Search Results for author: Ning Liu

Found 69 papers, 22 papers with code

Subjective-Aligned Dateset and Metric for Text-to-Video Quality Assessment

no code implementations18 Mar 2024 Tengchuan Kou, Xiaohong Liu, ZiCheng Zhang, Chunyi Li, HaoNing Wu, Xiongkuo Min, Guangtao Zhai, Ning Liu

Based on T2VQA-DB, we propose a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA).

LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper

no code implementations24 Feb 2024 Daoyuan Wu, Shuai Wang, Yang Liu, Ning Liu

Our key insight is that regardless of the kind of jailbreak strategies employed, they eventually need to include a harmful prompt (e. g., "how to make a bomb") in the prompt sent to LLMs, and we found that existing LLMs can effectively recognize such harmful prompts that violate their safety policies.

Adversarial Attack

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

no code implementations31 Jan 2024 Dong Chen, Ning Liu, Yichen Zhu, Zhengping Che, Rui Ma, Fachao Zhang, Xiaofeng Mou, Yi Chang, Jian Tang

Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network.

Knowledge Distillation Network Pruning +1

SWBT: Similarity Weighted Behavior Transformer with the Imperfect Demonstration for Robotic Manipulation

no code implementations17 Jan 2024 Kun Wu, Ning Liu, Zhen Zhao, Di Qiu, Jinming Li, Zhengping Che, Zhiyuan Xu, Qinru Qiu, Jian Tang

Imitation learning (IL), aiming to learn optimal control policies from expert demonstrations, has been an effective method for robot manipulation tasks.

Imitation Learning Robot Manipulation

Assessing Large Language Models in Mechanical Engineering Education: A Study on Mechanics-Focused Conceptual Understanding

no code implementations13 Jan 2024 Jie Tian, Jixin Hou, Zihao Wu, Peng Shu, Zhengliang Liu, Yujie Xiang, Beikang Gu, Nicholas Filla, Yiwei Li, Ning Liu, Xianyan Chen, Keke Tang, Tianming Liu, Xianqiao Wang

This study is a pioneering endeavor to investigate the capabilities of Large Language Models (LLMs) in addressing conceptual questions within the domain of mechanical engineering with a focus on mechanics.

Multiple-choice Prompt Engineering

Peridynamic Neural Operators: A Data-Driven Nonlocal Constitutive Model for Complex Material Responses

no code implementations11 Jan 2024 Siavash Jafarzadeh, Stewart Silling, Ning Liu, Zhongqiang Zhang, Yue Yu

In this work, we introduce a novel integral neural operator architecture called the Peridynamic Neural Operator (PNO) that learns a nonlocal constitutive law from data.

LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model

1 code implementation4 Jan 2024 Yichen Zhu, Minjie Zhu, Ning Liu, Zhicai Ou, Xiaofeng Mou, Jian Tang

In this paper, we introduce LLaVA-$\phi$ (LLaVA-Phi), an efficient multi-modal assistant that harnesses the power of the recently advanced small language model, Phi-2, to facilitate multi-modal dialogues.

Language Modelling Visual Question Answering

FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series Forecasting

1 code implementation27 Dec 2023 Weijun Chen, Heyuan Wang, Ye Tian, Shijie Guan, Ning Liu

Additionally, adopting a frequency-based perspective can effectively mitigate the influence of noise within MTS data, which helps capture more genuine dependencies.

Multivariate Time Series Forecasting Time Series

Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws

no code implementations18 Dec 2023 Ning Liu, Yiming Fan, Xianyi Zeng, Milan Klöwer, Yue Yu

In this work, we introduce conservation law-encoded neural operators (clawNOs), a suite of NOs that endow inference with automatic satisfaction of such conservation laws.

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites

1 code implementation4 Dec 2023 Lei Wang, Jiabang He, Shenshen Li, Ning Liu, Ee-Peng Lim

The fine-grained object attributes and behaviors non-existent in the image may still be generated but not measured by the current evaluation methods.

Hallucination Hallucination Evaluation +2

Learning Interpretable Rules for Scalable Data Representation and Classification

1 code implementation22 Oct 2023 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.

Classification

FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering

1 code implementation23 Aug 2023 Zhenyu Li, Sunqi Fan, Yu Gu, Xiuxing Li, Zhichao Duan, Bowen Dong, Ning Liu, Jianyong Wang

Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users.

