Related papers: KairosHope: A Next-Generation Time-Series Foundati…
Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the…
Accurate univariate forecasting remains a pressing need in real-world systems, such as energy markets, hydrology, retail demand, and IoT monitoring, where signals are often intermittent and horizons span both short- and long-term. While…
Temporal knowledge graph question answering (TKGQA) involves multi-hop reasoning over temporally constrained entity relationships in the knowledge graph to answer a given question. However, at each hop, large language models (LLMs) retrieve…
We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The…
Optimizing expensive black-box systems with limited data is an extremely challenging problem. As a resolution, we present a new surrogate optimization approach by addressing two gaps in prior research -- unimportant input variables and…
Due to their black-box and data-hungry nature, deep learning techniques are not yet widely adopted for real-world applications in critical domains, like healthcare and justice. This paper presents Memory Wrap, a plug-and-play extension to…
Sepsis accounts for nearly 20% of global ICU admissions, yet conventional prediction models often fail to effectively integrate heterogeneous data streams, remaining either siloed by modality or reliant on brittle early fusion. In this…
The prediction of formation resistivity plays a crucial role in the evaluation of oil and gas reservoirs, identification and assessment of geothermal energy resources, groundwater detection and monitoring, and carbon capture and storage.…
Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…
Multivariate time series forecasting (MTSF) is a critical task with broad applications in domains such as meteorology, transportation, and economics. Nevertheless, pervasive missing values caused by sensor failures or human errors…
Multi-modal medical image fusion is essential for the precise clinical diagnosis and surgical navigation since it can merge the complementary information in multi-modalities into a single image. The quality of the fused image depends on the…
We introduce KAPSO, a modular framework for autonomous program synthesis and optimization. Given a natural language goal and an evaluation method, KAPSO iteratively performs ideation, code synthesis and editing, execution, evaluation, and…
Financial time series forecasting is central to trading, portfolio optimization, and risk management, yet it remains challenging due to noisy, non-stationary, and heterogeneous data. Recent advances in time series foundation models (TSFMs),…
Time series forecasting is a subject of significant scientific and industrial importance. Despite the widespread utilization of forecasting methods, there is a dearth of research aimed at comprehending the conditions under which these…
Large Language Models struggle with memory demands from the growing Key-Value (KV) cache as context lengths increase. Existing compression methods homogenize head dimensions or rely on attention-guided token pruning, often sacrificing…
Time series forecasting presents significant challenges due to the complex temporal dependencies at multiple time scales. This paper introduces ScatterFusion, a novel framework that synergistically integrates scattering transforms with…
Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…
Benefiting from high capacity for capturing complex temporal patterns, deep learning (DL) has significantly advanced time series forecasting (TSF). However, deep models tend to suffer from severe overfitting due to the inherent…
Recurrent-attention hybrids aim to combine the efficiency of recurrence with the expressivity of attention, but existing approaches typically apply attention uniformly across all positions, even when the recurrent state alone is sufficient…
The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting offline inference is offloading-based batched inference, which…