no code implementations • 15 Feb 2025 • Zongqian Wu, Tianyu Li, Jiaying Yang, Mengmeng Zhan, Xiaofeng Zhu, Lei Feng
Deep iterative chain-of-thought (CoT) reasoning enables LLMs to tackle complex tasks by progressively activating relevant pre-trained knowledge.
1 code implementation • 8 Feb 2025 • Yongfan Chen, Xiuwen Zhu, Tianyu Li, Hao Chen, Chunhua Shen
We introduce a benchmark designed specifically to assess the Physical Coherence of generated videos, PhyCoBench.
1 code implementation • 24 Dec 2024 • Zhibin Wang, Yanxin Cai, Jiayi Zhou, Yangming Zhang, Tianyu Li, Wei Li, Xun Liu, Guoqing Wang, Yang Yang
Efficient compression of remote sensing imagery is a critical solution to alleviate these burdens on satellites.
1 code implementation • 26 Nov 2024 • Yuang Zhao, Tianyu Li, Jiadong Chen, Shenrong Ye, Fuxin Jiang, Tieying Zhang, Xiaofeng Gao
Existing deep learning and linear models often suffer from excessive parameter complexity and lack intuitive interpretability.
Ranked #1 on
Time Series Forecasting
on Weather (96)
no code implementations • 25 Nov 2024 • Yuming Feng, Zhiyang Dou, Ling-Hao Chen, YuAn Liu, Tianyu Li, Jingbo Wang, Zeyu Cao, Wenping Wang, Taku Komura, Lingjie Liu
Once the Wavelet Manifold is built, WDM trains a diffusion model to generate human motions from Wavelet latent vectors.
no code implementations • 5 Nov 2024 • George Jiayuan Gao, Tianyu Li, Nadia Figueroa
We propose an object-centric recovery policy framework to address the challenges of out-of-distribution (OOD) scenarios in visuomotor policy learning.
no code implementations • 3 Sep 2024 • Yifeng Wang, Zhouhong Gu, Siwei Zhang, SuHang Zheng, Tao Wang, Tianyu Li, Hongwei Feng, Yanghua Xiao
Explainable fake news detection predicts the authenticity of news items with annotated explanations.
1 code implementation • 11 Jul 2024 • Minghang Zhou, Tianyu Li, Chaofan Qiao, Dongyu Xie, Guoqing Wang, Ningjuan Ruan, Lin Mei, Yang Yang
Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task.
no code implementations • 5 Jul 2024 • Ye Bai, Jingping Chen, Jitong Chen, Wei Chen, Zhuo Chen, Chuang Ding, Linhao Dong, Qianqian Dong, Yujiao Du, Kepan Gao, Lu Gao, Yi Guo, Minglun Han, Ting Han, Wenchao Hu, Xinying Hu, Yuxiang Hu, Deyu Hua, Lu Huang, Mingkun Huang, Youjia Huang, Jishuo Jin, Fanliu Kong, Zongwei Lan, Tianyu Li, Xiaoyang Li, Zeyang Li, Zehua Lin, Rui Liu, Shouda Liu, Lu Lu, Yizhou Lu, Jingting Ma, Shengtao Ma, Yulin Pei, Chen Shen, Tian Tan, Xiaogang Tian, Ming Tu, Bo wang, Hao Wang, Yuping Wang, Yuxuan Wang, Hanzhang Xia, Rui Xia, Shuangyi Xie, Hongmin Xu, Meng Yang, Bihong Zhang, Jun Zhang, Wanyi Zhang, Yang Zhang, Yawei Zhang, Yijie Zheng, Ming Zou
Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.
Ranked #1 on
Speech Recognition
on AISHELL-1
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
no code implementations • 3 Jul 2024 • Li Fang, Tianyu Li, Yanghong Lin, Shudong Zhou, Wei Yao
Extensive experiments on the 3DRN benchmark dataset, featuring diverse urban environments with virtual TLS reflection noise, show our algorithm improves precision and recall rates for 3D points in reflective regions by 57. 03\% and 31. 80\%, respectively.
