no code implementations • 16 Apr 2024 • Rui Hu, Yahan Tu, Jitao Sang
In this paper, we propose a targeted instruction data generation framework named DFTG that tailored to the hallucination specificity of different models.
no code implementations • 10 Mar 2024 • Yuang Wang, Siyeop Yoon, Pengfei Jin, Matthew Tivnan, Zhennong Chen, Rui Hu, Li Zhang, Zhiqiang Chen, Quanzheng Li, Dufan Wu
As a promising alternative, the Image-to-Image Schr\"odinger Bridge (I2SB) initializes the generative process from corrupted images and integrates training techniques from conditional diffusion models.
no code implementations • 23 Jan 2024 • Yixuan Sun, Sami Khairy, Richard B. Vilim, Rui Hu, Akshay J. Dave
In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the control scheme accordingly.
no code implementations • 9 Dec 2023 • Chaoquan Jiang, Jinqiang Wang, Rui Hu, Jitao Sang
To address this issue, We propose a language-assisted diagnostic method that uses texts instead of images to diagnose bugs in vision models based on multi-modal models (eg CLIP).
no code implementations • 9 Nov 2023 • Ze Yang, Sivabalan Manivasagam, Yun Chen, Jingkang Wang, Rui Hu, Raquel Urtasun
In this work, we present NeuSim, a novel approach that estimates accurate geometry and realistic appearance from sparse in-the-wild data captured at distance and at limited viewpoints.
no code implementations • 2 Nov 2023 • Lunjun Zhang, Yuwen Xiong, Ze Yang, Sergio Casas, Rui Hu, Raquel Urtasun
Learning world models can teach an agent how the world works in an unsupervised manner.
1 code implementation • 30 Oct 2023 • Tianwen Wei, Liang Zhao, Lichang Zhang, Bo Zhu, Lijie Wang, Haihua Yang, Biye Li, Cheng Cheng, Weiwei Lü, Rui Hu, Chenxia Li, Liu Yang, Xilin Luo, Xuejie Wu, Lunan Liu, Wenjun Cheng, Peng Cheng, Jianhao Zhang, XiaoYu Zhang, Lei Lin, Xiaokun Wang, Yutuan Ma, Chuanhai Dong, Yanqi Sun, Yifu Chen, Yongyi Peng, Xiaojuan Liang, Shuicheng Yan, Han Fang, Yahui Zhou
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3. 2 trillion tokens drawn from both English and Chinese texts.
1 code implementation • 25 Oct 2023 • Liu Yang, Haihua Yang, Wenjun Cheng, Lei Lin, Chenxia Li, Yifu Chen, Lunan Liu, Jianfei Pan, Tianwen Wei, Biye Li, Liang Zhao, Lijie Wang, Bo Zhu, Guoliang Li, Xuejie Wu, Xilin Luo, Rui Hu
Large language models (LLMs) have shown great potential to solve varieties of natural language processing (NLP) tasks, including mathematical reasoning.
no code implementations • 7 Sep 2023 • Zikai Zhang, Rui Hu
Federated learning (FL) is designed to preserve data privacy during model training, where the data remains on the client side (i. e., IoT devices), and only model updates of clients are shared iteratively for collaborative learning.
no code implementations • 27 Jun 2023 • Chris Zhang, Runsheng Guo, Wenyuan Zeng, Yuwen Xiong, Binbin Dai, Rui Hu, Mengye Ren, Raquel Urtasun
Recent advances in high-fidelity simulators have enabled closed-loop training of autonomous driving agents, potentially solving the distribution shift in training v. s.
1 code implementation • 6 May 2023 • Rui Hu, Yahan Tu, Jitao Sang
This paper first presents experimental analyses revealing that the existing biased models overfit to bias-conflicting samples in the training data, which negatively impacts the debiasing performance of the target models.
no code implementations • 15 Mar 2023 • Muhammad Jahanzeb Khan, Rui Hu, Mohammad Sadoghi, Dongfang Zhao
To evaluate this approach, the authors develop a framework called Data-Decoupling Federated Learning (DDFL) and compare it with state-of-the-art FL systems that tightly couple data management and computation.
no code implementations • 8 Mar 2023 • Rui Hu, YunMei Chen, Kyungsang Kim, Marcio Aloisio Bezerra Cavalcanti Rockenbach, Quanzheng Li, Huafeng Liu
Deep learning based PET image reconstruction methods have achieved promising results recently.
no code implementations • 8 Mar 2023 • Rui Hu, Jianan Cui, Chengjin Yu, YunMei Chen, Huafeng Liu
Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame.
no code implementations • 21 Feb 2023 • Chenxu Li, Rui Hu, Jianan Cui, Huafeng Liu
Additionally, we compare the spatial and temporal consumption of list-mode data and sinogram data in model-based deep learning methods, demonstrating the superiority of list-mode data in model-based TOF-PET reconstruction.
no code implementations • 7 Sep 2022 • Wei Zhou, Xuanlin Min, Rui Hu, Yiwen Long, Huan Luo, JunYi
Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes.
no code implementations • 9 May 2022 • Rui Hu, Huafeng Liu
Positron emission tomography(PET) image reconstruction is an ill-posed inverse problem and suffers from high level of noise due to limited counts received.
no code implementations • 15 Feb 2022 • Rui Hu, Yanmin Gong, Yuanxiong Guo
Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect privacy in comparison with the traditional centralized learning paradigm.
no code implementations • 26 Nov 2021 • Lik-Hang Lee, Zijun Lin, Rui Hu, Zhengya Gong, Abhishek Kumar, Tangyao Li, Sijia Li, Pan Hui
The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity.
no code implementations • 17 Nov 2021 • Jitao Sang, Jinqiang Wang, Rui Hu, Chaoquan Jiang
Deep network models perform excellently on In-Distribution (ID) data, but can significantly fail on Out-Of-Distribution (OOD) data.
no code implementations • ICLR 2022 • Yuanxiong Guo, Ying Sun, Rui Hu, Yanmin Gong
Communication is a key bottleneck in federated learning where a large number of edge devices collaboratively learn a model under the orchestration of a central server without sharing their own training data.
