Zobrazeno 1 - 10
of 55 725
pro vyhledávání: '"Doan, A."'
Mixture of Experts (MoEs) plays an important role in the development of more efficient and effective large language models (LLMs). Due to the enormous resource requirements, studying large scale MoE algorithms remain in-accessible to many researchers
Externí odkaz:
http://arxiv.org/abs/2411.00918
The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with imbalanced text c
Externí odkaz:
http://arxiv.org/abs/2410.22197
Autor:
Doan, Aleksander, Walpuski, Thomas
Motivated by counting pseudo-holomorphic curves in symplectic Calabi-Yau $3$-folds, this article studies a chamber structure in the space of real Cauchy-Riemann operators on a Riemann surface, and constructs three chambered invariants associated with
Externí odkaz:
http://arxiv.org/abs/2410.21057
This paper presents novel algorithms for the Fermat-Weber Location Problem, guiding an autonomous agent to the point that minimizes the weighted sum of Euclidean distances to some beacons using only bearing measurements. The existing results address
Externí odkaz:
http://arxiv.org/abs/2410.18470
Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A practical solution is to selectively removing target concepts from the m
Externí odkaz:
http://arxiv.org/abs/2410.15618
By enabling capturing of 3D point clouds that reflect the geometry of the immediate environment, LiDAR has emerged as a primary sensor for autonomous systems. If a LiDAR scan is too sparse, occluded by obstacles, or too small in range, enhancing the
Externí odkaz:
http://arxiv.org/abs/2410.11628
Motivated by the optimality principles for non-subdifferentiable optimization problems, we introduce new relative subdifferentials and examine some properties for relatively lower semicontinuous functions including $\epsilon$-regular subdifferential
Externí odkaz:
http://arxiv.org/abs/2410.10065
Autor:
Thimonier, Hugo, Costa, José Lucas De Melo, Popineau, Fabrice, Rimmel, Arpad, Doan, Bich-Liên
Self-supervision is often used for pre-training to foster performance on a downstream task by constructing meaningful representations of samples. Self-supervised learning (SSL) generally involves generating different views of the same sample and thus
Externí odkaz:
http://arxiv.org/abs/2410.05016
Autor:
Manh, Dung Nguyen, Chau, Thang Phan, Hai, Nam Le, Doan, Thong T., Nguyen, Nam V., Pham, Quang, Bui, Nghi D. Q.
Recent advancements in Code Large Language Models (CodeLLMs) have predominantly focused on open-ended code generation tasks, often neglecting the critical aspect of code understanding and comprehension. To bridge this gap, we present CodeMMLU, a comp
Externí odkaz:
http://arxiv.org/abs/2410.01999
Autor:
Doan, Manh-Ha, Bøggild, Peter
Quantum devices, which rely on quantum mechanical effects for their operation, may offer advantages, such as reduced dimensions, increased speed, and energy efficiency, compared to conventional devices. However, quantum phenomena are typically observ
Externí odkaz:
http://arxiv.org/abs/2409.16752