Zobrazeno 1 - 10
of 572
pro vyhledávání: '"Nguyen, Tai"'
Autor:
Nguyen, Duy M. H., Diep, Nghiem T., Nguyen, Trung Q., Le, Hoang-Bao, Nguyen, Tai, Nguyen, Tien, Nguyen, TrungTin, Ho, Nhat, Xie, Pengtao, Wattenhofer, Roger, Zhou, James, Sonntag, Daniel, Niepert, Mathias
State-of-the-art medical multi-modal large language models (med-MLLM), like LLaVA-Med or BioMedGPT, leverage instruction-following data in pre-training. However, those models primarily focus on scaling the model size and data volume to boost performa
Externí odkaz:
http://arxiv.org/abs/2410.02615
Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challenges in balancing generalizatio
Externí odkaz:
http://arxiv.org/abs/2410.00454
Autor:
Nguyen, Duy M. H., Le, An T., Nguyen, Trung Q., Diep, Nghiem T., Nguyen, Tai, Duong-Tran, Duy, Peters, Jan, Shen, Li, Niepert, Mathias, Sonntag, Daniel
Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely on optimiz
Externí odkaz:
http://arxiv.org/abs/2407.04489
Publikováno v:
2024 Neurips
Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ expert-designed conte
Externí odkaz:
http://arxiv.org/abs/2405.14125
Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic
Externí odkaz:
http://arxiv.org/abs/2404.15955
As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new technique
Externí odkaz:
http://arxiv.org/abs/2404.08814
Autor:
Nguyen, Duy M. H., Lukashina, Nina, Nguyen, Tai, Le, An T., Nguyen, TrungTin, Ho, Nhat, Peters, Jan, Sonntag, Daniel, Zaverkin, Viktor, Niepert, Mathias
A molecule's 2D representation consists of its atoms, their attributes, and the molecule's covalent bonds. A 3D (geometric) representation of a molecule is called a conformer and consists of its atom types and Cartesian coordinates. Every conformer h
Externí odkaz:
http://arxiv.org/abs/2402.01975
AI-generated images have become increasingly realistic and have garnered significant public attention. While synthetic images are intriguing due to their realism, they also pose an important misinformation threat. To address this new threat, research
Externí odkaz:
http://arxiv.org/abs/2308.11557
Recognizing software entities such as library names from free-form text is essential to enable many software engineering (SE) technologies, such as traceability link recovery, automated documentation, and API recommendation. While many approaches hav
Externí odkaz:
http://arxiv.org/abs/2308.10564
Fuzzing has emerged as a powerful technique for finding security bugs in complicated real-world applications. American fuzzy lop (AFL), a leading fuzzing tool, has demonstrated its powerful bug finding ability through a vast number of reported CVEs.
Externí odkaz:
http://arxiv.org/abs/2307.02289