Zobrazeno 1 - 10
of 278
pro vyhledávání: '"Ho, Nhat"'
Autor:
Xie, Yichen, Xu, Chenfeng, Peng, Chensheng, Zhao, Shuqi, Ho, Nhat, Pham, Alexander T., Ding, Mingyu, Tomizuka, Masayoshi, Zhan, Wei
Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios. Despite their success in modeling single-modality data marginal distribution, there is an under-exploration
Externí odkaz:
http://arxiv.org/abs/2411.01123
We conduct the convergence analysis of parameter estimation in the contaminated mixture of experts. This model is motivated from the prompt learning problem where ones utilize prompts, which can be formulated as experts, to fine-tune a large-scaled p
Externí odkaz:
http://arxiv.org/abs/2410.12258
Mixture of Experts (MoE) models are highly effective in scaling model capacity while preserving computational efficiency, with the gating network, or router, playing a central role by directing inputs to the appropriate experts. In this paper, we est
Externí odkaz:
http://arxiv.org/abs/2410.11222
We explore a robust version of the barycenter problem among $n$ centered Gaussian probability measures, termed Semi-Unbalanced Optimal Transport (SUOT)-based Barycenter, wherein the barycenter remains fixed while the others are relaxed using Kullback
Externí odkaz:
http://arxiv.org/abs/2410.08117
Autor:
Tran, Quyen, Le, Minh, Truong, Tuan, Phung, Dinh, Ngo, Linh, Nguyen, Thien, Ho, Nhat, Le, Trung
Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning models by exploiting the relationships between continuously emerging class data. We find tha
Externí odkaz:
http://arxiv.org/abs/2410.04327
We introduce Flat Hilbert Bayesian Inference (FHBI), an algorithm designed to enhance generalization in Bayesian inference. Our approach involves an iterative two-step procedure with an adversarial functional perturbation step and a functional descen
Externí odkaz:
http://arxiv.org/abs/2410.04196
With the growing prominence of the Mixture of Experts (MoE) architecture in developing large-scale foundation models, we investigate the Hierarchical Mixture of Experts (HMoE), a specialized variant of MoE that excels in handling complex inputs and i
Externí odkaz:
http://arxiv.org/abs/2410.02935
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
Prompt-based techniques, such as prompt-tuning and prefix-tuning, have gained prominence for their efficiency in fine-tuning large pre-trained models. Despite their widespread adoption, the theoretical foundations of these methods remain limited. For
Externí odkaz:
http://arxiv.org/abs/2410.02200
Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering state-of-th
Externí odkaz:
http://arxiv.org/abs/2406.19753