Research
On-device research index

arXiv research

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.

168,786 papers · 148 categories

Trend · papers per month

3617221,0831,444 · Jun 202019922001200920172026
48 results for temporal language model

Paper introduces a conformer-based system for streaming language identification in long-form speech.

problem Language identification in long-form audio.
method Conformer layers with attentive temporal pooling and domain adaptation.
result Conformer-based models significantly outperform LSTM and transformer models.

HawkesLLM models text generation with temporal influence, improving semantic alignment under limited memory.

problem Path-dependent uncertainty in agentic text-simulation systems.
method HawkesLLM framework separates temporal influence modeling from text generation, using a multivariate Hawkes process and a language model.
result HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget.

Improved incremental sequence classification with temporal consistency.

problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.

FinHEAR combines LLMs with human expertise for better financial decision-making.

problem Challenges in financial decision-making for language models.
method Multi-agent framework with specialized LLMs for historical analysis, event interpretation, and expert retrieval.
result FinHEAR outperforms baselines in financial tasks with higher accuracy and risk-adjusted returns.

Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural…

2015-02-27abs ↗pdf ↗

Sequence models assign probabilities to variable-length sequences such as natural language texts. The ability of sequence models to capture temporal dependence can be characterized by the temporal scaling of correlation and mutual information. In this paper, we study the mutual information of recurrent neural networks …

2019-05-10abs ↗pdf ↗

FLUID-LLM uses LLMs to predict fluid dynamics with improved accuracy.

problem Leveraging LLMs for CFD due to their pattern recognition abilities but struggles with fluid dynamics complexities.
method Combines pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics.
result Significant performance improvements in CFD predictions across various datasets.

DatedGPT prevents lookahead bias in financial forecasting models.

problem Lookahead bias in large language models trained on internet-scale data.
method Time-aware pretraining with annual data cutoffs and instruction fine-tuning.
result Models' knowledge is effectively bounded by their data cutoff year, improving forecasting validity.

Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of human history. However, traditional techniques such as word representation learni…

2017-03-02abs ↗pdf ↗

Zero-shot understanding of accidents from surveillance videos using vision-language models

problem Accident understanding from surveillance videos
method Three-stage pipeline with vision-language similarity, metadata-driven multi-prompt reasoning, and entropy-gated pairwise adjudicator
result Substantial improvement in harmonic-mean score over baseline

MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.

problem Limited use of timestamp information and information bottleneck in sequential recommendation models.
method MEANTIME employs multiple types of temporal embeddings and attention mechanisms to capture diverse patterns from user behavior sequences.
result MEANTIME outperforms state-of-the-art sequential recommendation methods.

New approach uses inverse reinforcement learning to improve language model training.

problem Training large language models using imitation learning methods.
method Developed a new method of inverse reinforcement learning to optimize sequences directly.
result IRL-based fine-tuning leads to better performance and diversity in language generation.

Proposes a new RNN for language generation capturing long-range dependencies.

problem Capturing long-range word dependencies and sentence order in text corpora.
method Recurrent Hierarchical Topic-Guided RNN with dynamic deep topic model.
result Outperforms larger-context RNN-based language models and learns interpretable topics.

TRR detects stock portfolio crashes by simulating human reasoning.

problem Detecting stock portfolio crashes with limited historical data.
method Temporal Relational Reasoning (TRR) framework.
result TRR outperforms state-of-the-art techniques in detecting stock portfolio crashes.

Proposes a non-autoregressive Transformer for time series forecasting.

problem Autoregressive errors and spatial-temporal dependencies in time series forecasting.
method Introduces a Non-Autoregressive Transformer with a learned temporal influence map.
result Demonstrates state-of-the-art performance on time series forecasting datasets.

Chronologically consistent models maintain accuracy with time-restricted data.

problem Training data introduces lookahead bias and training leakage in large language models.
method ChronoBERT and ChronoGPT trained with only available data at each time point.
result Models achieve strong performance and competitive with larger models, mitigating lookahead bias.

Develops a learning algorithm for PSL formulas from examples.

problem Learning human-interpretable descriptions of complex systems from examples.
method Reduces learning to propositional logic constraint satisfaction and uses SAT solver.
result Proposed method provides succinct human-interpretable descriptions from examples.

Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…

2018-08-12abs ↗pdf ↗

GATGPT uses LLMs with graph attention for spatiotemporal data imputation.

problem Missing values in spatiotemporal data due to sensor malfunctions and data transmission errors.
method Integrates pre-trained large language models with graph attention mechanisms.
result GATGPT achieves comparable results to deep learning benchmarks on real-world datasets.

LLMs detect market patterns through causal reasoning, not just temporal association.

problem Detecting structural market patterns in financial data.
method Obfuscation testing using the WHO-WHOM-WHAT framework.
result LLMs achieve 71.5% detection rate of market patterns without temporal context.

The collaborative ranking problem has been an important open research question as most recommendation problems can be naturally formulated as ranking problems. While much of collaborative ranking methodology assumes static ranking data, the importance of temporal information to improving ranking performance is increasi…

2019-08-15abs ↗pdf ↗

Neural network framework for language recognition considers sequence information and improves accuracy.

problem Challenging task of automatic language identification in noisy conditions.
method Proposes a neural network framework with bidirectional LSTM and attention modeling for relevance weighting.
result Significant improvements over conventional methods in noisy conditions and multi-speaker speech.

Enhances neural models with simple functions to improve language modeling.

problem Neural models struggle with certain spatial, temporal, or quantitative relationships.
method Integrates simple functions into neural architecture to form a hierarchical NSLM.
result NSLMs significantly reduce perplexity in small-corpus language modeling.

New algorithm for online training of Spiking Neural Networks (SNNs).

problem Training Spiking Neural Networks (SNNs) online with BPTT-equivalent gradients.
method Clear separation of spatial and temporal gradient components, derived from biological insights.
result Online training of SNNs with BPTT-equivalent gradients and low time complexity.

A model integrates CNN and LSTM with LLM for better stock forecasting.

problem Complex stock market prediction with volatile patterns and multifaceted data.
method Two-Level Conv-LSTM Neural Network with LLM for holistic stock advising.
result Improved prediction accuracy and contextual insights.

Framework improves clinical timeline reconstruction from text and tables.

problem Temporal precision and event timing in clinical narratives and EHRs.
method Retrieval-augmented multimodal alignment framework.
result Consistently improves absolute timestamp accuracy and temporal concordance.

Survey of large language models in financial prediction and trading.

problem Improving predictability and robustness of financial predictions and trading decisions.
method Task-centered taxonomy, review of empirical evidence, design patterns, benchmarks, and challenges analysis.
result Improved predictability and robustness of financial predictions and trading decisions through large language models.

Unified model learns concepts across domains like left and right.

problem Limited generalization of language concepts in inference-only models.
method Logic-Enhanced Foundation Model (LEFT) with a differentiable, domain-independent program executor.
result LEFT flexibly learns and reasons with concepts across 2D images, 3D scenes, human motions, and robotic manipulation.

TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.

problem Inaccurate confidence scores from E2E ASR models, especially for overconfident predictions.
method Proposes TeLeS, a novel confidence score that considers temporal alignment and lexical errors, and uses shrinkage loss to handle data imbalance.
result TeLeS generalizes well across different languages and ASR models, leading to significant WER reduction.