Search Results for author: Zheng Chen

Found 121 papers, 41 papers with code

CATAMARAN: A Cross-lingual Long Text Abstractive Summarization Dataset

no code implementations LREC 2022 Zheng Chen, Hongyu Lin

Cross-lingual summarization, which produces the summary in one language from a given source document in another language, could be extremely helpful for humans to obtain information across the world.

Abstractive Text Summarization Articles +1

StainPIDR: A Pathological Image Decouplingand Reconstruction Method for Stain Normalization Based on Color Vector Quantization and Structure Restaining

no code implementations22 Jun 2025 Zheng Chen

We try to eliminate this color discrepancy by decoupling the image into structure features and vector-quantized color features, restaining the structure features with the target color features, and decoding the stained structure features to normalized pathological images.

Diagnostic Quantization

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

1 code implementation26 May 2025 Jue Gong, Tingyu Yang, Jingkai Wang, Zheng Chen, Xing Liu, Hong Gu, Yulun Zhang, Xiaokang Yang

To address this, we design a degradation pipeline that simulates the coexistence of HMB and generic noise, generating synthetic degraded data to train our proposed HAODiff, a human-aware one-step diffusion.

Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition

1 code implementation25 May 2025 Xiaoyang Liu, Bolin Qiu, JieZhang Cao, Zheng Chen, Yulun Zhang, Xiaokang Yang

Image demoir\'eing remains a challenging task due to the complex interplay between texture corruption and color distortions caused by moir\'e patterns.

Image Restoration

OSCAR: One-Step Diffusion Codec for Image Compression Across Multiple Bit-rates

1 code implementation22 May 2025 Jinpei Guo, Yifei Ji, Zheng Chen, Kai Liu, Min Liu, Wang Rao, Wenbo Li, Yong Guo, Yulun Zhang

By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates.

Denoising Image Compression

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

1 code implementation22 May 2025 Zheng Chen, Zichen Zou, Kewei Zhang, Xiongfei Su, Xin Yuan, Yong Guo, Yulun Zhang

To tackle the above issues, we propose DOVE, an efficient one-step diffusion model for real-world VSR.

Video Super-Resolution

NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results

2 code implementations20 Apr 2025 Zheng Chen, Kai Liu, Jue Gong, Jingkai Wang, Lei Sun, Zongwei Wu, Radu Timofte, Yulun Zhang, Xiangyu Kong, Xiaoxuan Yu, Hyunhee Park, Suejin Han, Hakjae Jeon, Dafeng Zhang, Hyung-Ju Chun, Donghun Ryou, Inju Ha, Bohyung Han, Lu Zhao, Yuyi Zhang, Pengyu Yan, Jiawei Hu, Pengwei Liu, Fengjun Guo, Hongyuan Yu, Pufan Xu, Zhijuan Huang, Shuyuan Cui, Peng Guo, Jiahui Liu, Dongkai Zhang, Heng Zhang, Huiyuan Fu, Huadong Ma, Yanhui Guo, Sisi Tian, Xin Liu, Jinwen Liang, Jie Liu, Jie Tang, Gangshan Wu, Zeyu Xiao, Zhuoyuan Li, Yinxiang Zhang, Wenxuan Cai, Vijayalaxmi Ashok Aralikatti, Nikhil Akalwadi, G Gyaneshwar Rao, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudenagudi, Marcos V. Conde, Alejandro Merino, Bruno Longarela, Javier Abad, Weijun Yuan, Zhan Li, Zhanglu Chen, Boyang Yao, Aagam Jain, Milan Kumar Singh, Ankit Kumar, Shubh Kawa, Divyavardhan Singh, Anjali Sarvaiya, Kishor Upla, Raghavendra Ramachandra, Chia-Ming Lee, Yu-Fan Lin, Chih-Chung Hsu, Risheek V Hiremath, Yashaswini Palani, YuXuan Jiang, Qiang Zhu, Siyue Teng, Fan Zhang, Shuyuan Zhu, Bing Zeng, David Bull, Jingwei Liao, Yuqing Yang, Wenda Shao, Junyi Zhao, Qisheng Xu, Kele Xu, Sunder Ali Khowaja, Ik Hyun Lee, Snehal Singh Tomar, Rajarshi Ray, Klaus Mueller, Sachin Chaudhary, Surya Vashisth, Akshay Dudhane, Praful Hambarde, Satya Naryan Tazi, Prashant Patil, Santosh Kumar Vipparthi, Subrahmanyam Murala, Bilel Benjdira, Anas M. Ali, Wadii Boulila, Zahra Moammeri, Ahmad Mahmoudi-Aznaveh, Ali Karbasi, Hossein Motamednia, Liangyan Li, Guanhua Zhao, Kevin Le, Yimo Ning, Haoxuan Huang, Jun Chen

This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025.

