no code implementations • 28 Feb 2024 • Jianxiong Li, Jinliang Zheng, Yinan Zheng, Liyuan Mao, Xiao Hu, Sijie Cheng, Haoyi Niu, Jihao Liu, Yu Liu, Jingjing Liu, Ya-Qin Zhang, Xianyuan Zhan
Multimodal pretraining has emerged as an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progression information; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding.
2 code implementations • 23 Feb 2024 • Zhe Wang, Siqi Fan, Xiaoliang Huo, Tongda Xu, Yan Wang, Jingjing Liu, Yilun Chen, Ya-Qin Zhang
In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.
no code implementations • 9 Feb 2024 • Tongda Xu, Ziran Zhu, Dailan He, Yuanyuan Wang, Ming Sun, Ning li, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang
In addition, we propose a new family of DIS using pure CM.
1 code implementation • 17 Jan 2024 • Tongda Xu, Ziran Zhu, Dailan He, Yanghao Li, Lina Guo, Yuanyuan Wang, Zhe Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang
However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec.
2 code implementations • 10 Jan 2024 • Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu
Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
no code implementations • 26 Oct 2023 • Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atılım Güneş Baydin, Sheila Mcilraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
In this short consensus paper, we outline risks from upcoming, advanced AI systems.
1 code implementation • 15 Oct 2023 • Tianyuan Zou, Zixuan Gu, Yu He, Hideaki Takahashi, Yang Liu, Ya-Qin Zhang
Vertical Federated Learning (VFL) has emerged as a collaborative training paradigm that allows participants with different features of the same group of users to accomplish cooperative training without exposing their raw data or model parameters.
1 code implementation • 22 Sep 2023 • Xiaoxue Chen, Junchen Liu, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
In this paper, we introduce the refractive-reflective field.
no code implementations • 16 Aug 2023 • Tongda Xu, Qian Zhang, Yanghao Li, Dailan He, Zhe Wang, Yuanyuan Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang
We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information.
no code implementations • 27 May 2023 • Xiao Hu, Jianxiong Li, Xianyuan Zhan, Qing-Shan Jia, Ya-Qin Zhang
To unravel this mystery, we identify a long-neglected issue in the query selection schemes of existing PbRL studies: Query-Policy Misalignment.
1 code implementation • 25 May 2023 • Jianxiong Li, Xiao Hu, Haoran Xu, Jingjing Liu, Xianyuan Zhan, Ya-Qin Zhang
Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance.
no code implementations • 18 Apr 2023 • Yujie Yang, Zhilong Zheng, Shengbo Eben Li, Jingliang Duan, Jingjing Liu, Xianyuan Zhan, Ya-Qin Zhang
To address this challenge, we propose an indirect safe RL framework called feasible policy iteration, which guarantees that the feasible region monotonically expands and converges to the maximum one, and the state-value function monotonically improves and converges to the optimal one.
1 code implementation • CVPR 2023 • Xiaoxue Chen, Yuhang Zheng, Yupeng Zheng, Qiang Zhou, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition.
2 code implementations • 20 Mar 2023 • Zhe Wang, Siqi Fan, Xiaoliang Huo, Tongda Xu, Yan Wang, Jingjing Liu, Yilun Chen, Ya-Qin Zhang
In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.
no code implementations • 13 Mar 2023 • Hao Wen, Yuanchun Li, Zunshuai Zhang, Shiqi Jiang, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang, Yunxin Liu
Model elastification generates a high-quality search space of model architectures with the guidance of a developer-specified oracle model.
1 code implementation • 27 Feb 2023 • Pengfei Li, Ruowen Zhao, Yongliang Shi, Hao Zhao, Jirui Yuan, Guyue Zhou, Ya-Qin Zhang
In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS.
1 code implementation • 3 Feb 2023 • Jianxiong Li, Xiao Hu, Haoran Xu, Jingjing Liu, Xianyuan Zhan, Qing-Shan Jia, Ya-Qin Zhang
RGM is formulated as a bi-level optimization problem: the upper layer optimizes a reward correction term that performs visitation distribution matching w. r. t.
no code implementations • 1 Jan 2023 • Tianyuan Zou, Yang Liu, Ya-Qin Zhang
However, previous works show that parties without labels (passive parties) in VFL can infer the sensitive label information owned by the party with labels (active party) or execute backdoor attacks to VFL.
no code implementations • 23 Nov 2022 • Yang Liu, Yan Kang, Tianyuan Zou, Yanhong Pu, Yuanqin He, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang, Qiang Yang
Motivated by the rapid growth in VFL research and real-world applications, we provide a comprehensive review of the concept and algorithms of VFL, as well as current advances and challenges in various aspects, including effectiveness, efficiency, and privacy.
1 code implementation • 19 Oct 2022 • Pengfei Li, Beiwen Tian, Yongliang Shi, Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on.
no code implementations • 29 Sep 2022 • Tongda Xu, Han Gao, Yuanyuan Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang
In this paper, we investigate the problem of bit allocation in Neural Video Compression (NVC).
1 code implementation • 20 Sep 2022 • Tongda Xu, Han Gao, Chenjian Gao, Yuanyuan Wang, Dailan He, Jinyong Pi, Jixiang Luo, Ziyu Zhu, Mao Ye, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC).
2 code implementations • 23 May 2022 • Jianxiong Li, Xianyuan Zhan, Haoran Xu, Xiangyu Zhu, Jingjing Liu, Ya-Qin Zhang
In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas.
1 code implementation • 29 Nov 2021 • Pengfei Li, Yongliang Shi, Tianyu Liu, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations.
1 code implementation • CVPR 2022 • Xiaoxue Chen, Tianyu Liu, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance.
Ranked #51 on Semantic Segmentation on NYU Depth v2
1 code implementation • 12 Sep 2021 • Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
Such a scheme has two limitations: 1) Storing and running several networks for different tasks are expensive for typical robotic platforms.