1 code implementation • 21 Jun 2024 • Daniel Dauner, Marcel Hallgarten, Tianyu Li, Xinshuo Weng, Zhiyu Huang, Zetong Yang, Hongyang Li, Igor Gilitschenski, Boris Ivanovic, Marco Pavone, Andreas Geiger, Kashyap Chitta
On a large set of challenging scenarios, we observe that simple methods with moderate compute requirements such as TransFuser can match recent large-scale end-to-end driving architectures such as UniAD.
no code implementations • 15 Jun 2024 • Yiye Zou, Tianyu Li, Lin Lu, Jingyu Wang, Shufan Zou, Laiping Zhang, Xiaogang Deng
To address this issue, \blueText{graphs and graph networks are used} to learn flow representations across multi-block-structured grids.
no code implementations • 7 Jun 2024 • Seungeun Rho, Laura Smith, Tianyu Li, Sergey Levine, Xue Bin Peng, Sehoon Ha
In this sense, we introduce Language Guided Skill Discovery (LGSD), a skill discovery framework that aims to directly maximize the semantic diversity between skills.
no code implementations • 15 Mar 2024 • Meixuan Li, Tianyu Li, Guoqing Wang, Peng Wang, Yang Yang, Heng Tao Shen
Aligning these distributions between corresponding regions from different tasks imparts higher flexibility and capacity to capture intra-region structures, accommodating a broader range of tasks.
2 code implementations • CVPR 2024 • Jiazhi Yang, Shenyuan Gao, Yihang Qiu, Li Chen, Tianyu Li, Bo Dai, Kashyap Chitta, Penghao Wu, Jia Zeng, Ping Luo, Jun Zhang, Andreas Geiger, Yu Qiao, Hongyang Li
In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline.
1 code implementation • 7 Mar 2024 • Yunsong Zhou, Linyan Huang, Qingwen Bu, Jia Zeng, Tianyu Li, Hang Qiu, Hongzi Zhu, Minyi Guo, Yu Qiao, Hongyang Li
Hereby, we introduce the Embodied Language Model (ELM), a comprehensive framework tailored for agents' understanding of driving scenes with large spatial and temporal spans.
no code implementations • 16 Jan 2024 • Junliang Luo, Tianyu Li, Di wu, Michael Jenkin, Steve Liu, Gregory Dudek
Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications.
1 code implementation • 31 Dec 2023 • Qifang Zhao, Weidong Ren, Tianyu Li, Xiaoxiao Xu, Hong Liu
We introduce \textit{GraphGPT}, a novel model for Graph learning by self-supervised Generative Pre-training Transformers.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
3 code implementations • 28 Dec 2023 • Haisong Liu, Yang Chen, Haiguang Wang, Zetong Yang, Tianyu Li, Jia Zeng, Li Chen, Hongyang Li, LiMin Wang
SparseOcc initially reconstructs a sparse 3D representation from camera-only inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries.
1 code implementation • 26 Dec 2023 • Tianyu Li, Peijin Jia, Bangjun Wang, Li Chen, Kun Jiang, Junchi Yan, Hongyang Li
A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines.
no code implementations • 20 Dec 2023 • Yuhui Wu, Guoqing Wang, Zhiwen Wang, Yang Yang, Tianyu Li, Malu Zhang, Chongyi Li, Heng Tao Shen
By treating Retinex- and semantic-based priors as the condition, JoReS-Diff presents a unique perspective for establishing an diffusion model for LLIE and similar image enhancement tasks.
no code implementations • CVPR 2024 • Tianyu Li, Calvin Qiao, Guanqiao Ren, KangKang Yin, Sehoon Ha
This paper introduces the Accelerated Auto-regressive Motion Diffusion Model (AAMDM), a novel motion synthesis framework designed to achieve quality, diversity, and efficiency all together.
