutable-State Transformer for Mechanistically Interpretable Tabular In-Context Learning▼1.2k3.00
[PDF]DeCoS: Decoding by Contrasting Steered Features Reduces Hallucinations in Large Language Models▼4.5k2.67
[PDF]Where Massive Activations Come From: Causal Evidence from MLP Geometry in Large Language Models▲3952.67
[PDF]K-Shield: Improving the Safety-Utility Trade-off in Refusal Steering with Local Null-Space Constraints▼4.5k2.67
[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]HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Activation Transitions▼4.3k2.00
[PDF]Representing and Steering a Hypothesized Consciousness Spectrum: Manifold-Guided vs. Linear Directions▼4.3k2.00
[PDF]Extracting and Composing Function Vectors for Analogical Reasoning over Latent Relations▲9.2k2.67
[PDF]PersJEPA: Interpretable Language Model Personalization through Sparse Residual Prediction▼1.2k1.67
Withdrawn or desk rejected (119)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