Search Results for author: Jia Li

Found 291 papers, 135 papers with code

CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics

1 code implementation6 May 2025 Junqi Liu, Xiaohan Lin, Jonas Bayer, Yael Dillies, Weijie Jiang, Xiaodan Liang, Roman Soletskyi, Haiming Wang, Yunzhou Xie, Beibei Xiong, Zhengfeng Yang, Jujian Zhang, Lihong Zhi, Jia Li, Zhengying Liu

CombiBench is suitable for testing IMO solving capabilities since it includes all IMO combinatorial problems since 2000 (except IMO 2004 P3 as its statement contain an images).

Benchmarking

VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

1 code implementation5 May 2025 Hao Cheng, Zhiwei Zhao, Yichao He, Zhenzhen Hu, Jia Li, Meng Wang, Richang Hong

Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages.

Contrastive Learning Dynamic Facial Expression Recognition +3

PhysioSync: Temporal and Cross-Modal Contrastive Learning Inspired by Physiological Synchronization for EEG-Based Emotion Recognition

1 code implementation24 Apr 2025 Kai Cui, Jia Li, Yu Liu, Xuesong Zhang, Zhenzhen Hu, Meng Wang

Besides, it introduces Long- and Short-Term Temporal Contrastive Learning (LS-TCL) to capture emotional synchronization at different temporal resolutions within modalities.

Contrastive Learning EEG +1

A Pre-Training and Adaptive Fine-Tuning Framework for Graph Anomaly Detection

no code implementations19 Apr 2025 Yunhui Liu, Jiashun Cheng, Jia Li, Fugee Tsung, Hongzhi Yin, Tieke He

Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet it remains challenging due to the scarcity of abnormal nodes and the high cost of label annotations.

Graph Anomaly Detection

The Tenth NTIRE 2025 Image Denoising Challenge Report

1 code implementation16 Apr 2025 Lei Sun, Hang Guo, Bin Ren, Luc van Gool, Radu Timofte, Yawei Li, Xiangyu Kong, Hyunhee Park, Xiaoxuan Yu, Suejin Han, Hakjae Jeon, Jia Li, Hyung-Ju Chun, Donghun Ryou, Inju Ha, Bohyung Han, JingYu Ma, Zhijuan Huang, Huiyuan Fu, Hongyuan Yu, Boqi Zhang, Jiawei Shi, Heng Zhang, Huadong Ma, Deepak Kumar Tyagi, Aman Kukretti, Gajender Sharma, Sriharsha Koundinya, Asim Manna, Jun Cheng, Shan Tan, Jun Liu, Jiangwei Hao, Jianping Luo, Jie Lu, Satya Narayan Tazi, Arnim Gautam, Aditi Pawar, Aishwarya Joshi, Akshay Dudhane, Praful Hambadre, Sachin Chaudhary, Santosh Kumar Vipparthi, Subrahmanyam Murala, Jiachen Tu, Nikhil Akalwadi, Vijayalaxmi Ashok Aralikatti, Dheeraj Damodar Hegde, G Gyaneshwar Rao, Jatin Kalal, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudenagudi, Zhenyuan Lin, Yubo Dong, Weikun Li, Anqi Li, Ang Gao, Weijun Yuan, Zhan Li, Ruting Deng, Yihang Chen, Yifan Deng, Zhanglu Chen, Boyang Yao, Shuling Zheng, Feng Zhang, Zhiheng Fu, Anas M. Ali, Bilel Benjdira, Wadii Boulila, Jan Seny, Pei Zhou, Jianhua Hu, K. L. Eddie Law, Jaeho Lee, M. J. Aashik Rasool, Abdur Rehman, SMA Sharif, Seongwan Kim, Alexandru Brateanu, Raul Balmez, Ciprian Orhei, Cosmin Ancuti, Zeyu Xiao, Zhuoyuan Li, Ziqi Wang, Yanyan Wei, Fei Wang, Kun Li, Shengeng Tang, Yunkai Zhang, Weirun Zhou, Haoxuan Lu

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge ({\sigma} = 50), highlighting the proposed methodologies and corresponding results.

Image Denoising valid

PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation

1 code implementation2 Apr 2025 Zhengwei Tao, Zhi Jin, Bincheng Li, Xiaoying Bai, Haiyan Zhao, Chengfeng Dou, Xiancai Chen, Jia Li, Linyu Li, Chongyang Tao

In constructing this benchmark, we first collected recent trend forecasting questions and then filtered the data using CIL, resulting in an inferable benchmark for event prediction.

