conftrace_

hidden activation

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (1) activation intervention (1) cache model (1) language model truthfulness (1) attribute classifier (1) model truthfulness (1) plug and play language model (1) linear steering (1) behavioral steering (1) gradient intervention (1)

Papers

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models EMNLP 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning ICML 2024 Wav2vec behind the Scenes: How end2end Models learn Phonetics Interspeech 2022 Plug and Play Language Models: A Simple Approach to Controlled Text Generation ICLR 2020 Towards Neural Programming Interfaces NeurIPS 2020 Online Normalization for Training Neural Networks NeurIPS 2019 Unbounded cache model for online language modeling with open vocabulary NeurIPS 2017