A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study examines how decoding algorithms affect fairness in language generation models.
This work proposes an efficient autoregressive model for text generation.
Adaptive contrastive search improves text generation quality and diversity.
Decoding strategies often exclude human-like tokens, creating a detectable gap in generated text.
Improved VAE models avoid posterior collapse in text modeling.
We propose a model for tagging unstructured texts with an arbitrary number of terms drawn from a tree-structured vocabulary (i.e., an ontology). We treat this as a special case of sequence-to-sequence learning in which the decoder begins at the root node of an ontological tree and recursively elects to expand child nod…
Improved text generation with constraints using discrete auto-regressive biasing.
Brain2Char decodes text from brain recordings, achieving state-of-the-art performance.
Improved acoustic word embeddings using shared decoder in multi-view encoders.
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing l…
The paper approaches the task of handwritten text recognition (HTR) with attentional encoder-decoder networks trained on sequences of characters, rather than words. We experiment on lines of text from popular handwriting datasets and compare different activation functions for the attention mechanism used for aligning i…
Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural network models consisting of an encoder model to produce a hidden representation o…
Paper improves text-to-SQL models with schema-aware denoising.
Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation. This approach allows for efficient iterative…
Top-H decoding improves text generation by balancing creativity and coherence.
Adaptive speculative decoding framework for LLMs using bandit algorithms.
For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE…
A new model generates summaries by conditioning on input text and latent topics.
Improved neural keyphrase generation by beam search with reward functions.
In this work, we study abstractive text summarization by exploring different models such as LSTM-encoder-decoder with attention, pointer-generator networks, coverage mechanisms, and transformers. Upon extensive and careful hyperparameter tuning we compare the proposed architectures against each other for the abstractiv…
The Kalman filter (KF) is used in a variety of applications for computing the posterior distribution of latent states in a state space model. The model requires a linear relationship between states and observations. Extensions to the Kalman filter have been proposed that incorporate linear approximations to nonlinear m…
Speech Translation has always been about giving source text or audio input and waiting for system to give translated output in desired form. In this paper, we present the Acoustic Dialect Decoder (ADD) - a voice to voice ear-piece translation device. We introduce and survey the recent advances made in the field of Spee…
New method improves text generation by assigning lower probability to repetitive sequences.
Improved image compression with diffusion models outperforming state-of-the-art methods.
SCROLLS benchmarks long text NLP tasks, improving existing models.
New study finds best language model architecture and pretraining objective for zero-shot tasks.
We present a fully convolutional wav-to-wav network for converting between speakers' voices, without relying on text. Our network is based on an encoder-decoder architecture, where the encoder is pre-trained for the task of Automatic Speech Recognition, and a multi-speaker waveform decoder is trained to reconstruct the…
JEPA fails to improve language model performance when fine-tuning.
We investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks. This model can a…
Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, char…
The paper proposes a new framework to generate synthetic data with human-like imperfections to prevent model collapse.
The quality of machine translation is rapidly evolving. Today one can find several machine translation systems on the web that provide reasonable translations, although the systems are not perfect. In some specific domains, the quality may decrease. A recently proposed approach to this domain is neural machine translat…
New model improves diversity in question generation over text.
Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the leng…
A new framework uses text descriptions to improve protein design.
This paper fine-tunes LLMs for stock return prediction using financial news.
New approach uses text generation to boost AI agent development.
Paper introduces Latent-CLIP for efficient text-image comparison in latent space.
Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthe…
Grad-TTS models speech from text using diffusion probabilistic techniques.
Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve decent performance, they do not explore the sequential information of text…
Proposes a VAE with a discrete bottleneck for better text generation.
A framework to explain decoder-only sequence classification models using intermediate predictions.
Generative models encode and decode 3D crystal structures from a large dataset.
Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were developed for graphs and graph signals. However, the mathematical properties of these methods are unclear, and training good generative models is di…
Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.
Generative Adversarial Networks (GANs) have experienced a recent surge in popularity, performing competitively in a variety of tasks, especially in computer vision. However, GAN training has shown limited success in natural language processing. This is largely because sequences of text are discrete, and thus gradients …
End-to-end dialogue model learns from joint embeddings and user intent.