Image Super-Resolution valid

SkyReels-V2: Infinite-length Film Generative Model

1 code implementation17 Apr 2025 Guibin Chen, Dixuan Lin, Jiangping Yang, Chunze Lin, Junchen Zhu, Mingyuan Fan, Hao Zhang, Sheng Chen, Zheng Chen, Chengcheng Ma, Weiming Xiong, Wei Wang, Nuo Pang, Kang Kang, Zhiheng Xu, Yuzhe Jin, Yupeng Liang, Yubing Song, Peng Zhao, Boyuan Xu, Di Qiu, Debang Li, Zhengcong Fei, Yang Li, Yahui Zhou

Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions.

Large Language Model model +2

One-Step Diffusion Model for Image Motion-Deblurring

1 code implementation9 Mar 2025 Xiaoyang Liu, Yuquan Wang, Zheng Chen, JieZhang Cao, He Zhang, Yulun Zhang, Xiaokang Yang

In this paper, we conduct an in-depth exploration of diffusion models in deblurring and propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step, significantly improving inference efficiency while maintaining high fidelity.

Deblurring Denoising +3

Dual-branch Graph Feature Learning for NLOS Imaging

no code implementations27 Feb 2025 Xiongfei Su, Tianyi Zhu, Lina Liu, Zheng Chen, Yulun Zhang, Siyuan Li, Juntian Ye, Feihu Xu, Xin Yuan

The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible.

ExPath: Towards Explaining Targeted Pathways for Biological Knowledge Bases

no code implementations25 Feb 2025 Rikuto Kotoge, Ziwei Yang, Zheng Chen, Yushun Dong, Yasuko Matsubara, Jimeng Sun, Yasushi Sakurai

In this paper, we frame this challenge as a solvable graph learning and explaining task and propose a novel pathway inference framework, ExPath, that explicitly integrates experimental data, specifically amino acid sequences (AA-seqs), to classify various graphs (bio-networks) in biological databases.

Graph Learning Mamba +1

Single-Channel EEG Tokenization Through Time-Frequency Modeling

no code implementations22 Feb 2025 Jathurshan Pradeepkumar, Xihao Piao, Zheng Chen, Jimeng Sun

By learning tokens that encapsulate these intrinsic patterns within a single channel, our approach yields a scalable tokenizer adaptable across diverse EEG settings.

EEG

IPAD: Inverse Prompt for AI Detection -- A Robust and Explainable LLM-Generated Text Detector

1 code implementation21 Feb 2025 Zheng Chen, Yushi Feng, Changyang He, Yue Deng, Hongxi Pu, Bo Li

Furthermore, a user study is conducted to illustrate that IPAD enhances the AI detection trustworthiness by allowing users to directly examine the decision-making evidence, which provides interpretable support for its state-of-the-art detection results.

Text Generation

CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution

1 code implementation21 Feb 2025 Kai Liu, Dehui Wang, Zhiteng Li, Zheng Chen, Yong Guo, Wenbo Li, Linghe Kong, Yulun Zhang

Experimentally, we observe that the degradation of quantization is mainly attributed to the quantization of activation instead of model weights.

Image Super-Resolution Quantization

Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal

1 code implementation14 Feb 2025 Jinpei Guo, Zheng Chen, Wenbo Li, Yong Guo, Yulun Zhang

The core of CODiff is the compression-aware visual embedder (CaVE), which extracts and leverages JPEG compression priors to guide the diffusion model.

Denoising JPEG Artifact Removal

Towards Physiologically Sensible Predictions via the Rule-based Reinforcement Learning Layer

no code implementations31 Jan 2025 Lingwei Zhu, Zheng Chen, Yukie Nagai, Jimeng Sun

This paper adds to the growing literature of reinforcement learning (RL) for healthcare by proposing a novel paradigm: augmenting any predictor with Rule-based RL Layer (RRLL) that corrects the model's physiologically impossible predictions.

Reinforcement Learning (RL)

Whisper D-SGD: Correlated Noise Across Agents for Differentially Private Decentralized Learning

1 code implementation24 Jan 2025 Angelo Rodio, Zheng Chen, Erik G. Larsson

Decentralized learning enables distributed agents to train a shared machine learning model through local computation and peer-to-peer communication.

