conftrace_

universal transformer

9 papers

Explore in graph

Also known as

UT

Co-occurring keywords · papers mentioning both

positional embedding (2) parameter sharing (2) language modeling (2) machine translation (2) relative positional embedding (1) dynamic depth (1) embedding scaling (1) lazy transition (1) compute distribution skew (1) turing completeness (1)

Papers

Polymorphic Universal Transformer ACL 2026 MoEUT: Mixture-of-Experts Universal Transformers NeurIPS 2024 Contextual Bangla Neural Stemmer: Finding Contextualized Root Word Representations for Bangla Words EMNLP 2023 Sparse Universal Transformer EMNLP 2023 Leveraging Relaxed Equilibrium by Lazy Transition for Sequence Modeling ACL 2022 The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers EMNLP 2021 Automatically Ranked Russian Paraphrase Corpus for Text Generation ACL 2020 Universal Speech Transformer Interspeech 2020 Universal Transformers ICLR 2019