Search Results for author: Zihao Li

Found 27 papers, 14 papers with code

UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework

1 code implementation16 Nov 2023 Chris Kelly, Luhui Hu, Cindy Yang, Yu Tian, Deshun Yang, Bang Yang, Zaoshan Huang, Zihao Li, Yuexian Zou

In the current landscape of artificial intelligence, foundation models serve as the bedrock for advancements in both language and vision domains.

Mapping the Empirical Evidence of the GDPR (In-)Effectiveness: A Systematic Review

no code implementations25 Oct 2023 Wenlong Li, Zihao Li, Wenkai Li, Yueming Zhang, Aolan Li

In the realm of data protection, a striking disconnect prevails between traditional domains of doctrinal, legal, theoretical, and policy-based inquiries and a burgeoning body of empirical evidence.

One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems

no code implementations22 Oct 2023 Zuoli Tang, ZhaoXin Huan, Zihao Li, Xiaolu Zhang, Jun Hu, Chilin Fu, Jun Zhou, Chenliang Li

We expect that by mixing the user's behaviors across different domains, we can exploit the common knowledge encoded in the pre-trained language model to alleviate the problems of data sparsity and cold start problems.

Language Modelling Question Answering +2

Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks

no code implementations16 Oct 2023 Zihao Li, Xiang Ji, Minshuo Chen, Mengdi Wang

In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE).

Off-policy evaluation reinforcement-learning

Large Language Models and Control Mechanisms Improve Text Readability of Biomedical Abstracts

1 code implementation22 Sep 2023 Zihao Li, Samuel Belkadi, Nicolo Micheletti, Lifeng Han, Matthew Shardlow, Goran Nenadic

In this work, we investigate the ability of state-of-the-art large language models (LLMs) on the task of biomedical abstract simplification, using the publicly available dataset for plain language adaptation of biomedical abstracts (\textbf{PLABA}).

Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion

no code implementations1 Sep 2023 Zaynab Zahra, Zihao Li, Rosa Filgueira

This paper introduces Laminar, a novel serverless framework based on dispel4py, a parallel stream-based dataflow library.

Code Completion Code Search +1

DeepGATGO: A Hierarchical Pretraining-Based Graph-Attention Model for Automatic Protein Function Prediction

no code implementations24 Jul 2023 Zihao Li, Changkun Jiang, Jianqiang Li

Then, we use GATs to dynamically extract the structural information of non-Euclidean data, and learn general features of the label dataset with contrastive learning by constructing positive and negative example samples.

Contrastive Learning Graph Attention +2

Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation

1 code implementation12 Jul 2023 Shengbo Gao, Ziji Zhang, Jiechao Ma, Zihao Li, Shu Zhang

Our approach is based on a mutual learning strategy that incorporates two modules: the Cross-sample Mutual Attention Module (CMA) and the Omni-Correlation Consistency Module (OCC).

Image Segmentation Segmentation +2

Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP

no code implementations21 Jun 2023 Jiacheng Guo, Zihao Li, Huazheng Wang, Mengdi Wang, Zhuoran Yang, Xuezhou Zhang

In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses it for more efficient exploration and planning.

Efficient Exploration Representation Learning

Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism

no code implementations29 May 2023 Zihao Li, Zhuoran Yang, Mengdi Wang

In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices.

Decision Making Econometrics +2

M$^2$DAR: Multi-View Multi-Scale Driver Action Recognition with Vision Transformer

1 code implementation13 May 2023 Yunsheng Ma, Liangqi Yuan, Amr Abdelraouf, Kyungtae Han, Rohit Gupta, Zihao Li, Ziran Wang

Ensuring traffic safety and preventing accidents is a critical goal in daily driving, where the advancement of computer vision technologies can be leveraged to achieve this goal.

Action Recognition

Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation

1 code implementation27 Apr 2023 Zihao Li, Pan Gao, Hui Yuan, Ran Wei, Manoranjan Paul

Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.