Contrast: A Hybrid Architecture of Transformers and State Space Models for Low-Level Vision

no code implementations23 Jan 2025 Aman Urumbekov, Zheng Chen

Transformers have become increasingly popular for image super-resolution (SR) tasks due to their strong global context modeling capabilities.

Image Super-Resolution Mamba +1

Learning-Based Stable Optimal Guidance for Spacecraft Close-Proximity Operations

no code implementations2 Jan 2025 Kun Wang, Roberto Armellin, Adam Evans, Harry Holt, Zheng Chen

This approach ensures that all loss terms related to the control Lyapunov function are either naturally satisfied or replaced by the derived control policy.

Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images

no code implementations CVPR 2025 Zheng Chen, Chenming Wu, Zhelun Shen, Chen Zhao, Weicai Ye, Haocheng Feng, Errui Ding, Song-Hai Zhang

Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs.

3DGS NeRF

Long-Term EEG Partitioning for Seizure Onset Detection

no code implementations20 Dec 2024 Zheng Chen, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun

Deep learning models have recently shown great success in classifying epileptic patients using EEG recordings.

Clustering EEG +1

PAFFA: Premeditated Actions For Fast Agents

no code implementations10 Dec 2024 Shambhavi Krishna, Zheng Chen, Vaibhav Kumar, Xiaojiang Huang, Yingjie Li, Fan Yang, Xiang Li

Modern AI assistants have made significant progress in natural language understanding and API/tool integration, with emerging efforts to incorporate diverse interfaces (such as Web interfaces) for enhanced scalability and functionality.

Natural Language Understanding

Splatter-360: Generalizable 360$^{\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images

1 code implementation9 Dec 2024 Zheng Chen, Chenming Wu, Zhelun Shen, Chen Zhao, Weicai Ye, Haocheng Feng, Errui Ding, Song-Hai Zhang

Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs.

3DGS NeRF

OSDFace: One-Step Diffusion Model for Face Restoration

1 code implementation CVPR 2025 Jingkai Wang, Jue Gong, Lin Zhang, Zheng Chen, Xing Liu, Hong Gu, Yutong Liu, Yulun Zhang, Xiaokang Yang

Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject's identity.

Face Recognition Generative Adversarial Network +1

Pseudo-Conversation Injection for LLM Goal Hijacking

no code implementations31 Oct 2024 Zheng Chen, Buhui Yao

In goal hijacking, an attacker typically appends a carefully crafted malicious suffix to the user's prompt, which coerces the model into ignoring the user's original input and generating the target response.

Adversarial Attack

DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion

1 code implementation31 Oct 2024 Weicai Ye, Chenhao Ji, Zheng Chen, Junyao Gao, Xiaoshui Huang, Song-Hai Zhang, Wanli Ouyang, Tong He, Cairong Zhao, Guofeng Zhang

Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation.

Scene Generation

MovieCharacter: A Tuning-Free Framework for Controllable Character Video Synthesis

no code implementations28 Oct 2024 Di Qiu, Zheng Chen, Rui Wang, Mingyuan Fan, Changqian Yu, Junshi Huang, Xiang Wen

Recent advancements in character video synthesis still depend on extensive fine-tuning or complex 3D modeling processes, which can restrict accessibility and hinder real-time applicability.

Can Large Language Models Replace Data Scientists in Biomedical Research?

no code implementations28 Oct 2024 Zifeng Wang, Benjamin Danek, Ziwei Yang, Zheng Chen, Jimeng Sun

To address this gap, we developed a benchmark of data science coding tasks derived from the analyses of 39 published studies.

GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation

no code implementations17 Oct 2024 Ziwei Yang, Zheng Chen, Xin Liu, Rikuto Kotoge, Peng Chen, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun

Retrieving gene functional networks from knowledge databases presents a challenge due to the mismatch between disease networks and subtype-specific variations.

Graph Generation Graph Neural Network +1

SplitSEE: A Splittable Self-supervised Framework for Single-Channel EEG Representation Learning

no code implementations15 Oct 2024 Rikuto Kotoge, Zheng Chen, Tasuku Kimura, Yasuko Matsubara, Takufumi Yanagisawa, Haruhiko Kishima, Yasushi Sakurai

In this paper, we present SplitSEE, a structurally splittable framework designed for effective temporal-frequency representation learning in single-channel EEG.

