相关论文: Apollo-Forecast: Overcoming Aliasing and Inference…

The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior work suggests using pretrained small models to improve…

Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance. Despite recent advances, forecasting accuracy remains limited due to the…

Diffusion Language Models (DLMs) promise parallel generation and bidirectional context, yet they underperform autoregressive (AR) models in both likelihood modeling and generated text quality. We identify that this performance gap arises…

How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective discrete vocabulary for a real-valued sequential input? To…

Time series Forecasting with large languagemodels (LLMs) requires bridging numericalpatterns and natural language. Effective fore-casting on LLM often relies on extensive pre-processing and fine-tuning.Recent studiesshow that a frozen LLM…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by analyzing the effective transfer from language models to time…

Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training…

With the development of astronomical facilities, large-scale time series data observed by these facilities is being collected. Analyzing anomalies in these astronomical observations is crucial for uncovering potential celestial events and…

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and…

Weather prediction is a quintessential problem involving the forecasting of a complex, nonlinear, and chaotic high-dimensional dynamical system. This work introduces an efficient reduced-order modeling (ROM) framework for short-range…

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present…

Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or…

Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks,…

We introduce RHYTHM (Reasoning with Hierarchical Temporal Tokenization for Human Mobility), a framework that leverages large language models (LLMs) as spatio-temporal predictors and trajectory reasoners. RHYTHM partitions trajectories into…

Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets,…

Time-series forecasting in real-world applications such as finance and energy often faces challenges due to limited training data and complex, noisy temporal dynamics. Existing deep forecasting models typically supervise predictions using…

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

The proliferation of mobile devices generates a massive volume of time series across various domains, where effective time series forecasting enables a variety of real-world applications. This study focuses on a new problem of source-free…