Causal Inference Prediction +2

SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain

no code implementations26 Mar 2025 Nan Gao, Yihua Bao, Dongdong Weng, Jiayi Zhao, Jia Li, Yan Zhou, Pengfei Wan, Di Zhang

Co-speech gesture generation enhances human-computer interaction realism through speech-synchronized gesture synthesis.

Gesture Generation

Sparseformer: a Transferable Transformer with Multi-granularity Token Sparsification for Medical Time Series Classification

no code implementations19 Mar 2025 Jiexia Ye, Weiqi Zhang, Ziyue Li, Jia Li, Fugee Tsung

Medical time series (MedTS) classification is crucial for improved diagnosis in healthcare, and yet it is challenging due to the varying granularity of patterns, intricate inter-channel correlation, information redundancy, and label scarcity.

Diagnostic Few-Shot Learning +4

Indoor Fusion Positioning Based on "IMU-Ultrasonic-UWB" and Factor Graph Optimization Method

no code implementations17 Mar 2025 Fengyun Zhang, Jia Li, Xiaoqing Zhang, Shukai Duan, Shuang-Hua Yang

This paper presents a high-precision positioning system that integrates ultra-wideband (UWB) time difference of arrival (TDoA) measurements, inertial measurement unit (IMU) data, and ultrasonic sensors through factor graph optimization.

Sensor Fusion

A Survey of Cross-domain Graph Learning: Progress and Future Directions

1 code implementation14 Mar 2025 Haihong Zhao, Chenyi Zi, Aochuan Chen, Jia Li

Graph learning plays a vital role in mining and analyzing complex relationships involved in graph data, which is widely used in many real-world applications like transaction networks and communication networks.

Graph Learning Survey

Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting

no code implementations3 Mar 2025 Xiaobin Hong, Jiawen Zhang, Wenzhong Li, Sanglu Lu, Jia Li

The rise of foundation models has revolutionized natural language processing and computer vision, yet their best practices to time series forecasting remains underexplored.

Domain Generalization Mixture-of-Experts +2

InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

1 code implementation3 Mar 2025 Yifan Niu, Ziqi Gao, Tingyang Xu, Yang Liu, Yatao Bian, Yu Rong, Junzhou Huang, Jia Li

In order to decode the complex knowledge of multiple properties in the inversion path, we propose a gradient-based Pareto search method to balance conflicting properties and generate Pareto optimal molecules.

Drug Discovery Graph Neural Network +1

Molecule Generation for Target Protein Binding with Hierarchical Consistency Diffusion Model

1 code implementation2 Mar 2025 Guanlue Li, Chenran Jiang, Ziqi Gao, Yu Liu, Chenyang Liu, Jiean Chen, Yong Huang, Jia Li

Effective generation of molecular structures, or new chemical entities, that bind to target proteins is crucial for lead identification and optimization in drug discovery.

Drug Design Drug Discovery +1

CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer

1 code implementation27 Feb 2025 Yang Liu, Zinan Zheng, Jiashun Cheng, Fugee Tsung, Deli Zhao, Yu Rong, Jia Li

Accurate Subseasonal-to-Seasonal (S2S) climate forecasting is pivotal for decision-making including agriculture planning and disaster preparedness but is known to be challenging due to its chaotic nature.

Decision Making

BatteryLife: A Comprehensive Dataset and Benchmark for Battery Life Prediction

1 code implementation26 Feb 2025 Ruifeng Tan, Weixiang Hong, Jiayue Tang, Xibin Lu, Ruijun Ma, Xiang Zheng, Jia Li, Jiaqiang Huang, Tong-Yi Zhang

Notably, BatteryLife is the first to release battery life datasets of zinc-ion batteries, sodium-ion batteries, and industry-tested large-capacity lithium-ion batteries.

Benchmarking Time Series

CodeSwift: Accelerating LLM Inference for Efficient Code Generation

no code implementations24 Feb 2025 Qianhui Zhao, Li Zhang, Fang Liu, Xiaoli Lian, Qiaoyuanhe Meng, Ziqian Jiao, Zetong Zhou, Borui Zhang, Runlin Guo, Jia Li

Experimental results show that CodeSwift can reach up to 2. 53x and 2. 54x speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%.

Code Generation Retrieval

G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation

1 code implementation18 Feb 2025 Yuhan Li, Xinni Zhang, Linhao Luo, Heng Chang, Yuxiang Ren, Irwin King, Jia Li

Moreover, existing methods often struggle with the integration of extracted CF information with LLMs due to its implicit representation and the modality gap between graph structures and natural language explanations.

