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517 results for “keyword:"activation"” in ICLR 2027. 119 withdrawn or desk rejected listed apart.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]Navigating the OCEAN: An Atlas of Big Five Personality Representations in Language Models▲8.9k2.75
[PDF]Measure Once, Steer with Many: Context Contamination and Composite Control for Persona Drift in LLMs▼5.8k2.33
[PDF]VeriSeek-VL: Seeking Visual Evidence and Verifying Hypotheses in Multimodal Deep Search▼4.3k2.00
[PDF]Probing Under Distribution Shift: Learning Generalizable Distributed Representations of LLM Activations▼5.8k2.33
[PDF]Predicting Reasoning Errors Before They Occur: A Prompt-Side Activation Direction Anticipates Correctness in a Large Language Model▼1351.33
[PDF]Steering Language Models Without Contrastive Pairs via Unsupervised Latent Region Matching▼1351.33
[PDF]Aggregation Order in Activation Patching: Which Circuit Is Selected and What It Preserves▼4.3k2.00
[PDF]Removing Redundant Computation in a BDH-GPU-Derived Language Model: Exact Recurrent Training and Conditional Neuron Selection▲11.00
[PDF]Activation Steering under Low-Bit Quantization: A Geometric Perspective on Degradation and Recovery▼4.3k2.00
[PDF]SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise▼1.2k1.67
[PDF]From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models▼4.3k2.00
[PDF]Knowing Whom to Trust: Reliability States and Information Use in Large Language Models▼5.8k2.33
[PDF]Bridging the Representation–Behavior Gap in Knowledge Editing with Calibrated Activation Steering▲6.1k2.00
[PDF]MetaSteer: Context-Conditioned, Non-linear Steering via Attention-Projection Adaptation▲9.2k2.67
[PDF]A Harmful Request Is Still a Request: Benign Fine-Tuning Rewrites How Aligned Models Begin to Answer▲4002.67
[PDF]Does the Workspace Do the Work? A Causal Protocol for Verifying Global-Workspace Computation in a Language Model▲5103.00
Withdrawn or desk rejected (119)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