Search Results for author: Junjie Wang

Found 39 papers, 13 papers with code

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering

1 code implementation Findings (EMNLP) 2021 Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

On the other hand, trilinear models such as the CTI model efficiently utilize the inter-modality information between answers, questions, and images, while ignoring intra-modality information.

Multiple-choice Question Answering +1

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing

no code implementations5 Mar 2024 Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Qing Wang

Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.

Multimodal Reasoning Sentence +1

Adversarial Testing for Visual Grounding via Image-Aware Property Reduction

no code implementations2 Mar 2024 Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Boyu Wu, Fanjiang Xu, Qing Wang

To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.

Visual Grounding

Evaluating Decision Optimality of Autonomous Driving via Metamorphic Testing

no code implementations28 Feb 2024 Mingfei Cheng, Yuan Zhou, Xiaofei Xie, Junjie Wang, Guozhu Meng, Kairui Yang

In this paper, we focus on evaluating the decision-making quality of an ADS and propose the first method for detecting non-optimal decision scenarios (NoDSs), where the ADS does not compute optimal paths for AVs.

Autonomous Driving Decision Making

StructLM: Towards Building Generalist Models for Structured Knowledge Grounding

no code implementations26 Feb 2024 Alex Zhuang, Ge Zhang, Tianyu Zheng, Xinrun Du, Junjie Wang, Weiming Ren, Stephen W. Huang, Jie Fu, Xiang Yue, Wenhu Chen

Utilizing this dataset, we train a series of models, referred to as StructLM, based on the Mistral and the CodeLlama model family, ranging from 7B to 34B parameters.

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

no code implementations14 Feb 2024 Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

With the development of LLMs, the security threats of LLMs are getting more and more attention.

CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark

1 code implementation22 Jan 2024 Ge Zhang, Xinrun Du, Bei Chen, Yiming Liang, Tongxu Luo, Tianyu Zheng, Kang Zhu, Yuyang Cheng, Chunpu Xu, Shuyue Guo, Haoran Zhang, Xingwei Qu, Junjie Wang, Ruibin Yuan, Yizhi Li, Zekun Wang, Yudong Liu, Yu-Hsuan Tsai, Fengji Zhang, Chenghua Lin, Wenhao Huang, Wenhu Chen, Jie Fu

We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context.

Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs

2 code implementations9 Jan 2024 Junjie Wang, Dan Yang, Binbin Hu, Yue Shen, Ziqi Liu, Wen Zhang, Jinjie Gu, Zhiqiang Zhang

Considering the impressive natural language processing ability of large language models (LLMs), we try to leverage LLMs to solve this issue.

AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation

no code implementations26 Dec 2023 Junjie Wang, Yicheng Chen, Wangshu Zhang, Sen Hu, Teng Xu, Jing Zheng

In the second stage, we distill the knowledge from the existing teacher adapters into the student adapter to help its inference.

Knowledge Distillation Retrieval

A Survey on Query-based API Recommendation

no code implementations17 Dec 2023 Moshi Wei, Nima Shiri Harzevili, Alvine Boaye Belle, Junjie Wang, Lin Shi, Jinqiu Yang, Song Wang, Ming Zhen, Jiang

We also investigate the typical data extraction procedures and collection approaches employed by the existing approaches.

From Beginner to Expert: Modeling Medical Knowledge into General LLMs

no code implementations2 Dec 2023 Qiang Li, Xiaoyan Yang, Haowen Wang, Qin Wang, Lei Liu, Junjie Wang, Yang Zhang, Mingyuan Chu, Sen Hu, Yicheng Chen, Yue Shen, Cong Fan, Wangshu Zhang, Teng Xu, Jinjie Gu, Jing Zheng, Guannan Zhang Ant Group

(3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs.

Language Modelling Large Language Model +3

GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions

no code implementations27 Nov 2023 Jiemin Fang, Junjie Wang, Xiaopeng Zhang, Lingxi Xie, Qi Tian

Specifically, we first extract the region of interest (RoI) corresponding to the text instruction, aligning it to 3D Gaussians.

3D scene Editing

EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval

1 code implementation2 Oct 2023 Yiyao Yu, Junjie Wang, Yuxiang Zhang, Lin Zhang, Yujiu Yang, Tetsuya Sakai

Artificial intelligence (AI) technologies should adhere to human norms to better serve our society and avoid disseminating harmful or misleading information, particularly in Conversational Information Retrieval (CIR).

Ethics Information Retrieval +1

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

no code implementations17 May 2023 Ping Yang, Junyu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Jiaxing Zhang, Pingjian Zhang

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment analysis.