Deep Clustering EEG +2

C^2DA: Contrastive and Context-aware Domain Adaptive Semantic Segmentation

1 code implementation10 Oct 2024 Md. Al-Masrur Khan, Zheng Chen, Lantao Liu

To learn the intra-domain knowledge, we incorporate contrastive loss in both domains, which pulls pixels of similar classes together and pushes the rest away, facilitating intra-image-pixel-wise correlations.

Semantic Segmentation

Temporal Predictive Coding for Gradient Compression in Distributed Learning

no code implementations3 Oct 2024 Adrian Edin, Zheng Chen, Michel Kieffer, Mikael Johansson

We use a linear predictor that \textit{combines past gradients to form a prediction of the current gradient}, with coefficients that are optimized by solving a least-square problem.

Prediction

FredNormer: Frequency Domain Normalization for Non-stationary Time Series Forecasting

no code implementations2 Oct 2024 Xihao Piao, Zheng Chen, Yushun Dong, Yasuko Matsubara, Yasushi Sakurai

Since these methods operate in the time domain, they may fail to fully capture the dynamic patterns that are more apparent in the frequency domain, leading to suboptimal results.

Time Series Time Series Forecasting

MLOmics: Cancer Multi-Omics Database for Machine Learning

1 code implementation2 Sep 2024 Ziwei Yang, Rikuto Kotoge, Xihao Piao, Zheng Chen, Lingwei Zhu, Peng Gao, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun

Framing the investigation of diverse cancers as a machine learning problem has recently shown significant potential in multi-omics analysis and cancer research.

Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities

no code implementations25 Aug 2024 Zheyu Zhang, Xinzhao Liu, Zheng Chen, Yueyi Zhang, Huanjing Yue, Yunwei Ou, Xiaoyan Sun

Through validation on the BraTS2018 and BraTS2020 datasets, ACDIS substantiates its efficacy in the segmentation of brain tumors with missing MRI modalities.

Brain Tumor Segmentation Segmentation +2

Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation

no code implementations19 Aug 2024 Haijin Wang, Mianrong Zhang, Zheng Chen, Nan Shang, Shangheng Yao, Fushuan Wen, Junhua Zhao

Carbon footprint accounting is crucial for quantifying greenhouse gas emissions and achieving carbon neutrality. The dynamic nature of processes, accounting rules, carbon-related policies, and energy supply structures necessitates real-time updates of CFA.

Information Retrieval RAG +2

BernGraph: Probabilistic Graph Neural Networks for EHR-based Medication Recommendations

1 code implementation18 Aug 2024 Xihao Piao, Pei Gao, Zheng Chen, Lingwei Zhu, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun

In this paper, we attempt to build the first successful binary EHR data-oriented drug recommendation system by tackling the two difficulties, making sensible drug recommendations solely using the binary EHR medical records.

Graph Neural Network

Binarized Diffusion Model for Image Super-Resolution

1 code implementation9 Jun 2024 Zheng Chen, Haotong Qin, Yong Guo, Xiongfei Su, Xin Yuan, Linghe Kong, Yulun Zhang

Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation.

Attribute Binarization +3

Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach

no code implementations20 May 2024 Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson

Federated learning (FL) has received significant attention in recent years for its advantages in efficient training of machine learning models across distributed clients without disclosing user-sensitive data.

Federated Learning Scheduling

DmADs-Net: Dense multiscale attention and depth-supervised network for medical image segmentation

no code implementations1 May 2024 Zhaojin Fu, Zheng Chen, Jinjiang Li, Lu Ren

In addition, in the feature fusion phase, a Feature Refinement and Fusion Block is created to enhance the fusion of different semantic information. We validated the performance of the network using five datasets of varying sizes and types.

Image Segmentation Medical Image Segmentation +1

Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection

no code implementations22 Mar 2024 Hongzhi Gao, Zheng Chen, Zehui Chen, Lin Chen, Jiaming Liu, Shanghang Zhang, Feng Zhao

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming.

3D Object Detection object-detection +2

NARUTO: Neural Active Reconstruction from Uncertain Target Observations

1 code implementation CVPR 2024 Ziyue Feng, Huangying Zhan, Zheng Chen, Qingan Yan, Xiangyu Xu, Changjiang Cai, Bing Li, Qilun Zhu, Yi Xu

We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction.

Surface Reconstruction

Improving Building Temperature Forecasting: A Data-driven Approach with System Scenario Clustering

no code implementations21 Feb 2024 Dafang Zhao, Zheng Chen, Zhengmao Li, Xiaolei Yuan, Ittetsu Taniguchi

For smart energy management in buildings, usage patterns and their resulting profiles allow the improvement of control systems with prediction capabilities.