Knowledge Base Question Answering

FLAME-based Multi-View 3D Face Reconstruction

no code implementations15 Aug 2023 Wenzhuo Zheng, Junhao Zhao, Xiaohong Liu, Yongyang Pan, Zhenghao Gan, Haozhe Han, Ning Liu

Our work mainly addresses the problem of combining parametric models of faces with multi-view face 3D reconstruction and explores the implementation of a Flame based multi-view training and testing framework for contributing to the field of face 3D reconstruction.

3D Face Reconstruction 3D Reconstruction +1

StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability

1 code implementation9 Aug 2023 Tengchuan Kou, Xiaohong Liu, Wei Sun, Jun Jia, Xiongkuo Min, Guangtao Zhai, Ning Liu

Indeed, most existing quality assessment models evaluate video quality as a whole without specifically taking the subjective experience of video stability into consideration.

Video Quality Assessment Video Stabilization +1

Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models

1 code implementation5 Jun 2023 Jiabang He, Yi Hu, Lei Wang, Xing Xu, Ning Liu, Hui Liu, Heng Tao Shen

Results from the experiments demonstrate that there is a significant performance gap between the in-distribution (ID) and OOD settings for document images, and that fine-grained analysis of distribution shifts can reveal the brittle nature of existing pre-trained VDU models and OOD generalization algorithms.

document understanding Question Answering

Can LLMs like GPT-4 outperform traditional AI tools in dementia diagnosis? Maybe, but not today

no code implementations2 Jun 2023 Zhuo Wang, Rongzhen Li, Bowen Dong, Jie Wang, Xiuxing Li, Ning Liu, Chenhui Mao, Wei zhang, Liling Dong, Jing Gao, Jianyong Wang

In this paper, we explore the potential of LLMs such as GPT-4 to outperform traditional AI tools in dementia diagnosis.

Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning

2 code implementations25 May 2023 Hongzuo Xu, Yijie Wang, Juhui Wei, Songlei Jian, Yizhou Li, Ning Liu

Due to the unsupervised nature of anomaly detection, the key to fueling deep models is finding supervisory signals.

Anomaly Detection

Bridging the Language Gap: Knowledge Injected Multilingual Question Answering

no code implementations6 Apr 2023 Zhichao Duan, Xiuxing Li, Zhengyan Zhang, Zhenyu Li, Ning Liu, Jianyong Wang

As a popular topic in natural language processing tasks, extractive question answering task (extractive QA) has gained extensive attention in the past few years.

Cross-Lingual Transfer Extractive Question-Answering +3

CP$^3$: Channel Pruning Plug-in for Point-based Networks

no code implementations23 Mar 2023 Yaomin Huang, Ning Liu, Zhengping Che, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Guixu Zhang, Xinmei Liu, Feifei Feng, Jian Tang

CP$^3$ is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs.

Gauges and Accelerated Optimization over Smooth and/or Strongly Convex Sets

no code implementations9 Mar 2023 Ning Liu, Benjamin Grimmer

We consider feasibility and constrained optimization problems defined over smooth and/or strongly convex sets.

ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction

1 code implementation ICCV 2023 Jiabang He, Lei Wang, Yi Hu, Ning Liu, Hui Liu, Xing Xu, Heng Tao Shen

To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples.

Document AI In-Context Learning

CP3: Channel Pruning Plug-In for Point-Based Networks

no code implementations CVPR 2023 Yaomin Huang, Ning Liu, Zhengping Che, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Guixu Zhang, Xinmei Liu, Feifei Feng, Jian Tang

Directly implementing the 2D CNN channel pruning methods to PNNs undermine the performance of PNNs because of the different representations of 2D images and 3D point clouds as well as the network architecture disparity.

ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector

no code implementations CVPR 2023 Yichen Zhu, Qiqi Zhou, Ning Liu, Zhiyuan Xu, Zhicai Ou, Xiaofeng Mou, Jian Tang

Unlike existing works that struggle to balance the trade-off between inference speed and SOD performance, in this paper, we propose a novel Scale-aware Knowledge Distillation (ScaleKD), which transfers knowledge of a complex teacher model to a compact student model.

Knowledge Distillation object-detection +2

INO: Invariant Neural Operators for Learning Complex Physical Systems with Momentum Conservation

no code implementations29 Dec 2022 Ning Liu, Yue Yu, Huaiqian You, Neeraj Tatikola

Neural operators, which emerge as implicit solution operators of hidden governing equations, have recently become popular tools for learning responses of complex real-world physical systems.

Toward a Unified Framework for Unsupervised Complex Tabular Reasoning

1 code implementation20 Dec 2022 Zhenyu Li, Xiuxing Li, Zhichao Duan, Bowen Dong, Ning Liu, Jianyong Wang

To bridge the gap between the programs and natural language sentences, we design a powerful "NL-Generator" module to generate natural language sentences with complex logic from these programs.