Collaborative Filtering Explainable Recommendation +4

S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning

1 code implementation18 Feb 2025 Ruotian Ma, Peisong Wang, Cheng Liu, Xingyan Liu, Jiaqi Chen, Bang Zhang, Xin Zhou, Nan Du, Jia Li

In this work, we introduce S$^2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.

Math

Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?

no code implementations1 Feb 2025 Jia Li, Wenjie Zhao, Ziru Huang, Yunhui Guo, Yapeng Tian

Our study reveals a fundamental bias in current methods: they tend to generate segmentation masks based predominantly on visual salience, irrespective of the audio context.

Segmentation

Constructing Cell-type Taxonomy by Optimal Transport with Relaxed Marginal Constraints

no code implementations29 Jan 2025 Sebastian Pena, Lin Lin, Jia Li

Many existing algorithms cannot recognize new cell types present in only one of the two samples when establishing a correspondence between clusters obtained from two samples.

InfoBFR: Real-World Blind Face Restoration via Information Bottleneck

no code implementations26 Jan 2025 Nan Gao, Jia Li, Huaibo Huang, Ke Shang, Ran He

Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns.

Attribute Blind Face Restoration

Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning

no code implementations10 Jan 2025 Yifan Zhao, Jia Li, Zeyin Song, Yonghong Tian

Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems.

class-incremental learning Contrastive Learning +5

Mixed geometry information regularization for image multiplicative denoising

no code implementations21 Dec 2024 Shengkun Yang, Zhichang Guo, Jia Li, Fanghui Song, Wenjuan Yao

We employ the second order SAV algorithm to further speed up the calculation while maintaining accuracy.

Denoising

Why language models collapse when trained on recursively generated text

no code implementations19 Dec 2024 Lecheng Wang, Xianjie Shi, Ge Li, Jia Li, Yihong Dong, Xuanming Zhang, Wenpin Jiao, Hong Mei

We present a new finding: the performance of LMs gradually declines when trained on recursively generated text until they perform no better than a randomly initialized LM.

Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation

1 code implementation9 Dec 2024 Xuesong Zhang, Yunbo Xu, Jia Li, Zhenzhen Hu, Richnag Hong

SUSA includes a Textual Semantic Understanding (TSU) module, which narrows the modality gap between instructions and environments by generating and associating the descriptions of environmental landmarks in agent's immediate surroundings.

Object Localization Vision and Language Navigation +2

How to Use Diffusion Priors under Sparse Views?

1 code implementation3 Dec 2024 Qisen Wang, Yifan Zhao, Jiawei Ma, Jia Li

However, the diffusion model, as an external prior that can directly provide visual supervision, has always underperformed in sparse-view 3D reconstruction using Score Distillation Sampling (SDS) due to the low information entropy of sparse views compared to text, leading to optimization challenges caused by mode deviation.

3D Reconstruction Novel View Synthesis

A Tunable Despeckling Neural Network Stabilized via Diffusion Equation

no code implementations24 Nov 2024 Yi Ran, Zhichang Guo, Jia Li, Yao Li, Martin Burger, Boying Wu

Adversarial attacks can be used as a criterion for judging the adaptability of neural networks to real data, since adversarial attacks can find the most extreme perturbations that make neural networks ineffective.

Denoising

Heterophilic Graph Neural Networks Optimization with Causal Message-passing

no code implementations21 Nov 2024 Botao Wang, Jia Li, Heng Chang, Keli Zhang, Fugee Tsung

We then present an analysis of decomposing the optimization target into a consistency penalty and a structure modification based on cause-effect relations.

Causal Inference Graph Learning +3

UniGAD: Unifying Multi-level Graph Anomaly Detection

1 code implementation10 Nov 2024 Yiqing Lin, Jianheng Tang, Chenyi Zi, H. Vicky Zhao, Yuan YAO, Jia Li

Existing methods generally focus on a single graph object type (node, edge, graph, etc.)

Graph Anomaly Detection

Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models

1 code implementation9 Nov 2024 XiaoJun Wu, Junxi Liu, Huanyi Su, Zhouchi Lin, Yiyan Qi, Chengjin Xu, Jiajun Su, Jiajie Zhong, Fuwei Wang, Saizhuo Wang, Fengrui Hua, Jia Li, Jian Guo

As large language models become increasingly prevalent in the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance.

ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer

1 code implementation4 Nov 2024 Jiawen Zhang, Shun Zheng, Xumeng Wen, Xiaofang Zhou, Jiang Bian, Jia Li

Numerous industrial sectors necessitate models capable of providing robust forecasts across various horizons.

Position Time Series +1

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations

no code implementations30 Oct 2024 Jia Li, Ge Li, Xuanming Zhang, YunFei Zhao, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li

These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs.

Code Generation Fairness

Graph Pre-Training Models Are Strong Anomaly Detectors

no code implementations24 Oct 2024 Jiashun Cheng, Zinan Zheng, Yang Liu, Jianheng Tang, Hongwei Wang, Yu Rong, Jia Li, Fugee Tsung

Graph Anomaly Detection (GAD) is a challenging and practical research topic where Graph Neural Networks (GNNs) have recently shown promising results.

Graph Anomaly Detection

GCoder: Improving Large Language Model for Generalized Graph Problem Solving

1 code implementation24 Oct 2024 Qifan Zhang, Xiaobin Hong, Jianheng Tang, Nuo Chen, Yuhan Li, Wenzhong Li, Jing Tang, Jia Li

Furthermore, GCoder efficiently manages large-scale graphs with millions of nodes and diverse input formats, overcoming the limitations of previous models focused on the reasoning steps paradigm.

Language Modeling Language Modelling +1

Addressing Heterogeneity and Heterophily in Graphs: A Heterogeneous Heterophilic Spectral Graph Neural Network

no code implementations17 Oct 2024 Kangkang Lu, Yanhua Yu, Zhiyong Huang, Jia Li, Yuling Wang, Meiyu Liang, Xiting Qin, Yimeng Ren, Tat-Seng Chua, Xidian Wang

Specifically, we propose a Heterogeneous Heterophilic Spectral Graph Neural Network (H2SGNN), which employs a dual-module approach: local independent filtering and global hybrid filtering.

Graph Neural Network

Zeroth-Order Fine-Tuning of LLMs in Random Subspaces

1 code implementation11 Oct 2024 Ziming Yu, Pan Zhou, Sike Wang, Jia Li, Hua Huang

Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks.

Language Modeling Language Modelling

DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation

1 code implementation11 Oct 2024 Jia Li, Yangchen Yu, Yin Chen, Yu Zhang, Peng Jia, Yunbo Xu, Ziqiang Li, Meng Wang, Richang Hong

Engagement estimation plays a crucial role in understanding human social behaviors, attracting increasing research interests in fields such as affective computing and human-computer interaction.

Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval

1 code implementation9 Oct 2024 Jian Xiao, Zhenzhen Hu, Jia Li, Richang Hong

By replacing a single text query with a series of text proxies, TV-ProxyNet not only broadens the query scope but also achieves a more precise expansion.

Text Retrieval Video-Text Retrieval

Showing LLM-Generated Code Selectively Based on Confidence of LLMs

no code implementations4 Oct 2024 Jia Li, Yuqi Zhu, Yongmin Li, Ge Li, Zhi Jin

HonestCoder selectively shows the generated programs to developers based on LLMs' confidence.

Code Generation

FAN: Fourier Analysis Networks

2 code implementations3 Oct 2024 Yihong Dong, Ge Li, Yongding Tao, Xue Jiang, Kechi Zhang, Jia Li, Jinliang Deng, Jing Su, Jun Zhang, Jingjing Xu

Despite the remarkable successes of general-purpose neural networks, such as MLPs and Transformers, we find that they exhibit notable shortcomings in modeling and reasoning about periodic phenomena, achieving only marginal performance within the training domain and failing to generalize effectively to out-of-domain (OOD) scenarios.

Language Modeling Language Modelling +1

Energy Saving and Traffic Steering Use Case and Testing by O-RAN RIC xApp/rApp Multi-vendor Interoperability

no code implementations29 Sep 2024 Arda Akman, Peyman Tehrani, Pablo Oliver, Marcin Hoffmann, Michael Jones, Jia Li

This paper discusses the use case of energy saving and traffic steering in O-RAN, the mechanism of multi-vendor interoperability to make it work and depict its test methodology.

ControlMath: Controllable Data Generation Promotes Math Generalist Models

no code implementations20 Sep 2024 Nuo Chen, Ning Wu, Jianhui Chang, Jia Li

The module creates diverse equations, which the Problem-Crafter agent then transforms into math word problems.

Data Augmentation Diversity +3

Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation

no code implementations19 Sep 2024 Chenyu Li, Shiming Ge, Daichi Zhang, Jia Li

Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation, leading to a sharp drop in accuracy.