Clustering Computational Efficiency +3

Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks

no code implementations24 Jan 2024 Daniel Pérez Herrera, Zheng Chen, Erik G. Larsson

Consensus-based decentralized stochastic gradient descent (D-SGD) is a widely adopted algorithm for decentralized training of machine learning models across networked agents.

Scheduling

Training a General Spiking Neural Network with Improved Efficiency and Minimum Latency

1 code implementation5 Jan 2024 Yunpeng Yao, Man Wu, Zheng Chen, Renyuan Zhang

This paper proposes a general training framework that enhances feature learning and activation efficiency within a limited time step, providing a new solution for more energy-efficient SNNs.

Self-Supervised Position Debiasing for Large Language Models

no code implementations2 Jan 2024 Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Pengjie Ren, Zhumin Chen

Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality.

Position

PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields

no code implementations30 Dec 2023 Zheng Chen, Qingan Yan, Huangying Zhan, Changjiang Cai, Xiangyu Xu, Yuzhong Huang, Weihan Wang, Ziyue Feng, Lantao Liu, Yi Xu

Through extensive experiments, we demonstrate the effectiveness of PlanarNeRF in various scenarios and remarkable improvement over existing works.

3D Plane Detection

STADEE: STAtistics-based DEEp Detection of Machine Generated Text

1 code implementation4 Dec 2023 Zheng Chen, Huming Liu

We present STADEE, a \textbf{STA}tistics-based \textbf{DEE}p detection method to identify machine-generated text, addressing the limitations of current methods that rely heavily on fine-tuning pre-trained language models (PLMs).

Image Super-Resolution with Text Prompt Diffusion

1 code implementation24 Nov 2023 Zheng Chen, Yulun Zhang, Jinjin Gu, Xin Yuan, Linghe Kong, Guihai Chen, Xiaokang Yang

Specifically, we first design a text-image generation pipeline to integrate text into the SR dataset through the text degradation representation and degradation model.

Image Generation Image Super-Resolution +2

Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers

1 code implementation2 Nov 2023 Weiwei Sun, Zheng Chen, Xinyu Ma, Lingyong Yan, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren

Furthermore, our approach surpasses the performance of existing supervised methods like monoT5 and is on par with the state-of-the-art zero-shot methods.

Prompt Engineering

Decentralized Learning over Wireless Networks with Broadcast-Based Subgraph Sampling

no code implementations24 Oct 2023 Daniel Pérez Herrera, Zheng Chen, Erik G. Larsson

This work centers on the communication aspects of decentralized learning over wireless networks, using consensus-based decentralized stochastic gradient descent (D-SGD).

Scheduling

Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?

no code implementations5 Oct 2023 Adrian Edin, Zheng Chen

Over-the-Air (OtA) Federated Learning (FL) refers to an FL system where multiple agents apply OtA computation for transmitting model updates to a common edge server.

compressed sensing Federated Learning

RecMind: Large Language Model Powered Agent For Recommendation

no code implementations28 Aug 2023 Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Yingzhen Yang

While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale and data size constraints.

Explanation Generation Language Modeling +4

Dual Aggregation Transformer for Image Super-Resolution

1 code implementation ICCV 2023 Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang, Fisher Yu

Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner.

Image Super-Resolution

Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Prediction

no code implementations26 Jun 2023 Zheng Chen, Durgakant Pushp, Jason M. Gregory, Lantao Liu

We prove that our CALI model -- a pseudo-trilateral game structure is advantageous over existing bilateral game structures.

Autonomous Navigation Data Augmentation +2

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

no code implementations19 Jun 2023 Xinli Yu, Zheng Chen, Yuan Ling, Shujing Dong, Zongyi Liu, Yanbin Lu

The application of machine learning models to financial time series comes with several challenges, including the difficulty in cross-sequence reasoning and inference, the hurdle of incorporating multi-modal signals from historical news, financial knowledge graphs, etc., and the issue of interpreting and explaining the model results.

Knowledge Graphs Time Series +1

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

no code implementations NeurIPS 2023 Zheng Chen, Yan-Pei Cao, Yuan-Chen Guo, Chen Wang, Ying Shan, Song-Hai Zhang

Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection.

