conftrace_

activation scaling

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

channel-wise scaling (1) activation optimization (1) group fusion (1) mohd (1) hidden dimension (1) energy score (1) model steering (1) post-hoc detection (1) model depth (1) model width (1)

Papers

Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in Transformer ICML 2025 Activation Scaling for Steering and Interpreting Language Models EMNLP 2024 Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement ICLR 2024 Quadapter: Adapter for GPT-2 Quantization EMNLP 2022 Fast and Accurate Model Scaling CVPR 2021