Zobrazeno 1 - 10
of 2 036
pro vyhledávání: '"Le, Trung"'
Autor:
Doan, Khanh, Vuong, Long Tung, Nguyen, Tuan, Bui, Anh Tuan, Tran, Quyen, Do, Thanh-Toan, Phung, Dinh, Le, Trung
Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family cov
Externí odkaz:
http://arxiv.org/abs/2408.04221
Amid the proliferation of forged images, notably the tsunami of deepfake content, extensive research has been conducted on using artificial intelligence (AI) to identify forged content in the face of continuing advancements in counterfeiting technolo
Externí odkaz:
http://arxiv.org/abs/2407.18614
Autor:
Pham, Cuong, Dung, Hoang Anh, Nguyen, Cuong C., Le, Trung, Phung, Dinh, Carneiro, Gustavo, Do, Thanh-Toan
Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a large traini
Externí odkaz:
http://arxiv.org/abs/2407.14726
Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effect
Externí odkaz:
http://arxiv.org/abs/2407.02721
Autor:
Nguyen, Duy, Hoang, Ca, Huynh, Phat K., Truong, Tien, Nguyen, Dang, Sharma, Abhay, Le, Trung Q.
Cardiovascular diseases (CVDs) are notably prevalent among patients with obstructive sleep apnea (OSA), posing unique challenges in predicting CVD progression due to the intricate interactions of comorbidities. Traditional models typically lack the n
Externí odkaz:
http://arxiv.org/abs/2406.18602
Autor:
Huynh, Tuan-Luc, Vu, Thuy-Trang, Wang, Weiqing, Wei, Yinwei, Le, Trung, Gasevic, Dragan, Li, Yuan-Fang, Do, Thanh-Toan
Differentiable Search Index (DSI) utilizes Pre-trained Language Models (PLMs) for efficient document retrieval without relying on external indexes. However, DSIs need full re-training to handle updates in dynamic corpora, causing significant computat
Externí odkaz:
http://arxiv.org/abs/2406.12593
Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt learning levera
Externí odkaz:
http://arxiv.org/abs/2406.09353
Sharpness-aware minimization (SAM) has been instrumental in improving deep neural network training by minimizing both the training loss and the sharpness of the loss landscape, leading the model into flatter minima that are associated with better gen
Externí odkaz:
http://arxiv.org/abs/2406.07107
Autor:
Lê, Trung Nghia Nguyên, Kondratenko, Kirill, Arbouch, Imane, Moréac, Alain, Breton, d Jean-Christophe Le, van Dyck, Colin, Cornil, Jérôme, Vuillaume, Dominique, Fabre, Bruno
Publikováno v:
J. Phys. Chem. C, 128, 7706-7722 (2024)
The attachment of redox active molecules to transition metal dichalcogenides (TMDs), such as MoS2, constitutes a promising approach for designing electrochemically switchable devices through the control of the material charge/spin transport propertie
Externí odkaz:
http://arxiv.org/abs/2404.10565
Video summarization is a crucial research area that aims to efficiently browse and retrieve relevant information from the vast amount of video content available today. With the exponential growth of multimedia data, the ability to extract meaningful
Externí odkaz:
http://arxiv.org/abs/2404.04564