Depth Estimation

Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding

no code implementations23 May 2023 Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan

This paper presents our "Collaborative Query Rewriting" approach, which specifically addresses the task of rewriting new user interactions that have not been previously observed in the user's history.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +9

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

1 code implementation NeurIPS 2023 Zheng Chen, Yulun Zhang, Ding Liu, Bin Xia, Jinjin Gu, Linghe Kong, Xin Yuan

Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process.

Deblurring Image Deblurring +2

Decentralized Learning over Wireless Networks: The Effect of Broadcast with Random Access

no code implementations12 May 2023 Zheng Chen, Martin Dahl, Erik G. Larsson

In particular, we investigate the impact of broadcast transmission and probabilistic random access policy on the convergence performance of D-SGD, considering the broadcast nature of wireless channels and the link dynamics in the communication topology.

Dynamic Scheduling for Federated Edge Learning with Streaming Data

no code implementations2 May 2023 Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson

In this work, we consider a Federated Edge Learning (FEEL) system where training data are randomly generated over time at a set of distributed edge devices with long-term energy constraints.

Scheduling

Recursive Generalization Transformer for Image Super-Resolution

1 code implementation11 Mar 2023 Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang

In this work, we propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images.

Image Reconstruction Image Super-Resolution

IDA: Informed Domain Adaptive Semantic Segmentation

no code implementations5 Mar 2023 Zheng Chen, Zhengming Ding, Jason M. Gregory, Lantao Liu

To improve the UDA-SS performance, we propose an Informed Domain Adaptation (IDA) model, a self-training framework that mixes the data based on class-level segmentation performance, which aims to emphasize small-region semantics during mixup.

Data Augmentation Domain Adaptation +2

SePaint: Semantic Map Inpainting via Multinomial Diffusion

no code implementations5 Mar 2023 Zheng Chen, Deepak Duggirala, David Crandall, Lei Jiang, Lantao Liu

Prediction beyond partial observations is crucial for robots to navigate in unknown environments because it can provide extra information regarding the surroundings beyond the current sensing range or resolution.

Navigate

Drugs Resistance Analysis from Scarce Health Records via Multi-task Graph Representation

no code implementations22 Feb 2023 Honglin Shu, Pei Gao, Lingwei Zhu, Zheng Chen

In this paper, we propose a novel framework for rapid clinical intervention by viewing health records as graphs whose nodes are mapped from medical events and edges as correspondence between events in given a time window.

Multi-Task Learning

Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence

no code implementations27 Jan 2023 Lingwei Zhu, Zheng Chen, Matthew Schlegel, Martha White

Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly.

Atari Games reinforcement-learning +2

HSE: Hybrid Species Embedding for Deep Metric Learning

1 code implementation ICCV 2023 Bailin Yang, Haoqiang Sun, Frederick W. B. Li, Zheng Chen, Jianlu Cai, Chao Song

Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes.

Metric Learning

Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks

no code implementations14 Dec 2022 Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson

Federated Learning (FL) is a collaborative machine learning (ML) framework that combines on-device training and server-based aggregation to train a common ML model among distributed agents.

Federated Learning Scheduling

Cross Aggregation Transformer for Image Restoration

3 code implementations24 Nov 2022 Zheng Chen, Yulun Zhang, Jinjin Gu, Yongbing Zhang, Linghe Kong, Xin Yuan

The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the features cross different windows.

Image Restoration Inductive Bias

Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations

no code implementations5 Oct 2022 Jialing Liao, Zheng Chen, Erik G. Larsson

In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server at the same time.

Federated Learning

StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints

no code implementations12 Sep 2022 Zheng Chen, Chen Wang, Yuan-Chen Guo, Song-Hai Zhang

Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images.

Depth Estimation NeRF +1

Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder

no code implementations20 Jul 2022 Zheng Chen, Ziwei Yang, Lingwei Zhu, Guang Shi, Kun Yue, Takashi Matsubara, Shigehiko Kanaya, MD Altaf-Ul-Amin

As such, existing methods often impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations.

Clustering Prognosis

Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning

no code implementations16 May 2022 Lingwei Zhu, Zheng Chen, Eiji Uchibe, Takamitsu Matsubara

Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy.

reinforcement-learning Reinforcement Learning (RL)

$q$-Munchausen Reinforcement Learning

no code implementations16 May 2022 Lingwei Zhu, Zheng Chen, Eiji Uchibe, Takamitsu Matsubara

The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy.

reinforcement-learning Reinforcement Learning +1

Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling

no code implementations7 May 2022 Zheng Chen, Jian Zhao, Mingyu Yang, Wengang Zhou, Houqiang Li

In this work, we are dedicated to multi-target active object tracking (AOT), where there are multiple targets as well as multiple cameras in the environment.