Data Augmentation Fact Verification +1

Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models

1 code implementation27 Nov 2022 Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu

In this paper, we propose a new model architecture with alignment-enriched tuning (dubbed AETNet) upon pre-trained document image models, to adapt downstream tasks with the joint task-specific supervised and alignment-aware contrastive objective.

Effective Few-Shot Named Entity Linking by Meta-Learning

1 code implementation12 Jul 2022 Xiuxing Li, Zhenyu Li, Zhengyan Zhang, Ning Liu, Haitao Yuan, Wei zhang, Zhiyuan Liu, Jianyong Wang

In this paper, we endeavor to solve the problem of few-shot entity linking, which only requires a minimal amount of in-domain labeled data and is more practical in real situations.

Entity Linking Knowledge Base Completion +2

A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences

no code implementations9 Jun 2022 Yu Fan, ZiCheng Zhang, Wei Sun, Xiongkuo Min, Wei Lu, Tao Wang, Ning Liu, Guangtao Zhai

Point cloud is one of the most widely used digital formats of 3D models, the visual quality of which is quite sensitive to distortions such as downsampling, noise, and compression.

Point Cloud Quality Assessment

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

1 code implementation NeurIPS 2021 Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, Siyue Wang, Minghai Qin, Bin Ren, Yanzhi Wang, Sijia Liu, Xue Lin

Systematical evaluation on accuracy, training speed, and memory footprint are conducted, where the proposed MEST framework consistently outperforms representative SOTA works.

CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization

no code implementations21 Oct 2021 Wenzheng Hu, Zhengping Che, Ning Liu, Mingyang Li, Jian Tang, ChangShui Zhang, Jianqiang Wang

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks.

Scalable Rule-Based Representation Learning for Interpretable Classification

2 code implementations NeurIPS 2021 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.

Classification Representation Learning

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

2 code implementations NeurIPS 2021 Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin, Sijia Liu, Zhangyang Wang, Yanzhi Wang

Based on our analysis, we summarize a guideline for parameter settings in regards of specific architecture characteristics, which we hope to catalyze the research progress on the topic of lottery ticket hypothesis.

Beyond Outlier Detection: Outlier Interpretation by Attention-Guided Triplet Deviation Network

1 code implementation19 Apr 2021 Hongzuo Xu, Yijie Wang, Songlei Jian, Zhenyu Huang, Ning Liu, Yongjun Wang, Fei Li

We obtain an optimal attention-guided embedding space with expanded high-level information and rich semantics, and thus outlying behaviors of the queried outlier can be better unfolded.

Anomaly Detection Outlier Interpretation

Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning

no code implementations13 Apr 2021 Ning Liu, Songlei Jian, Dongsheng Li, Yiming Zhang, Zhiquan Lai, Hongzuo Xu

Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks.

Graph Classification Graph Matching +2

IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning

no code implementations22 Mar 2021 Wei zhang, Yunfeng Zhang, Ning Liu, Kai Ren, Pengfei Wang

This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL).

Reinforcement Learning (RL)

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

no code implementations19 Feb 2021 Ning Liu, Geng Yuan, Zhengping Che, Xuan Shen, Xiaolong Ma, Qing Jin, Jian Ren, Jian Tang, Sijia Liu, Yanzhi Wang

In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i. e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network.

Model Compression

Shape Self-Correction for Unsupervised Point Cloud Understanding

no code implementations ICCV 2021 Ye Chen, Jinxian Liu, Bingbing Ni, Hang Wang, Jiancheng Yang, Ning Liu, Teng Li, Qi Tian

Then the destroyed shape and the normal shape are sent into a point cloud network to get representations, which are employed to segment points that belong to distorted parts and further reconstruct them to restore the shape to normal.

Self-Supervised Learning

RRL: A Scalable Classifier for Interpretable Rule-Based Representation Learning

no code implementations1 Jan 2021 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.

Representation Learning

DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

no code implementations4 Nov 2020 Yushuo Guan, Ning Liu, Pengyu Zhao, Zhengping Che, Kaigui Bian, Yanzhi Wang, Jian Tang

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment.

Neural Architecture Search

Dynamics of Momentum Distribution and Structure Factor in a Weakly Interacting Bose Gas with a Periodical Modulation

no code implementations25 Apr 2020 Ning Liu, Zhanchun Tu

The momentum distribution and dynamical structure factor in a weakly interacting Bose gas with a time-dependent periodic modulation in terms of the Bogoliubov treatment are investigated.

