linear representations - Robuta Search

https://aclanthology.org/2023.blackboxnlp-1.2/ Emergent Linear Representations in World Models of Self-Supervised Sequence Models - ACL Anthology Neel Nanda, Andrew Lee, Martin Wattenberg. Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP. 2023. linear representations world models https://openreview.net/forum?id=aajyHYjjsk The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of... Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a... large language model the geometry https://arxiv.org/abs/1605.06259 [1605.06259] Minimal linear representations of filiform Lie algebras and their application for... Abstract page for arXiv paper 1605.06259: Minimal linear representations of filiform Lie algebras and their application for construction of Leibniz algebras https://arxiv.org/abs/1310.7215 [1310.7215] Linear and synchrosqueezed time-frequency representations revisited. Part I: Overview,... Abstract page for arXiv paper 1310.7215: Linear and synchrosqueezed time-frequency representations revisited. Part I: Overview, standards of use, related... time frequency https://deepai.org/publication/a-cheap-linear-attention-mechanism-with-fast-lookups-and-fixed-size-representations A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations | DeepAI Sep 19, 2016 - 09/19/16 - The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. ... https://openreview.net/forum?id=sezgRffNiS TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for... We propose a framework to combine strong non-linear expressiveness with strict SO(3)-equivariance in prediction of the electronic-structure Hamiltonian, by... so 3 https://openreview.net/forum?id=Im6lEFiROpp Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can... We compute the expressivity of deep neural networks under the geometric constraint of equivariance https://openreview.net/forum?id=8CIKCf9ri6 Learning Linear Causal Representations from Interventions under General Nonlinear Mixing |... We study the problem of learning causal representations from unknown, latent interventions in a general setting, where the latent distribution is Gaussian but... learning linear causal representations interventions https://deepai.org/publication/similarity-equivariant-linear-transformation-of-joint-orientation-scale-space-representations Similarity Equivariant Linear Transformation of Joint Orientation-Scale Space Representations |... Mar 13, 2022 - 03/13/22 - Convolution is conventionally defined as a linear operation on functions of one or more variables which commutes with shifts. Grou... linear transformation scale space similarity equivariant joint https://arxiv.org/abs/1310.7215v2 [1310.7215v2] Linear and synchrosqueezed time-frequency representations revisited. Part I:... Abstract page for arXiv paper 1310.7215v2: Linear and synchrosqueezed time-frequency representations revisited. Part I: Overview, standards of use, related... time frequency 1310 linear https://arxiv.org/abs/1310.7274 [1310.7274] Linear and synchrosqueezed time-frequency representations revisited. Part II:... Abstract page for arXiv paper 1310.7274: Linear and synchrosqueezed time-frequency representations revisited. Part II: Resolution, reconstruction and... time frequency 1310 7274 linear