Face Recognition Facial Inpainting +1

Efficient Low-Resolution Face Recognition via Bridge Distillation

no code implementations18 Sep 2024 Shiming Ge, Shengwei Zhao, Chenyu Li, Yu Zhang, Jia Li

Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability.

Dataset Distillation Face Model +2

Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

1 code implementation10 Sep 2024 Yin Chen, Jia Li, Yu Zhang, Zhenzhen Hu, Shiguang Shan, Meng Wang, Richang Hong

Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot.

Dynamic Facial Expression Recognition Facial Expression Recognition +1

Seeing is Believing? Enhancing Vision-Language Navigation using Visual Perturbations

no code implementations9 Sep 2024 Xuesong Zhang, Jia Li, Yunbo Xu, Zhenzhen Hu, Richang Hong

Autonomous navigation for an embodied agent guided by natural language instructions remains a formidable challenge in vision-and-language navigation (VLN).

Autonomous Navigation Diversity +2

Tackling Noisy Clients in Federated Learning with End-to-end Label Correction

1 code implementation8 Aug 2024 Xuefeng Jiang, Sheng Sun, Jia Li, Jingjing Xue, Runhan Li, Zhiyuan Wu, Gang Xu, Yuwei Wang, Min Liu

Intuitively, the performance degradation is dominated by clients with higher noise rates since their trained models contain more misinformation from data, thus it is necessary to devise an effective optimization scheme to mitigate the negative impacts of these noisy clients.

Federated Learning Misinformation

E$^3$NeRF: Efficient Event-Enhanced Neural Radiance Fields from Blurry Images

no code implementations3 Aug 2024 Yunshan Qi, Jia Li, Yifan Zhao, Yu Zhang, Lin Zhu

To effectively introduce event streams into the neural volumetric representation learning process, we propose an event-enhanced blur rendering loss and an event rendering loss, which guide the network via modeling the real blur process and event generation process, respectively.

Camera Pose Estimation NeRF +2

PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network

no code implementations2 Aug 2024 Changqun Xia, Chenxi Xie, Zhentao He, Tianshu Yu, Jia Li

To compensate for the lack of HRSOD dataset, we thoughtfully collect a large-scale high resolution salient object detection dataset, called UHRSD, containing 5, 920 images from real-world complex scenarios at 4K-8K resolutions.

4k 8k +4

Evidence and quantification of cooperation of driving agents in mixed traffic flow

no code implementations31 Jul 2024 Di Chen, Jia Li, H. Michael Zhang

This study provides the first empirical understanding of collective cooperativeness in human-driven mixed traffic and points to new possibilities to manage mixed autonomy traffic systems.

Parameter-Efficient Fine-Tuning via Circular Convolution

no code implementations27 Jul 2024 Aochuan Chen, Jiashun Cheng, Zijing Liu, Ziqi Gao, Fugee Tsung, Yu Li, Jia Li

Low-Rank Adaptation (LoRA) has gained popularity for fine-tuning large foundation models, leveraging low-rank matrices $\mathbf{A}$ and $\mathbf{B}$ to represent weight changes (i. e., $\Delta \mathbf{W} = \mathbf{B} \mathbf{A}$).

parameter-efficient fine-tuning

The Oscars of AI Theater: A Survey on Role-Playing with Language Models

1 code implementation16 Jul 2024 Nuo Chen, Yan Wang, Yang Deng, Jia Li

This survey explores the burgeoning field of role-playing with language models, focusing on their development from early persona-based models to advanced character-driven simulations facilitated by Large Language Models (LLMs).

Survey

GLBench: A Comprehensive Benchmark for Graph with Large Language Models

1 code implementation10 Jul 2024 Yuhan Li, Peisong Wang, Xiao Zhu, Aochuan Chen, Haiyun Jiang, Deng Cai, Victor Wai Kin Chan, Jia Li

To bridge this gap, we introduce GLBench, the first comprehensive benchmark for evaluating GraphLLM methods in both supervised and zero-shot scenarios.

GraphArena: Benchmarking Large Language Models on Graph Computational Problems

1 code implementation29 Jun 2024 Jianheng Tang, Qifan Zhang, Yuhan Li, Jia Li

The "arms race" of Large Language Models (LLMs) demands novel, challenging, and diverse benchmarks to faithfully examine their progresses.