Quantum Gases

Transparent Classification with Multilayer Logical Perceptrons and Random Binarization

1 code implementation10 Dec 2019 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

In this paper, we propose a new hierarchical rule-based model for classification tasks, named Concept Rule Sets (CRS), which has both a strong expressive ability and a transparent inner structure.

Binarization Classification +1

Deep Compressed Pneumonia Detection for Low-Power Embedded Devices

no code implementations4 Nov 2019 Hongjia Li, Sheng Lin, Ning Liu, Caiwen Ding, Yanzhi Wang

Deep neural networks (DNNs) have been expanded into medical fields and triggered the revolution of some medical applications by extracting complex features and achieving high accuracy and performance, etc.

Pneumonia Detection

REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs

no code implementations29 Sep 2019 Caiwen Ding, Shuo Wang, Ning Liu, Kaidi Xu, Yanzhi Wang, Yun Liang

To achieve real-time, highly-efficient implementations on FPGA, we present the detailed hardware implementation of block circulant matrices on CONV layers and develop an efficient processing element (PE) structure supporting the heterogeneous weight quantization, CONV dataflow and pipelining techniques, design optimization, and a template-based automatic synthesis framework to optimally exploit hardware resource.

Model Compression object-detection +2

Distinguishing Individual Red Pandas from Their Faces

no code implementations9 Aug 2019 Qi He, Qijun Zhao, Ning Liu, Peng Chen, Zhihe Zhang, Rong Hou

We are going to release our database and model in the public domain to promote the research on automatic animal identification and particularly on the technique for protecting red pandas.

A Stochastic-Computing based Deep Learning Framework using Adiabatic Quantum-Flux-Parametron SuperconductingTechnology

no code implementations22 Jul 2019 Ruizhe Cai, Ao Ren, Olivia Chen, Ning Liu, Caiwen Ding, Xuehai Qian, Jie Han, Wenhui Luo, Nobuyuki Yoshikawa, Yanzhi Wang

Further, the application of SC has been investigated in DNNs in prior work, and the suitability has been illustrated as SC is more compatible with approximate computations.

AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates

no code implementations6 Jul 2019 Ning Liu, Xiaolong Ma, Zhiyuan Xu, Yanzhi Wang, Jian Tang, Jieping Ye

This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose an innovative additional purification step for further weight reduction without accuracy loss; and (iii) develop effective heuristic search method enhanced by experience-based guided search, replacing the prior deep reinforcement learning technique which has underlying incompatibility with the target pruning problem.

Model Compression

ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding

1 code implementation CVPR 2019 Ning Liu, Yongchao Long, Changqing Zou, Qun Niu, Li Pan, Hefeng Wu

We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes.

Crowd Counting

StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs

1 code implementation29 Jul 2018 Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Xiaolong Ma, Ning Liu, Linfeng Zhang, Jian Tang, Kaisheng Ma, Xue Lin, Makan Fardad, Yanzhi Wang

Without loss of accuracy on the AlexNet model, we achieve 2. 58X and 3. 65X average measured speedup on two GPUs, clearly outperforming the prior work.

Model Compression

Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICs

no code implementations28 Mar 2018 Caiwen Ding, Ao Ren, Geng Yuan, Xiaolong Ma, Jiayu Li, Ning Liu, Bo Yuan, Yanzhi Wang

For FPGA implementations on deep convolutional neural networks (DCNNs), we achieve at least 152X and 72X improvement in performance and energy efficiency, respectively using the SWM-based framework, compared with the baseline of IBM TrueNorth processor under same accuracy constraints using the data set of MNIST, SVHN, and CIFAR-10.

Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data

no code implementations28 Jan 2018 Ning Liu, Ying Liu, Brent Logan, Zhiyuan Xu, Jian Tang, Yanzhi Wang

This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data.

reinforcement-learning Reinforcement Learning (RL)

FFT-Based Deep Learning Deployment in Embedded Systems

no code implementations13 Dec 2017 Sheng Lin, Ning Liu, Mahdi Nazemi, Hongjia Li, Caiwen Ding, Yanzhi Wang, Massoud Pedram

The large model size of DNNs, while providing excellent accuracy, also burdens the embedded platforms with intensive computation and storage.

speech-recognition Speech Recognition

A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning

no code implementations13 Mar 2017 Ning Liu, Zhe Li, Zhiyuan Xu, Jielong Xu, Sheng Lin, Qinru Qiu, Jian Tang, Yanzhi Wang

Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.

Cloud Computing Decision Making +3

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