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.
Language models can predict numeric values as strings.
Express improves causal attention guarantees for language models.
A framework to explain decoder-only sequence classification models using intermediate predictions.
Causal terminology is often introduced in the interpretation of encoding and decoding models trained on neuroimaging data. In this article, we investigate which causal statements are warranted and which ones are not supported by empirical evidence. We argue that the distinction between encoding and decoding models is n…
Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding- than in decoding models. In this paper, we a…
New study finds best language model architecture and pretraining objective for zero-shot tasks.
Constrained sequence codes have been widely used in modern communication and data storage systems. Sequences encoded with constrained sequence codes satisfy constraints imposed by the physical channel, hence enabling efficient and reliable transmission of coded symbols. Traditional encoding and decoding of constrained …
New insights into how encoder-decoder networks generate attention matrices.
A model learns causal representations from high-dimensional data.
Sequence probability predicts correctness in LLMs, but not for repeated prompts
The paper introduces FMCI and hybrid decoding for hidden Markov models.
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of t…
A novel sequence-to-sequence model predicts missing sensor data.
Recurrent models can produce infinite sequences, causing bias; new methods prevent this.
This study mainly investigates two common decoding problems in neural keyphrase generation: sequence length bias and beam diversity. To tackle the problems, we introduce a beam search decoding strategy based on word-level and ngram-level reward function to constrain and refine Seq2Seq inference at test time. Results sh…
A model learns stock trading rules from raw prices using encoder-decoder neural network.
Undirected neural sequence models such as BERT (Devlin et al., 2019) have received renewed interest due to their success on discriminative natural language understanding tasks such as question-answering and natural language inference. The problem of generating sequences directly from these models has received relativel…
Timer-XL predicts multidimensional time series using a unified Transformer approach.
A new model captures variability in time series data.
CAUSE learns Granger causality from event sequences, outperforming existing methods.
The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …
Training-free method improves large language model sequence quality via reward-guided sampling.
Generating logical form equivalents of human language is a fresh way to employ neural architectures where long short-term memory effectively captures dependencies in both encoder and decoder units. The logical form of the sequence usually preserves information from the natural language side in the form of similar token…
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…
A framework infers causal direction from symbolic sequences using compression measures.
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over ti…
Conformer encoder reverses sequence in time dimension, affecting decoder training.
In this paper, we compare different types of Recurrent Neural Network (RNN) Encoder-Decoders in anomaly detection viewpoint. We focused on finding the model that can learn the same data more effectively. We compared multiple models under the same conditions, such as the number of parameters, optimizer, and learning rat…
A simple model explains phase transition in large language models.
This paper examines how different decoding algorithms for LLMs align with various goals.
Accelerates TPP sampling with speculative decoding for faster sequence generation.
GPT learns a causal world model from token predictions, validated in game sequences.
We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia revisions and employ an iterative decoding strategy that is tailored to the loosely-…
Parallelizes autoregressive generation using VSSM.
Study reveals issues with neural autoregressive models and proposes mode recovery cost.
TIMeSynC combines financial service interactions for intent prediction.
Machine-assisted treatment recommendations hold a promise to reduce physician time and decision errors. We formulate the task as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications. It is built on the …
Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make different trade-offs between the amount of computation needed per layer and the le…
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…
In this paper we propose a deep neural network model with an encoder-decoder architecture that translates images of math formulas into their LaTeX markup sequences. The encoder is a convolutional neural network (CNN) that transforms images into a group of feature maps. To better capture the spatial relationships of mat…
New technique learns causally disentangled representations for better generation.
QATS efficiently decodes HMMs with polylogarithmic complexity.
Steady progress has been made in abstractive summarization with attention-based sequence-to-sequence learning models. In this paper, we propose a new decoder where the output summary is generated by conditioning on both the input text and the latent topics of the document. The latent topics, identified by a topic model…
Transformers learn causal structure through gradient descent on self-attention mechanisms.
Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To address these issues, we propose Monotonic Chunkwise Attention (MoChA), which adaptiv…
We present Piano Genie, an intelligent controller which allows non-musicians to improvise on the piano. With Piano Genie, a user performs on a simple interface with eight buttons, and their performance is decoded into the space of plausible piano music in real time. To learn a suitable mapping procedure for this proble…
Proposes TNCM-VAE for generating causal financial time series.
Decoding language representations directly from the brain can enable new Brain-Computer Interfaces (BCI) for high bandwidth human-human and human-machine communication. Clinically, such technologies can restore communication in people with neurological conditions affecting their ability to speak. In this study, we prop…