2 code implementations • 19 Sep 2023 • Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Ce Bian, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, Fan Yang, Fei Deng, Feng Wang, Feng Liu, Guangwei Ai, Guosheng Dong, Haizhou Zhao, Hang Xu, Haoze Sun, Hongda Zhang, Hui Liu, Jiaming Ji, Jian Xie, Juntao Dai, Kun Fang, Lei Su, Liang Song, Lifeng Liu, Liyun Ru, Luyao Ma, Mang Wang, Mickel Liu, MingAn Lin, Nuolan Nie, Peidong Guo, Ruiyang Sun, Tao Zhang, Tianpeng Li, Tianyu Li, Wei Cheng, WeiPeng Chen, Xiangrong Zeng, Xiaochuan Wang, Xiaoxi Chen, Xin Men, Xin Yu, Xuehai Pan, Yanjun Shen, Yiding Wang, Yiyu Li, Youxin Jiang, Yuchen Gao, Yupeng Zhang, Zenan Zhou, Zhiying Wu
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
no code implementations • 5 Sep 2023 • Tianyu Li, Nadia Figueroa
Given a new task instance/context, the Elastic-GMM is transformed with Laplacian Editing and used to re-estimate the LPV-DS policy.
no code implementations • 19 Jul 2023 • Qifang Zhao, Tianyu Li, Meng Du, Yu Jiang, Qinghui Sun, Zhongyao Wang, Hong Liu, Huan Xu
When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a very high cost.
1 code implementation • 15 Jun 2023 • Tianyu Li, Subhankar Roy, Huayi Zhou, Hongtao Lu, Stephane Lathuiliere
To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation.
1 code implementation • 24 May 2023 • Daniël Vos, Jelle Vos, Tianyu Li, Zekeriya Erkin, Sicco Verwer
By leveraging the better privacy-utility trade-off of PrivaTree we are able to train decision trees with significantly better robustness against backdoor attacks compared to regular decision trees and with meaningful theoretical guarantees.
1 code implementation • NeurIPS 2023 • Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, Feng Wen, Hang Xu, Ping Luo, Junchi Yan, Wei zhang, Hongyang Li
Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments.
no code implementations • 19 Apr 2023 • Laura Smith, J. Chase Kew, Tianyu Li, Linda Luu, Xue Bin Peng, Sehoon Ha, Jie Tan, Sergey Levine
Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running.
1 code implementation • 11 Apr 2023 • Tianyu Li, Li Chen, Huijie Wang, Yang Li, Jiazhi Yang, Xiangwei Geng, Shengyin Jiang, Yuting Wang, Hang Xu, Chunjing Xu, Junchi Yan, Ping Luo, Hongyang Li
Understanding the road genome is essential to realize autonomous driving.
Ranked #6 on
3D Lane Detection
on OpenLane-V2 val
no code implementations • 18 Mar 2023 • Wenwen Tong, Jiangwei Xie, Tianyu Li, Hanming Deng, Xiangwei Geng, Ruoyi Zhou, Dingchen Yang, Bo Dai, Lewei Lu, Hongyang Li
The proposed data augmentation approach contributes to a gain of 1. 7% and 1. 4% in terms of detection accuracy, on Waymo and nuScences respectively.
2 code implementations • 12 Sep 2022 • Hongyang Li, Chonghao Sima, Jifeng Dai, Wenhai Wang, Lewei Lu, Huijie Wang, Jia Zeng, Zhiqi Li, Jiazhi Yang, Hanming Deng, Hao Tian, Enze Xie, Jiangwei Xie, Li Chen, Tianyu Li, Yang Li, Yulu Gao, Xiaosong Jia, Si Liu, Jianping Shi, Dahua Lin, Yu Qiao
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
no code implementations • 8 Jun 2022 • Tianyu Li, Bogdan Mazoure, Guillaume Rabusseau
Although WFAs have been extended to deal with continuous input data, namely continuous WFAs (CWFAs), it is still unclear how to approximate density functions over sequences of continuous random variables using WFA-based models, due to the limitation on the expressiveness of the model as well as the tractability of approximating density functions via CWFAs.
