conftrace_

steering

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mechanistic error reduction (1) optimisation (1) performance (1) particles (1) transformer heads (1) cross-layer feature maps (1) potentials (1) lor a (1) intervention vector (1) feature flow (1)

Papers

A General Framework for Inference-time Scaling and Steering of Diffusion Models ICML 2025 Analyze Feature Flow to Enhance Interpretation and Steering in Language Models ICML 2025 Joint Localization and Activation Editing for Low-Resource Fine-Tuning ICML 2025 To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models ICML 2025