Benchmarking Hallucination +1

Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Physical Dynamics Learning

1 code implementation24 Jun 2024 Zinan Zheng, Yang Liu, Jia Li, Jianhua Yao, Yu Rong

Moreover, we show that DEGNN is data efficient, learning with less data, and can generalize across scenarios such as unobserved orientation.

Graph Neural Network

Deblurring Neural Radiance Fields with Event-driven Bundle Adjustment

no code implementations20 Jun 2024 Yunshan Qi, Lin Zhu, Yifan Zhao, Nan Bao, Jia Li

Neural Radiance Fields (NeRF) achieves impressive 3D representation learning and novel view synthesis results with high-quality multi-view images as input.

Deblurring NeRF +2

SynthTree: Co-supervised Local Model Synthesis for Explainable Prediction

no code implementations16 Jun 2024 Evgenii Kuriabov, Jia Li

Explainable machine learning (XML) has emerged as a major challenge in artificial intelligence (AI).

Clustering Prediction

ProG: A Graph Prompt Learning Benchmark

1 code implementation8 Jun 2024 Chenyi Zi, Haihong Zhao, Xiangguo Sun, Yiqing Lin, Hong Cheng, Jia Li

Artificial general intelligence on graphs has shown significant advancements across various applications, yet the traditional 'Pre-train & Fine-tune' paradigm faces inefficiencies and negative transfer issues, particularly in complex and few-shot settings.

Prompt Learning

MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning

no code implementations7 Jun 2024 Jiexia Ye, Weiqi Zhang, Ziyue Li, Jia Li, Meng Zhao, Fugee Tsung

The recent rapid advancements in language models (LMs) have garnered attention in medical time series-text multimodal learning.

Contrastive Learning Language Modeling +2

Text Guided Image Editing with Automatic Concept Locating and Forgetting

no code implementations30 May 2024 Jia Li, Lijie Hu, Zhixian He, Jingfeng Zhang, Tianhang Zheng, Di Wang

With the advancement of image-to-image diffusion models guided by text, significant progress has been made in image editing.

text-guided-image-editing

4-bit Shampoo for Memory-Efficient Network Training

1 code implementation28 May 2024 Sike Wang, Pan Zhou, Jia Li, Hua Huang

In this paper, we propose the first 4-bit second-order optimizers, exemplified by 4-bit Shampoo, maintaining performance similar to that of 32-bit ones.

Image Classification Language Modeling +2

Canonical Variates in Wasserstein Metric Space

no code implementations24 May 2024 Jia Li, Lin Lin

Central to our investigation is dimension reduction within the Wasserstein metric space to enhance classification accuracy.

Dimensionality Reduction

A Survey of Time Series Foundation Models: Generalizing Time Series Representation with Large Language Model

1 code implementation3 May 2024 Jiexia Ye, Weiqi Zhang, Ke Yi, Yongzi Yu, Ziyue Li, Jia Li, Fugee Tsung

There are two main research lines, namely pre-training foundation models from scratch for time series and adapting large language foundation models for time series.

Decision Making Few-Shot Learning +5

A Comprehensive Evaluation on Event Reasoning of Large Language Models

1 code implementation26 Apr 2024 Zhengwei Tao, Zhi Jin, Yifan Zhang, Xiancai Chen, Xiaoying Bai, Yue Fang, Haiyan Zhao, Jia Li, Chongyang Tao

It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms.

Diversity

Exploring and Unleashing the Power of Large Language Models in Automated Code Translation

1 code implementation23 Apr 2024 Zhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung, Jia Li, Shuo Liu, Yifan Hong, Xiaoxue Ma, Zhi Jin, Ge Li

This paper investigates diverse LLMs and learning-based transpilers for automated code translation tasks, finding that: although certain LLMs have outperformed current transpilers, they still have some accuracy issues, where most of the failures are induced by a lack of comprehension of source programs, missing clear instructions on I/O types in translation, and ignoring discrepancies between source and target programs.

Code Translation Translation

EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories

1 code implementation31 Mar 2024 Jia Li, Ge Li, Xuanming Zhang, Yihong Dong, Zhi Jin

Existing benchmarks demonstrate poor alignment with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs.

Code Generation

DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration

no code implementations15 Mar 2024 Nan Gao, Jia Li, Huaibo Huang, Zhi Zeng, Ke Shang, Shuwu Zhang, Ran He

Experimental results demonstrate the superiority of DiffMAC over state-of-the-art methods, with a high degree of generalization in real-world and heterogeneous settings.