no code implementations • 14 Feb 2022 • Tianyu Li, Ali Cevahir, Derek Cho, Hao Gong, DuyKhuong Nguyen, Bjorn Stenger
This paper extends the BERT model to e-commerce user data for pre-training representations in a self-supervised manner.
no code implementations • 29 Sep 2021 • Di wu, Tianyu Li, David Meger, Michael Jenkin, Xue Liu, Gregory Dudek
Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.
no code implementations • 1 Jan 2021 • Tianyu Li, Ali Cevahir, Derek Cho, Hao Gong, DuyKhuong Nguyen, Bjorn Stenger
This paper extends the BERT model to user data for pretraining user representations in a self-supervised way.
no code implementations • 19 Oct 2020 • Tianyu Li, Doina Precup, Guillaume Rabusseau
In this paper, we present connections between three models used in different research fields: weighted finite automata~(WFA) from formal languages and linguistics, recurrent neural networks used in machine learning, and tensor networks which encompasses a set of optimization techniques for high-order tensors used in quantum physics and numerical analysis.
1 code implementation • 12 Oct 2020 • Ramin Raziperchikolaei, Tianyu Li, Young-joo Chung
We also apply the NRP framework to a direct neural network structure which predicts the ratings without reconstructing the user and item information.
no code implementations • 21 Aug 2020 • Hao Gong, Qifang Zhao, Tianyu Li, Derek Cho, DuyKhuong Nguyen
1) Meta-learning model: In the context of representation learning with e-commerce user behavior data, we propose a meta-learning framework called the Meta-Profile Network, which extends the ideas of matching network and relation network for knowledge transfer and fast adaptation; 2) Encoding strategy: To keep high fidelity of large-scale long-term sequential behavior data, we propose a time-heatmap encoding strategy that allows the model to encode data effectively; 3) Deep network architecture: A multi-modal model combined with multi-task learning architecture is utilized to address the cross-domain knowledge learning and insufficient label problems.
no code implementations • 7 Feb 2020 • Bogdan Mazoure, Thang Doan, Tianyu Li, Vladimir Makarenkov, Joelle Pineau, Doina Precup, Guillaume Rabusseau
We propose a general framework for policy representation for reinforcement learning tasks.
no code implementations • 12 Nov 2019 • Tianyu Li, Bogdan Mazoure, Doina Precup, Guillaume Rabusseau
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning.
1 code implementation • 15 Oct 2019 • Tianyu Li, Chien-Chih Wang, Yukun Ma, Patricia Ortal, Qifang Zhao, Bjorn Stenger, Yu Hirate
Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model.
1 code implementation • 10 Jul 2019 • Rika Antonova, Akshara Rai, Tianyu Li, Danica Kragic
We propose a model and architecture for a sequential variational autoencoder that embeds the space of simulated trajectories into a lower-dimensional space of latent paths in an unsupervised way.
no code implementations • 1 Mar 2019 • Tianyu Li, Bolun Dai
Learning from complex demonstrations is challenging, especially when the demonstration consists of different strategies.
no code implementations • 17 Dec 2018 • Tianyu Li, Yukun Ma, Jiu Xu, Bjorn Stenger, Chen Liu, Yu Hirate
This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems.
no code implementations • 4 Jul 2018 • Guillaume Rabusseau, Tianyu Li, Doina Precup
In this paper, we unravel a fundamental connection between weighted finite automata~(WFAs) and second-order recurrent neural networks~(2-RNNs): in the case of sequences of discrete symbols, WFAs and 2-RNNs with linear activation functions are expressively equivalent.
no code implementations • 13 Sep 2017 • Tianyu Li, Guillaume Rabusseau, Doina Precup
Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models.
3 code implementations • ICCV 2017 • Rui Huang, Shu Zhang, Tianyu Li, Ran He
This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.