Multi-agent Reinforcement Learning Object Tracking

Multi-Tier Platform for Cognizing Massive Electroencephalogram

no code implementations21 Apr 2022 Zheng Chen, Lingwei Zhu, Ziwei Yang, Renyuan Zhang

A spiking neural network (SNN) based tier is designed to distill the principle information in terms of spike-streams from the rare features, which maintains the temporal implication in the nature of EEGs.

EEG

Automated Sleep Staging via Parallel Frequency-Cut Attention

no code implementations7 Apr 2022 Zheng Chen, Ziwei Yang, Lingwei Zhu, Wei Chen, Toshiyo Tamura, Naoaki Ono, MD Altaf-Ul-Amin, Shigehiko Kanaya, Ming Huang

This paper proposes a novel framework for automatically capturing the time-frequency nature of electroencephalogram (EEG) signals of human sleep based on the authoritative sleep medicine guidance.

Decision Making EEG +2

Adaptive Spike-Like Representation of EEG Signals for Sleep Stages Scoring

no code implementations2 Apr 2022 Lingwei Zhu, Koki Odani, Ziwei Yang, Guang Shi, Yirong Kan, Zheng Chen, Renyuan Zhang

Recently there has seen promising results on automatic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG).

EEG Feature Engineering

Cancer Subtyping via Embedded Unsupervised Learning on Transcriptomics Data

no code implementations2 Apr 2022 Ziwei Yang, Lingwei Zhu, Zheng Chen, Ming Huang, Naoaki Ono, MD Altaf-Ul-Amin, Shigehiko Kanaya

In this paper, we propose to investigate automatic subtyping from an unsupervised learning perspective by directly constructing the underlying data distribution itself, hence sufficient data can be generated to alleviate the issue of overfitting.

Quantization

On-Demand AoI Minimization in Resource-Constrained Cache-Enabled IoT Networks with Energy Harvesting Sensors

no code implementations28 Jan 2022 Mohammad Hatami, Markus Leinonen, Zheng Chen, Nikolaos Pappas, Marian Codreanu

We consider a resource-constrained IoT network, where multiple users make on-demand requests to a cache-enabled edge node to send status updates about various random processes, each monitored by an energy harvesting sensor.

Device Scheduling and Update Aggregation Policies for Asynchronous Federated Learning

no code implementations23 Jul 2021 Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson

Federated Learning (FL) is a newly emerged decentralized machine learning (ML) framework that combines on-device local training with server-based model synchronization to train a centralized ML model over distributed nodes.

Federated Learning Scheduling

SPSA-Based Successive Beamforming for Mobile Satellite Receivers with Phased Arrays

no code implementations19 Apr 2021 Zheng Chen, Håkan Johansson

Efficient and low-complexity beamforming design is an important element of satellite communication systems with mobile receivers equipped with phased arrays.

Theoretical analysis on the transient ignition of premixed expanding flame in a quiescent mixture

no code implementations16 Feb 2021 Dehai Yu, Zheng Chen

It is found that as the heating power grows, the memory effect becomes increasingly important and it can greatly reduce the minimum ignition energy.

Fluid Dynamics

Self-Supervised Transfer Learning for Hand Mesh Recovery From Binocular Images

no code implementations ICCV 2021 Zheng Chen, Sihan Wang, Yi Sun, Xiaohong Ma

Traditional methods for RGB hand mesh recovery usually need to train a separate model for each dataset with the corresponding ground truth and are hardly adapted to new scenarios without the ground truth for supervision.

Transfer Learning

Consensus-Based Distributed Computation of Link-Based Network Metrics

no code implementations29 Dec 2020 Zheng Chen, Erik G. Larsson

Average consensus algorithms have wide applications in distributed computing systems where all the nodes agree on the average value of their initial states by only exchanging information with their local neighbors.

Distributed Computing Distributed, Parallel, and Cluster Computing Social and Information Networks Signal Processing

Time-Optimal Guidance to Intercept Moving Targets by Dubins Vehicles

no code implementations22 Dec 2020 Yuan Zheng, Xueming Shao, Zheng Chen, Wenjie Zhao

When the target's velocity is constant, by employing the geometric properties, those 4 candidates are transformed to a class of sufficiently smooth real-valued functions.

Optimization and Control

ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation

no code implementations COLING 2020 Zheng Chen, Kangjian Wu

First, ForceReader proposes a novel solution called the Attention Separation Representation to respond to attention deconcentration.

