English
Related papers

Related papers: A completely uniform transformer for parity

200 papers

This paper demonstrates that any general 3-DOF three-legged planar parallel robot with extensible legs can change assembly modes without passing through parallel singularities (configurations where the mobile platform loses its stiffness).…

Robotics · Computer Science 2008-09-22 Ilian Bonev , Sébastien Briot , Philippe Wenger , Damien Chablat

Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While these Transformers generalize well on unseen inputs of the same…

Machine Learning · Computer Science 2025-05-13 Ying Fan , Yilun Du , Kannan Ramchandran , Kangwook Lee

We present Unicoder, a universal language encoder that is insensitive to different languages. Given an arbitrary NLP task, a model can be trained with Unicoder using training data in one language and directly applied to inputs of the same…

Computation and Language · Computer Science 2019-09-05 Haoyang Huang , Yaobo Liang , Nan Duan , Ming Gong , Linjun Shou , Daxin Jiang , Ming Zhou

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Previous work has suggested that parameter sharing between transition-based neural dependency parsers for related languages can lead to better performance, but there is no consensus on what parameters to share. We present an evaluation of…

Computation and Language · Computer Science 2018-10-08 Miryam de Lhoneux , Johannes Bjerva , Isabelle Augenstein , Anders Søgaard

This paper investigates the decoding of a remarkable set of lattices: We treat in a unified framework the Leech lattice in dimension 24, the Nebe lattice in dimension 72, and the Barnes-Wall lattices. A new interesting lattice is…

Information Theory · Computer Science 2021-10-11 Vincent Corlay , Joseph J. Boutros , Philippe Ciblat , Loïc Brunel

The recent surge in Time Series Foundation Models has rapidly advanced the field, yet the heterogeneous training setups across studies make it difficult to attribute improvements to architectural innovations versus data engineering. In this…

Machine Learning · Computer Science 2026-02-09 Yunshi Wen , Wesley M. Gifford , Chandra Reddy , Lam M. Nguyen , Jayant Kalagnanam , Anak Agung Julius

We show that conformal blocks simplify greatly when there is a large difference between two of the scaling dimensions for external operators. In particular the spacetime dimension only appears in an overall constant which we determine via…

High Energy Physics - Theory · Physics 2014-09-09 Connor Behan

The linkage construction and its generalization is one of the most powerful constructions for constant dimension code, accounting for approximately 50\% of all the listed parameters. We show how to improve the linkage construction of…

Information Theory · Computer Science 2020-05-12 Xianmang He

We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing…

Machine Learning · Computer Science 2024-05-17 Tsuyoshi Idé , Jokin Labaien , Pin-Yu Chen

Auto Composing is an active and appealing research area in the past few years, and lots of efforts have been put into inventing more robust models to solve this problem. With the fast evolution of deep learning techniques, some deep neural…

Machine Learning · Computer Science 2019-11-12 Xu Zhao

Understanding Transformer-based models has attracted significant attention, as they lie at the heart of recent technological advances across machine learning. While most interpretability methods rely on running models over inputs, recent…

Computation and Language · Computer Science 2023-12-27 Guy Dar , Mor Geva , Ankit Gupta , Jonathan Berant

This paper introduces a class of structured lowdensity parity-check (LDPC) codes whose parity check matrices are arrays of permutation matrices. The permutation matrices are obtained from Latin squares and form a finite field under some…

Information Theory · Computer Science 2010-04-09 Dung Viet Nguyen , Bane Vasic , Michael Marcellin , Shashi Kiran Chilappagari

It is pointed out that if we allow for the possibility of a multilayered universe, it is possible to maintain exact supersymmetry and arrange, in principle, for the vanishing of the cosmological constant. Superpartner(s) of a known particle…

High Energy Physics - Theory · Physics 2007-05-23 Freydoon Mansouri

A recent variation of Transformer, Performer, scales Transformer to longer sequences with a linear attention mechanism. However, it is not compatible with relative position encoding, which has advantages over absolute position encoding. In…

Computation and Language · Computer Science 2021-09-09 Peng Chen

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…

Computation and Language · Computer Science 2018-07-12 Tomáš Brychcín

By considering the parity-transformation properties of the $(1/2,\,0)$ and $(0,\,1/2)$ fields in the {\it front form} we find ourselves forced to study the front-form evolution both along $x^+$ and $x^-$ directions. As a by product, we find…

High Energy Physics - Theory · Physics 2007-05-23 M. Sawicki , D. V. Ahluwalia

In this paper, we study the absolute equivalence between Pfaffian systems with a degree 1 independence condition and obtain structural results, particularly for systems of corank 3. We apply these results to understanding dynamic feedback…

Differential Geometry · Mathematics 2023-11-06 Jeanne Clelland , Yuhao Hu

Recently, low-resolution LDPC decoders have been introduced that perform mutual information maximizing signal processing. However, the optimal quantization in variable and check nodes requires expensive non-uniform operations. Instead, we…

Information Theory · Computer Science 2022-11-15 Philipp Mohr , Gerhard Bauch