Attribute Blind Face Restoration +1

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

1 code implementation14 Mar 2024 Mingyuan Sun, Donghao Zhang, ZongYuan Ge, Jiaxu Wang, Jia Li, Zheng Fang, Renjing Xu

Based on this, we propose EventRPG, which leverages relevance propagation on the spiking neural network for more efficient augmentation.

Action Recognition Data Augmentation +1

All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)

no code implementations11 Mar 2024 Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan

This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award (Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, and Jihong Guan.

All Meta-Learning +1

Deep Reinforcement Learning for Modelling Protein Complexes

no code implementations11 Mar 2024 Ziqi Gao, Tao Feng, Jiaxuan You, Chenyi Zi, Yan Zhou, Chen Zhang, Jia Li

In this work, by taking each chain as a node and assembly actions as edges, we show that an acyclic undirected connected graph can be used to predict the structure of multi-chain protein complexes (a. k. a., protein complex modelling, PCM).

Combinatorial Optimization Deep Reinforcement Learning +2

GraphWiz: An Instruction-Following Language Model for Graph Problems

1 code implementation25 Feb 2024 Nuo Chen, Yuhan Li, Jianheng Tang, Jia Li

Large language models (LLMs) have achieved impressive success across several fields, but their proficiency in understanding and resolving complex graph problems is less explored.

Instruction Following Language Modeling +1

ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs

1 code implementation17 Feb 2024 Yuhan Li, Peisong Wang, ZHIXUN LI, Jeffrey Xu Yu, Jia Li

The results underscore the effectiveness of our model in achieving significant cross-dataset zero-shot transferability, opening pathways for the development of graph foundation models.

Graph Learning Language Modeling +3

All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining

3 code implementations15 Feb 2024 Haihong Zhao, Aochuan Chen, Xiangguo Sun, Hong Cheng, Jia Li

In response to this challenge, we propose a novel approach called Graph COordinators for PrEtraining (GCOPE), that harnesses the underlying commonalities across diverse graph datasets to enhance few-shot learning.

All Few-Shot Learning

Weakly Supervised Anomaly Detection via Knowledge-Data Alignment

no code implementations6 Feb 2024 Haihong Zhao, Chenyi Zi, Yang Liu, Chen Zhang, Yan Zhou, Jia Li

In this paper, we introduce a novel framework Knowledge-Data Alignment (KDAlign) to integrate rule knowledge, typically summarized by human experts, to supplement the limited labeled data.

Malware Detection Supervised Anomaly Detection +1

DevEval: Evaluating Code Generation in Practical Software Projects

no code implementations12 Jan 2024 Jia Li, Ge Li, YunFei Zhao, Yongmin Li, Zhi Jin, Hao Zhu, Huanyu Liu, Kaibo Liu, Lecheng Wang, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yihong Dong, Yuqi Zhu, Bin Gu, Mengfei Yang

Compared to previous benchmarks, DevEval aligns to practical projects in multiple dimensions, e. g., real program distributions, sufficient dependencies, and enough-scale project contexts.

Code Generation

Path-based Explanation for Knowledge Graph Completion

1 code implementation4 Jan 2024 Heng Chang, Jiangnan Ye, Alejo Lopez Avila, Jinhua Du, Jia Li

Graph Neural Networks (GNNs) have achieved great success in Knowledge Graph Completion (KGC) by modelling how entities and relations interact in recent years.

Knowledge Graph Completion

Learning Performance Maximizing Ensembles with Explainability Guarantees

no code implementations20 Dec 2023 Vincent Pisztora, Jia Li

In this paper we propose a method for the optimal allocation of observations between an intrinsically explainable glass box model and a black box model.

From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting

no code implementations18 Dec 2023 Nuo Chen, Hongguang Li, Baoyuan Wang, Jia Li

IMP-TIP follows the ``From Good to Great" concept, collecting multiple potential solutions from both LLMs and their Tool-Augmented counterparts for the same math problem, and then selecting or re-generating the most accurate answer after cross-checking these solutions via tool-augmented interleaf prompting.

Diversity GSM8K +2

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers

1 code implementation7 Dec 2023 Nuo Chen, Ning Wu, Shining Liang, Ming Gong, Linjun Shou, Dongmei Zhang, Jia Li

This paper presents an in-depth analysis of Large Language Models (LLMs), focusing on LLaMA, a prominent open-source foundational model in natural language processing.

Math Multiple-choice +1

Fair Text-to-Image Diffusion via Fair Mapping

no code implementations29 Nov 2023 Jia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng, Hua Zhang, Di Wang

In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions.

