arXiv research

Representation mixing combines character and phoneme inputs for flexible TTS synthesis.

We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) and a highway network over characters, whose output is given to a long short-term memory (LSTM) recurrent neural network language mo…

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in turn determine model size, computational costs of softmax normalization, and han…

Scene text magnifier enhances readability for visually impaired.

A minimal RNN model learns to generate new characters from a single example.

We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent ne…

Unsupervised model learns word and context embeddings from character sequences.

Generative Neuro-Symbolic model learns from raw data with rich conceptual representations.

End-to-end character-level model for text generation without delexicalization.

This paper proposed a bias-compensated normalized maximum correntropy criterion (BCNMCC) algorithm charactered by its low steady-state misalignment for system identification with noisy input in an impulsive output noise environment. The normalized maximum correntropy criterion (NMCC) is derived from a correntropy based…

Improves text-to-speech speed by interleaving character reading and audio synthesis.

The theory of differential characters is developed completely from a de Rham - Federer viewpoint. Characters are defined as equivalence classes of special currents, called sparks, which appear naturally in the theory of singular connections. There are many different spaces of currents which yield the character groups. …

We introduce multiplicative LSTM (mLSTM), a recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by its ability to have different recurrent transition functions for each possible inp…

Predicting the click-through rate of an advertisement is a critical component of online advertising platforms. In sponsored search, the click-through rate estimates the probability that a displayed advertisement is clicked by a user after she submits a query to the search engine. Commercial search engines typically rel…

Character scheme of small Seifert 3-manifolds is reduced if and only if no exceptional abelian character exists.

We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall …

Quantum character varieties unify four construction methods.

We show that for any knot there exist only finitely many irreducible metabelian characters in the $SL(2,\mathbb{C})$-character variety of the knot group, and the number is given explicitly by using the determinant of the knot. Then it turns out that for any 2-bridge knot a section of the $SL(2,\mathbb{C})$-character va…

Study of orbifold Chern character using superconnections.

Character varieties get a natural Poisson structure.

ABC learns context-aware representations for clustering.

In this paper, we give a quantum interpretation of the Bismut-Chern character form (the loop space lifting of the Chern character form) as well as the Chern character form associated to a complex vector bundle with connection over a smooth manifold in the framework of supersymmetric quantum field theories developed by …

Study shows how certain knots and tori are detected by ideal points in character varieties.

Study SL(2,C) character schemes for finitely generated groups.

Background elimination for noisy character images or character images from real scene is still a challenging problem, due to the bewildering backgrounds, uneven illumination, low resolution and different distortions. We propose a stroke-based character reconstruction(SCR) method that use a weighted quadratic Bezier cur…

Character variety of Borromean link solved, Alexander polynomial formula found.

SmoothLLM defends LLMs from jailbreaking attacks by randomly perturbing inputs.

Character varieties of 2-bridge knots and links explained using Farey recursion.

FinMem enhances LLM trading agents with layered memory and character design.

Computes dimensions of representation and character varieties for 2 and 3-dimensional orbifolds.

Paper generates personalized fonts from a few characters.

We study some basic properties of the variety of characters in PSL(2,C) of a finitely generated group. In particular we give an interpretation of its points as characters of representations. We construct 3-manifolds whose variety of characters has arbitrarily many components that do not lift to SL(2,C). We also study t…

Study of quantum decorated character stacks and their quantizations.

Let K be a knot in an integral homology 3-sphere and let B denote the 2-fold branched cover of the integral homology sphere branched along K. We construct a map from the slice of characters with trace free along meridians in the SL(2, C)-character variety of the knot exterior to the SL(2, C)-character variety of 2-fold…

Study character varieties of hyperbolic 3-manifolds using bundle methods.

Finite automorphisms of SL(2,C) character varieties identified.

Researchers describe character varieties for Hopf links, proving geometric properties.

Study of SU(2,1) character varieties on one-holed torus.

RNN model predicts handwritten characters from accelerometer and gyroscope data.

We calculate the universal character ring of a class of two-generator, one-relator groups. As an application we give a less technical proof of a result in [LT] on the universal character ring of the (-2,3,2n+1)-pretzel knot. We also give an elementary proof of a result in [Ma] on the character variety of the (-2,3,2n+1…

Character variety of Whitehead link described in detail.

Proves Torelli group action is ergodic on Lie group character varieties.

Study $\mathrm{SL}_2(\mathbb{F})$-character varieties of knots over fields of odd characteristic.

Detecting essential surfaces in 3-manifolds and orbifolds using character varieties.

Quantum trace maps abelian character varieties to SL2 character varieties.

We introduce certain relative differential characters which we call Cheeger-Chern-Simons characters. These combine the well-known Cheeger-Simons characters with Chern-Simons forms. In the same way as the Cheeger-Simons characters generalize Chern-Simons invariants of oriented closed manifolds, the Cheeger-Chern-Simons …

A transformer model improves spell correction with hierarchical attention.

We describe on any finitely generated group G the space of maps G->C which satisfy the parallelogram identity, f(xy)+f(xy^{-1})=2f(x)+2f(y). It is known (but not well-known) that these functions correspond to Zariski-tangent vectors at the trivial character of the character variety of G in SL_2(C). We study the obstruc…