Event Extraction named-entity-recognition +3

NER-to-MRC: Named-Entity Recognition Completely Solving as Machine Reading Comprehension

no code implementations6 May 2023 Yuxiang Zhang, Junjie Wang, Xinyu Zhu, Tetsuya Sakai, Hayato Yamana

Named-entity recognition (NER) detects texts with predefined semantic labels and is an essential building block for natural language processing (NLP).

Machine Reading Comprehension named-entity-recognition +2

Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning

no code implementations23 Nov 2022 Junjie Wang, Yao Mu, Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Ping Luo, Bin Wang, Jianye Hao

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging.

Model-based Reinforcement Learning reinforcement-learning +1

Solving Math Word Problems via Cooperative Reasoning induced Language Models

1 code implementation28 Oct 2022 Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang

This inspires us to develop a cooperative reasoning-induced PLM for solving MWPs, called Cooperative Reasoning (CoRe), resulting in a human-like reasoning architecture with system 1 as the generator and system 2 as the verifier.

Arithmetic Reasoning Math

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective

1 code implementation16 Oct 2022 Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

We propose a new paradigm for zero-shot learners that is format agnostic, i. e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and sentiment analysis.

Multiple-choice Natural Language Inference +4

TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene

no code implementations5 Oct 2022 Luyuan Xie, Yan Zhong, Lin Yang, Zhaoyu Yan, Zhonghai Wu, Junjie Wang

In our experiments, the performance gain brought by GridMask is stronger than spectrum augmentation in ASCs.

AutoML Data Augmentation

Im2Oil: Stroke-Based Oil Painting Rendering with Linearly Controllable Fineness Via Adaptive Sampling

1 code implementation27 Sep 2022 Zhengyan Tong, Xiaohang Wang, Shengchao Yuan, Xuanhong Chen, Junjie Wang, Xiangzhong Fang

Comparison with existing state-of-the-art oil painting techniques shows that our results have higher fidelity and more realistic textures.

Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss

1 code implementation5 Aug 2022 Junjie Wang, Yuxiang Zhang, Ping Yang, Ruyi Gan

This report describes a pre-trained language model Erlangshen with propensity-corrected loss, the No. 1 in CLUE Semantic Matching Challenge.

Language Modelling Masked Language Modeling

Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification

1 code implementation22 Jan 2022 Junjie Wang, Feng Gao, Junyu Dong, Qian Du

Second, an adaptive DropBlock (AdapDrop) is proposed as a regularization method employed in the generator and discriminator to alleviate the mode collapse issue.

Classification Hyperspectral Image Classification

Change Detection from Synthetic Aperture Radar Images via Graph-Based Knowledge Supplement Network

1 code implementation22 Jan 2022 Junjie Wang, Feng Gao, Junyu Dong, Shan Zhang, Qian Du

Synthetic aperture radar (SAR) image change detection is a vital yet challenging task in the field of remote sensing image analysis.

Change Detection Feature Correlation

Low-Latency Online Speaker Diarization with Graph-Based Label Generation

no code implementations27 Nov 2021 Yucong Zhang, Qinjian Lin, Weiqing Wang, Lin Yang, Xuyang Wang, Junjie Wang, Ming Li

To ensure the low latency in the online setting, we introduce a variant of AHC, namely chkpt-AHC, to cluster the speakers.

Clustering speaker-diarization +1

Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning

no code implementations22 Sep 2021 Junjie Wang, Qichao Zhang, Dongbin Zhao

We train several state-of-the-art deep reinforcement learning methods in the designed training scenarios and provide the benchmark metrics evaluation results of the trained models in the test scenarios.

Autonomous Driving Benchmarking +4

Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

no code implementations6 Apr 2021 Junjie Wang, Feng Gao, Junyu Dong

Convolutional neural networks (CNN) have made great progress for synthetic aperture radar (SAR) images change detection.

Change Detection

TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

no code implementations4 Apr 2021 Tze Yuang Chong, Xuyang Wang, Lin Yang, Junjie Wang

Also, the TransfoRNN model was applied on the LibriSpeech speech recognition task and has shown comparable results with the Transformer models.

Language Modelling speech-recognition +1

Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery

no code implementations ICCV 2021 Zhenbo Yu, Junjie Wang, Jingwei Xu, Bingbing Ni, Chenglong Zhao, Minsi Wang, Wenjun Zhang

The challenges of the latter task are two folds: (1) pose failure (i. e., pose mismatching -- different skeleton definitions in dataset and SMPL , and pose ambiguity -- endpoints have arbitrary joint angle configurations for the same 3D joint coordinates).

3D Pose Estimation Human Mesh Recovery

Training Wake Word Detection with Synthesized Speech Data on Confusion Words

no code implementations3 Nov 2020 Yan Jia, Zexin Cai, Murong Ma, Zeqing Zhao, Xuyang Wang, Junjie Wang, Ming Li

Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords.

Data Augmentation Keyword Spotting +1

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