Machine Reading Comprehension

Neural Stochastic Block Model & Scalable Community-Based Graph Learning

no code implementations16 May 2020 Zheng Chen, Xinli Yu, Yuan Ling, Xiaohua Hu

Compared with SBM, our framework is flexible, naturally allows soft labels and digestion of complex node attributes.

Community Detection Graph Attention +3

Pre-Training for Query Rewriting in A Spoken Language Understanding System

no code implementations13 Feb 2020 Zheng Chen, Xing Fan, Yuan Ling, Lambert Mathias, Chenlei Guo

Then, inspired by the wide success of pre-trained contextual language embeddings, and also as a way to compensate for insufficient QR training data, we propose a language-modeling (LM) based approach to pre-train query embeddings on historical user conversation data with a voice assistant.

Entity Resolution Friction +6

An Ontology-driven Treatment Article Retrieval System for Precision Oncology

no code implementations13 Feb 2020 Zheng Chen, Sadid A. Hasan, Joey Liu, Vivek Datla, Md Shamsuzzaman, Hafiz Khan, Mohammad S. Sorower, Gabe Mankovich, Rob van Ommering, Nevenka Dimitrova

This paper presents an ontology-driven treatment article retrieval system developed and experimented using the data and ground truths provided by the TREC 2017 precision medicine track.

Retrieval

Optimizing Information Freshness in a Multiple Access Channel with Heterogeneous Devices

no code implementations10 Oct 2019 Zheng Chen, Nikolaos Pappas, Emil Björnson, Erik G. Larsson

We formulate an optimization problem that aims at minimizing the average age of information (AoI) of the EH node subject to the queue stability condition of the grid-connected node.

Information Theory Networking and Internet Architecture Information Theory

Creating Navigable Space from Sparse Noisy Map Points

1 code implementation4 Mar 2019 Zheng Chen, Lantao Liu

We present a framework for creating navigable space from sparse and noisy map points generated by sparse visual SLAM methods.

Robotics

Large-Scale Joint Topic, Sentiment & User Preference Analysis for Online Reviews

no code implementations14 Jan 2019 Xinli Yu, Zheng Chen, Wei-Shih Yang, Xiaohua Hu, Erjia Yan

This paper presents a non-trivial reconstruction of a previous joint topic-sentiment-preference review model TSPRA with stick-breaking representation under the framework of variational inference (VI) and stochastic variational inference (SVI).

Variational Inference

Correlated Anomaly Detection from Large Streaming Data

no code implementations19 Dec 2018 Zheng Chen, Xinli Yu, Yuan Ling, Bo Song, Wei Quan, Xiaohua Hu, Erjia Yan

Correlated anomaly detection (CAD) from streaming data is a type of group anomaly detection and an essential task in useful real-time data mining applications like botnet detection, financial event detection, industrial process monitor, etc.

Event Detection Group Anomaly Detection

Fast Botnet Detection From Streaming Logs Using Online Lanczos Method

no code implementations19 Dec 2018 Zheng Chen, Xinli Yu, Chi Zhang, Jin Zhang, Cui Lin, Bo Song, Jianliang Gao, Xiaohua Hu, Wei-Shih Yang, Erjia Yan

Botnet, a group of coordinated bots, is becoming the main platform of malicious Internet activities like DDOS, click fraud, web scraping, spam/rumor distribution, etc.

Unifying Topic, Sentiment & Preference in an HDP-Based Rating Regression Model for Online Reviews

1 code implementation19 Dec 2018 Zheng Chen, Yong Zhang, Yue Shang, Xiaohua Hu

TSPRA combines topics (i. e. product aspects), word sentiment and user preference as regression factors, and is able to perform topic clustering, review rating prediction, sentiment analysis and what we invent as "critical aspect" analysis altogether in one framework.

Clustering Collaborative Filtering +3

Detecting and Explaining Causes From Text For a Time Series Event

1 code implementation EMNLP 2017 Dongyeop Kang, Varun Gangal, Ang Lu, Zheng Chen, Eduard Hovy

Our quantitative and human analysis show empirical evidence that our method successfully extracts meaningful causality relationships between time series with textual features and generates appropriate explanation between them.

Time Series Time Series Analysis

Knowledge Graph Embedding by Translating on Hyperplanes

1 code implementation AAAI 2014 2014 Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen

Utilizing the one-to-many/many-to-one mapping property of a relation, we propose a simple trick to reduce the possibility of false negative labeling.

Knowledge Graph Embedding Link Prediction +1

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