1 code implementation • 17 Jan 2021 • Yan Wang, Bin Yang, Rui Hu, Ming Liang, Raquel Urtasun
In this paper we propose a model that unifies these two tasks and performs them in the same metric space.
no code implementations • CVPR 2019 • Ming Liang, Bin Yang, Yun Chen, Rui Hu, Raquel Urtasun
In this paper we propose to exploit multiple related tasks for accurate multi-sensor 3D object detection.
Ranked #13 on 3D Object Detection on KITTI Cars Easy
no code implementations • 12 Nov 2020 • Davi Frossard, Simon Suo, Sergio Casas, James Tu, Rui Hu, Raquel Urtasun
In this paper we propose StrObe, a novel approach that minimizes latency by ingesting LiDAR packets and emitting a stream of detections without waiting for the full sweep to be built.
no code implementations • 12 Sep 2020 • Zhidong Gao, Rui Hu, Yanmin Gong
Graph classification has practical applications in diverse fields.
no code implementations • 11 Sep 2020 • Rui Hu, Yanmin Gong
Federated Learning rests on the notion of training a global model distributedly on various devices.
no code implementations • ECCV 2020 • Jerry Liu, Shenlong Wang, Wei-Chiu Ma, Meet Shah, Rui Hu, Pranaab Dhawan, Raquel Urtasun
We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames.
no code implementations • 1 Aug 2020 • Rui Hu, Yanmin Gong, Yuanxiong Guo
Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost.
1 code implementation • ECCV 2020 • Ming Liang, Bin Yang, Rui Hu, Yun Chen, Renjie Liao, Song Feng, Raquel Urtasun
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions.
no code implementations • 3 Jun 2020 • Nemanja Djuric, Henggang Cui, Zhaoen Su, Shangxuan Wu, Huahua Wang, Fang-Chieh Chou, Luisa San Martin, Song Feng, Rui Hu, Yang Xu, Alyssa Dayan, Sidney Zhang, Brian C. Becker, Gregory P. Meyer, Carlos Vallespi-Gonzalez, Carl K. Wellington
One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future.
no code implementations • CVPR 2020 • Ming Liang, Bin Yang, Wenyuan Zeng, Yun Chen, Rui Hu, Sergio Casas, Raquel Urtasun
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles.
no code implementations • 30 Mar 2020 • Rui Hu, Yuanxiong Guo, Yanmin Gong
Federated learning is a machine learning setting where a set of edge devices collaboratively train a model under the orchestration of a central server without sharing their local data.
no code implementations • 28 Mar 2020 • Rui Hu, Yuanxiong Guo, E. Paul. Ratazzi, Yanmin Gong
With the proliferation of smart devices having built-in sensors, Internet connectivity, and programmable computation capability in the era of Internet of things (IoT), tremendous data is being generated at the network edge.
no code implementations • CVPR 2020 • Justin Liang, Namdar Homayounfar, Wei-Chiu Ma, Yuwen Xiong, Rui Hu, Raquel Urtasun
In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods.
Ranked #1000000000 on Instance Segmentation on Cityscapes test (using extra training data)
1 code implementation • ICCV 2019 • Shivam Duggal, Shenlong Wang, Wei-Chiu Ma, Rui Hu, Raquel Urtasun
Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms to enable real-time inference.
no code implementations • CVPR 2019 • Wei-Chiu Ma, Shenlong Wang, Rui Hu, Yuwen Xiong, Raquel Urtasun
In this paper we tackle the problem of scene flow estimation in the context of self-driving.
1 code implementation • CVPR 2019 • Yuwen Xiong, Renjie Liao, Hengshuang Zhao, Rui Hu, Min Bai, Ersin Yumer, Raquel Urtasun
More importantly, we introduce a parameter-free panoptic head which solves the panoptic segmentation via pixel-wise classification.
Ranked #3 on Panoptic Segmentation on Indian Driving Dataset
no code implementations • 30 Aug 2018 • Zonghao Huang, Rui Hu, Yuanxiong Guo, Eric Chan-Tin, Yanmin Gong
The goal of this paper is to provide differential privacy for ADMM-based distributed machine learning.
no code implementations • 2 Feb 2015 • Yandong Wen, Weiyang Liu, Meng Yang, Yuli Fu, Youjun Xiang, Rui Hu
We propose the structured occlusion coding (SOC) to address occlusion problems.
no code implementations • 20 Jun 2013 • Rui Hu, Stephen M. Watt
In a variety of applications, such as handwritten mathematics and diagram labelling, it is common to have symbols of many different sizes in use and for the writing not to follow simple baselines.