3D Object Classification 3D Part Segmentation +2

The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination

no code implementations21 Apr 2023 Zihao Li

With the launch of ChatGPT, Large Language Models (LLMs) are shaking up our whole society, rapidly altering the way we think, create and live.

DiffuRec: A Diffusion Model for Sequential Recommendation

1 code implementation3 Apr 2023 Zihao Li, Aixin Sun, Chenliang Li

Mainstream solutions to Sequential Recommendation (SR) represent items with fixed vectors.

Sequential Recommendation

Dynamic Local Feature Aggregation for Learning on Point Clouds

1 code implementation7 Jan 2023 Zihao Li, Pan Gao, Hui Yuan, Ran Wei

Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers.

Point Cloud Classification

Latent Space Diffusion Models of Cryo-EM Structures

no code implementations25 Nov 2022 Karsten Kreis, Tim Dockhorn, Zihao Li, Ellen Zhong

The state-of-the-art method cryoDRGN uses a Variational Autoencoder (VAE) framework to learn a continuous distribution of protein structures from single particle cryo-EM imaging data.

Generative Modeling in Structural-Hankel Domain for Color Image Inpainting

1 code implementation25 Nov 2022 Zihao Li, CHUNHUA WU, Shenglin Wu, Wenbo Wan, Yuhao Wang, Qiegen Liu

To better apply the score-based generative model to learn the internal statistical distribution within patches, the large-scale Hankel matrices are finally folded into the higher dimensional tensors for prior learning.

Image Inpainting

Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning

no code implementations6 Oct 2022 Chaolun Ma, Bruce Wang, Zihao Li, Ahmadreza Mahmoudzadeh, Yunlong Zhang

The numerical tests are conducted on a single corridor and on a local grid network under three traffic demand scenarios of low, medium, and heavy traffic, respectively.

reinforcement-learning Reinforcement Learning (RL)

FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs

1 code implementation17 Jun 2022 Hui Li, Zihao Li, Rui Ma, Tieru Wu

In this paper, we propose a novel CAM weighting scheme, named FD-CAM, to improve both the faithfulness and discriminability of the CAM-based CNN visual explanation.

Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training

1 code implementation5 Jan 2022 Shu Zhang, Zihao Li, Hong-Yu Zhou, Jiechao Ma, Yizhou Yu

The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications.

Contrastive Learning Medical Object Detection

Variable Augmented Network for Invertible Modality Synthesis-Fusion

1 code implementation2 Sep 2021 Yuhao Wang, Ruirui Liu, Zihao Li, Cailian Yang, Qiegen Liu

As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning.

Image Generation

Improved Lyman Alpha Tomography using Optimized Reconstruction with Constraints on Absorption (ORCA)

no code implementations24 Feb 2021 Zihao Li, Benjamin Horowitz, Zheng Cai

In this work, we propose an improved approach to reconstruct the three-dimensional intergalactic medium from observed Lyman-$\alpha$ forest absorption features.

Astrophysics of Galaxies

Interaction between optical pulse and tumor using finite element analysis

no code implementations19 Jan 2021 Xianlin Song, Ao Teng, Jianshuang Wei, Hao Chen, Yang Zhao, Jianheng Chen, Fangwei Liu, Qianxiang Wan, Guoning Huang, Lingfang Song, Aojie Zhao, Bo Li, Zihao Li, Qiming He, Jinhong Zhang

As a non-destructive biological tissue imaging technology, photoacoustic imaging has important application value in the field of biomedicine.

Biological Physics

WB-DETR: Transformer-Based Detector Without Backbone

no code implementations ICCV 2021 Fanfan Liu, Haoran Wei, Wenzhe Zhao, Guozhen Li, Jingquan Peng, Zihao Li

In this paper, we propose WB-DETR (DETR-based detector Without Backbone) to prove that the reliance on CNN features extraction for a transformer-based detector is not necessary.

object-detection Object Detection

Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices

1 code implementation16 Dec 2020 Shu Zhang, Jincheng Xu, Yu-Chun Chen, Jiechao Ma, Zihao Li, Yizhou Wang, Yizhou Yu

We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.

Computed Tomography (CT) Lesion Detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.