Related papers: The mini-DST: a high-level LCIO format
In this work, we first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework. Unlike conventional multi-step diffusion-based methods, DiffVC-OSD feeds the reconstructed latent representation directly…
De novo peptide sequencing aims to recover amino acid sequences of a peptide from tandem mass spectrometry (MS) data. Existing approaches for de novo analysis enumerate MS evidence for all amino acid classes during inference. It leads to…
In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity…
A new computer program named CutLHCO is introduced, whose function is the implementation of generic data selection cuts on collider event specification files in the standardized .lhco format. This software is intended to fill an open market…
Downlink massive multiple-input multiple-output (MIMO) precoding algorithms in frequency division duplexing (FDD) systems rely on accurate channel state information (CSI) feedback from users. In this paper, we analyze the tradeoff between…
Spatial transformer network has been used in a layered form in conjunction with a convolutional network to enable the model to transform data spatially. In this paper, we propose a combined spatial transformer network (STN) and a Long…
Dynamic Mode Decomposition (DMD) is a data-driven and model-free decomposition technique. It is suitable for revealing spatio-temporal features of both numerically and experimentally acquired data. Conceptually, DMD performs a…
Spatial transcriptomics (ST) technologies have revolutionized the study of gene expression patterns in tissues by providing multimodality data in transcriptomic, spatial, and morphological, offering opportunities for understanding tissue…
Addressing uncertainty in Deep Learning (DL) is essential, as it enables the development of models that can make reliable predictions and informed decisions in complex, real-world environments where data may be incomplete or ambiguous. This…
Nowadays, Large Language Models (LLMs) have been gradually employed to solve complex tasks. To face the challenge, task decomposition has become an effective way, which proposes to divide a complex task into multiple simpler subtasks and…
Low-dose CT (LDCT) protocols reduce radiation exposure but increase image noise, compromising diagnostic confidence. Diffusion-based generative models have shown promise for LDCT denoising by learning image priors and performing iterative…
Conducting data analysis typically involves authoring code to transform, visualize, analyze, and interpret data. Large language models (LLMs) are now capable of generating such code for simple, routine analyses. LLMs promise to democratize…
Analysing and learning from spatio-temporal datasets is an important process in many domains, including transportation, healthcare and meteorology. In particular, data collected by sensors in the environment allows us to understand and…
DFST proposes an optimized visual tracking algorithm based on the real-time selection of locally and temporally discriminative features. A feature selection mechanism is embedded in the Adaptive colour Names (CN) tracking system that…
Currently, in the field of video-text retrieval, there are many transformer-based methods. Most of them usually stack frame features and regrade frames as tokens, then use transformers for video temporal modeling. However, they commonly…
This work takes the first steps towards solving the "phaseless subspace tracking" (PST) problem. PST involves recovering a time sequence of signals (or images) from phaseless linear projections of each signal under the following structural…
LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has…
Large-scale LiDAR-based point cloud semantic segmentation is a critical task in autonomous driving perception. Almost all of the previous state-of-the-art LiDAR semantic segmentation methods are variants of sparse 3D convolution. Although…
The increasing computational and memory demands of large language models (LLMs) necessitate innovative approaches to optimize resource usage without compromising performance. This paper leverages microscaling floating-point formats, a novel…
Obtaining 3D conformations of realistic polyatomic molecules at the quantum chemistry level remains challenging, and although recent machine learning advances offer promise, predicting large-molecule structures still requires substantial…