conftrace_

representational capacity

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

recurrent neural network (4) language model (3) attention mechanism (2) group whitening (1) normalization operation (1) group normalization (1) structural re-parameterization (1) box embedding (1) turing completeness (1) mini-batch standardization (1)

Papers

Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning ACL 2026 Quality over Quantity in Attention Layers: When Adding More Heads Hurts ICLR 2025 Transformer Meets Twicing: Harnessing Unattended Residual Information ICLR 2025 Lower Bounds on the Expressivity of Recurrent Neural Language Models NAACL 2024 On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning ACL 2024 Separations in the Representational Capabilities of Transformers and Recurrent Architectures NeurIPS 2024 Transformers Can Represent n-gram Language Models NAACL 2024 On the Representational Capacity of Recurrent Neural Language Models EMNLP 2023 DyRep: Bootstrapping Training With Dynamic Re-Parameterization CVPR 2022 Capacity and Bias of Learned Geometric Embeddings for Directed Graphs NeurIPS 2021 Group Whitening: Balancing Learning Efficiency and Representational Capacity CVPR 2021