no code implementations • 30 Mar 2024 • Bo Liu, Lemeng Wu, Lizhang Chen, Kaizhao Liang, Jiaxu Zhu, Chen Liang, Raghuraman Krishnamoorthi, Qiang Liu
The Lion optimizer has been a promising competitor with the AdamW for training large AI models, with advantages on memory, computation, and sample efficiency.
no code implementations • 25 Mar 2024 • Shujian Zhang, Lemeng Wu, Chengyue Gong, Xingchao Liu
Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
1 code implementation • 1 Dec 2023 • Yunyang Xiong, Bala Varadarajan, Lemeng Wu, Xiaoyu Xiang, Fanyi Xiao, Chenchen Zhu, Xiaoliang Dai, Dilin Wang, Fei Sun, Forrest Iandola, Raghuraman Krishnamoorthi, Vikas Chandra
On segment anything task such as zero-shot instance segmentation, our EfficientSAMs with SAMI-pretrained lightweight image encoders perform favorably with a significant gain (e. g., ~4 AP on COCO/LVIS) over other fast SAM models.
Ranked #3 on Zero-Shot Instance Segmentation on LVIS v1.0 val
no code implementations • 4 May 2023 • Shujian Zhang, Chengyue Gong, Lemeng Wu, Xingchao Liu, Mingyuan Zhou
Ultimately, with this prompt paragraph, AutoML-GPT will automatically conduct the experiments from data processing to model architecture, hyperparameter tuning, and predicted training log.
no code implementations • CVPR 2023 • Xingchao Liu, Lemeng Wu, Shujian Zhang, Chengyue Gong, Wei Ping, Qiang Liu
To further accelerate the computation of the back-propagation, we propose to use a non-uniform discretization to approximate the ODE trajectory, where we measure how straight the trajectory is and gather the straight parts into one discretization step.
no code implementations • 12 Dec 2022 • Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties.
1 code implementation • CVPR 2023 • Lemeng Wu, Dilin Wang, Chengyue Gong, Xingchao Liu, Yunyang Xiong, Rakesh Ranjan, Raghuraman Krishnamoorthi, Vikas Chandra, Qiang Liu
We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods.
no code implementations • 6 Oct 2022 • Yan Zheng, Lemeng Wu, Xingchao Liu, Zhen Chen, Qiang Liu, QiXing Huang
We first propose a diffusion-based generative model to tackle this problem by generating voxelized shapes with close-to-reality outlines and structures.
no code implementations • 2 Sep 2022 • Mao Ye, Lemeng Wu, Qiang Liu
We propose a family of First Hitting Diffusion Models (FHDM), deep generative models that generate data with a diffusion process that terminates at a random first hitting time.
no code implementations • 2 Sep 2022 • Lemeng Wu, Chengyue Gong, Xingchao Liu, Mao Ye, Qiang Liu
AI-based molecule generation provides a promising approach to a large area of biomedical sciences and engineering, such as antibody design, hydrolase engineering, or vaccine development.
no code implementations • 31 Aug 2022 • Xingchao Liu, Lemeng Wu, Mao Ye, Qiang Liu
Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains.
no code implementations • 20 Apr 2022 • Lemeng Wu, Mengchen Liu, Yinpeng Chen, Dongdong Chen, Xiyang Dai, Lu Yuan
In this paper, we propose Residual Mixture of Experts (RMoE), an efficient training pipeline for MoE vision transformers on downstream tasks, such as segmentation and detection.
no code implementations • 16 Feb 2022 • Chengyue Gong, Lemeng Wu, Qiang Liu
Although traditional optimization methods focus on finding a single optimal solution, most objective functions in modern machine learning problems, especially those in deep learning, often have multiple or infinite numbers of optima.
1 code implementation • 2 Dec 2021 • Xingchao Liu, Chengyue Gong, Lemeng Wu, Shujian Zhang, Hao Su, Qiang Liu
We approach text-to-image generation by combining the power of the retrained CLIP representation with an off-the-shelf image generator (GANs), optimizing in the latent space of GAN to find images that achieve maximum CLIP score with the given input text.
Ranked #48 on Text-to-Image Generation on MS COCO
1 code implementation • NeurIPS 2020 • Lemeng Wu, Bo Liu, Peter Stone, Qiang Liu
We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures.
no code implementations • 17 Feb 2021 • Lemeng Wu, Xingchao Liu, Qiang Liu
Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs.
Ranked #618 on Image Classification on ImageNet
1 code implementation • NeurIPS 2020 • Mao Ye, Lemeng Wu, Qiang Liu
Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size.
no code implementations • 23 Mar 2020 • Lemeng Wu, Mao Ye, Qi Lei, Jason D. Lee, Qiang Liu
Recently, Liu et al.[19] proposed a splitting steepest descent (S2D) method that jointly optimizes the neural parameters and architectures based on progressively growing network structures by splitting neurons into multiple copies in a steepest descent fashion.
1 code implementation • ICLR 2020 • Dilin Wang, Meng Li, Lemeng Wu, Vikas Chandra, Qiang Liu
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited.
1 code implementation • NeurIPS 2019 • Qiang Liu, Lemeng Wu, Dilin Wang
We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs.
1 code implementation • CVPR 2019 • Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou, Qi-Xing Huang
Optimizing a network of maps among a collection of objects/domains (or map synchronization) is a central problem across computer vision and many other relevant fields.