Zobrazeno 1 - 10
of 329
pro vyhledávání: '"Liu, Shusen"'
In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the original model ac
Externí odkaz:
http://arxiv.org/abs/2407.00356
Publikováno v:
2023 IEEE Visualization and Visual Analytics (VIS), Melbourne, Australia, 2023, pp. 221-225
As applications of generative AI become mainstream, it is important to understand what generative models are capable of producing, and the extent to which one can predictably control their outputs. In this paper, we propose a visualization design, na
Externí odkaz:
http://arxiv.org/abs/2406.19987
The recent introduction of multimodal large language models (MLLMs) combine the inherent power of large language models (LLMs) with the renewed capabilities to reason about the multimodal context. The potential usage scenarios for MLLMs significantly
Externí odkaz:
http://arxiv.org/abs/2407.10996
Transfer function design is crucial in volume rendering, as it directly influences the visual representation and interpretation of volumetric data. However, creating effective transfer functions that align with users' visual objectives is often chall
Externí odkaz:
http://arxiv.org/abs/2406.15634
In this work, we explore the use of deep learning techniques to learn the relationships between nuclear cross-sections across the chart of isotopes. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime that are
Externí odkaz:
http://arxiv.org/abs/2404.02332
With recent advances in multi-modal foundation models, the previously text-only large language models (LLM) have evolved to incorporate visual input, opening up unprecedented opportunities for various applications in visualization. Our work explores
Externí odkaz:
http://arxiv.org/abs/2312.04494
Autor:
Olson, Matthew L., Liu, Shusen, Thiagarajan, Jayaraman J., Kustowski, Bogdan, Wong, Weng-Keen, Anirudh, Rushil
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize be
Externí odkaz:
http://arxiv.org/abs/2312.03642
Neural network have achieved remarkable successes in many scientific fields. However, the interpretability of the neural network model is still a major bottlenecks to deploy such technique into our daily life. The challenge can dive into the non-line
Externí odkaz:
http://arxiv.org/abs/2310.16295
Autor:
Glatt, Ruben, Liu, Shusen
Emerging foundation models in machine learning are models trained on vast amounts of data that have been shown to generalize well to new tasks. Often these models can be prompted with multi-modal inputs that range from natural language descriptions o
Externí odkaz:
http://arxiv.org/abs/2306.17400
Autor:
Olson, Matthew L., Liu, Shusen, Anirudh, Rushil, Thiagarajan, Jayaraman J., Bremer, Peer-Timo, Wong, Weng-Keen
Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for tools to audit trained networks in human intelligible format, for example, to identify
Externí odkaz:
http://arxiv.org/abs/2303.10774