相关论文: LINNA: Likelihood Inference Neural Network Acceler…

The multi-band template analysis (MBTA) pipeline is a low-latency coincident analysis pipeline for the detection of gravitational waves (GWs) from compact binary coalescences. MBTA runs with a low computational cost, and can identify…

Modern computationally-intensive applications often operate under time constraints, necessitating acceleration methods and distribution of computational workloads across multiple entities. However, the outcome is either achieved within the…

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. LLM inference systems, however, are slow compared to database systems, and inference performance and…

The Laser Interferometer Space Antenna (LISA) is a planned space-based gravitational wave telescope with the goal of measuring gravitational waves in the milli-Hertz frequency band, which is dominated by millions of Galactic binaries. While…

Deep learning is attracting interest across a variety of domains, including natural language processing, speech recognition, and computer vision. However, model training is time-consuming and requires huge computational resources. Existing…

The full-size MLPs and the projection layers in attention introduce tremendous model sizes of large language models (LLMs), consuming extensive computational resources in pre-training. We empirically observe that the activations of…

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused…

While modern machine learning has transformed numerous application domains, its growing computational demands increasingly constrain scalability and efficiency, particularly on embedded and resource-limited platforms. In practice, neural…

COSINE-100 aims to conclusively test the claimed dark matter annual modulation signal detected by DAMA/LIBRA collaboration. DAMA/LIBRA has released updated analysis results by lowering the energy threshold to 0.75 keV through various…

Recent advance in sparse attention mechanisms has demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs). Native Sparse Attention (NSA), one state-of-the-art…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Modeling longitudinal and survival data jointly offers many advantages such as addressing measurement error and missing data in the longitudinal processes, understanding and quantifying the association between the longitudinal markers and…

Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has…

The Vera Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to process ${\sim}10^6$ transient detections per night. For precision measurements of cosmological parameters and rates, it is critical to understand the…

State-of-the-art neural network-based methods for learning summary statistics have delivered promising results for simulation-based likelihood-free parameter inference. Existing approaches require density estimation as a post-processing…

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…

We present a new approach to parameter inference targeted on generic situations where the evaluation of the likelihood $\mathcal{L}$ (i.e., the probability to observe the data given a fixed model configuration) is numerically expensive.…

In this work, we present EDRIS (French for Distance Estimator for Incomplete Supernova Surveys), a cosmological inference framework tailored to reconstruct unbiased cosmological distances from type Ia supernovae light-curve parameters. This…

The growing computational demands of large language models (LLMs) make efficient inference and activation strategies increasingly critical. While recent approaches, such as Mixture-of-Experts (MoE), leverage selective activation but require…

Recurring industrial analytics and machine-learning workflows are becoming a major computational burden in modern engineering practice. Large parametric database generation, scheduled model retraining, repeated evaluation pipelines, and…