Fairness Text-to-Image Generation

Graph Prompt Learning: A Comprehensive Survey and Beyond

3 code implementations28 Nov 2023 Xiangguo Sun, Jiawen Zhang, Xixi Wu, Hong Cheng, Yun Xiong, Jia Li

This paper presents a pioneering survey on the emerging domain of graph prompts in AGI, addressing key challenges and opportunities in harnessing graph data for AGI applications.

Prompt Learning Survey

Segment Every Out-of-Distribution Object

1 code implementation CVPR 2024 Wenjie Zhao, Jia Li, Xin Dong, Yu Xiang, Yunhui Guo

Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects.

Object Segmentation +1

SSIN: Self-Supervised Learning for Rainfall Spatial Interpolation

1 code implementation27 Nov 2023 Jia Li, Yanyan Shen, Lei Chen, Charles Wang Wai Ng

Inspired by the Cloze task and BERT, we fully consider the characteristics of spatial interpolation and design the SpaFormer model based on the Transformer architecture as the core of SSIN.

Self-Supervised Learning Spatial Interpolation

A Survey of Graph Meets Large Language Model: Progress and Future Directions

3 code implementations21 Nov 2023 Yuhan Li, ZHIXUN LI, Peisong Wang, Jia Li, Xiangguo Sun, Hong Cheng, Jeffrey Xu Yu

First of all, we propose a new taxonomy, which organizes existing methods into three categories based on the role (i. e., enhancer, predictor, and alignment component) played by LLMs in graph-related tasks.

Language Modeling Language Modelling +2

Enabling CMF Estimation in Data-Constrained Scenarios: A Semantic-Encoding Knowledge Mining Model

no code implementations15 Nov 2023 Yanlin Qi, Jia Li, Michael Zhang

This new data-driven framework provides a cost-effective and adaptable solution that complements the case-specific approaches for CMF estimation, which is particularly beneficial when availability of crash data or time imposes constraints.

ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation

no code implementations1 Nov 2023 Zejun Wang, Jia Li, Ge Li, Zhi Jin

To help human users refine their requirements and improve large language models' code generation performances, we propose ChatCoder: a method to refine the requirements via chatting with large language models.

Code Generation

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations

2 code implementations31 Oct 2023 Nuo Chen, Zinan Zheng, Ning Wu, Ming Gong, Dongmei Zhang, Jia Li

This indicates that crafting multilingual corpora can be regarded as a vital strategy for enhancing model performance in a specific language, especially in mathematical reasoning tasks.

GSM8K Math +1

Large Language Model-Aware In-Context Learning for Code Generation

no code implementations15 Oct 2023 Ge Li, Chongyang Tao, Jia Li, Huangzhao Zhang, Fang Liu, Zhi Jin

Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation.

Code Generation Contrastive Learning +5

Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA

no code implementations13 Oct 2023 Sheng Zhou, Dan Guo, Jia Li, Xun Yang, Meng Wang

The associations between these repetitive objects are superfluous for answer reasoning; (2) two spatially distant OCR tokens detected in the image frequently have weak semantic dependencies for answer reasoning; and (3) the co-existence of nearby objects and tokens may be indicative of important visual cues for predicting answers.

Graph Learning Object +6

ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons

1 code implementation11 Oct 2023 Jiawen Zhang, Xumeng Wen, Zhenwei Zhang, Shun Zheng, Jia Li, Jiang Bian

Delivering precise point and distributional forecasts across a spectrum of prediction horizons represents a significant and enduring challenge in the application of time-series forecasting within various industries.

Benchmarking Position +2

Deep Insights into Noisy Pseudo Labeling on Graph Data

1 code implementation NeurIPS 2023 Botao Wang, Jia Li, Yang Liu, Jiashun Cheng, Yu Rong, Wenjia Wang, Fugee Tsung

We first present the error analysis of PL strategy by showing that the error is bounded by the confidence of PL threshold and consistency of multi-view prediction.

Graph Learning Link Prediction +2

Dual-Path Temporal Map Optimization for Make-up Temporal Video Grounding

1 code implementation12 Sep 2023 Jiaxiu Li, Kun Li, Jia Li, Guoliang Chen, Dan Guo, Meng Wang

Compared with the general video grounding task, MTVG focuses on meticulous actions and changes on the face.

Sentence text similarity +1

Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

1 code implementation6 Sep 2023 Yuqi Zhu, Ge Li, YunFei Zhao, Jia Li, Zhi Jin, Hong Mei

With an analysis of loss distributions of code tokens, we find that code tokens can be divided into two categories: challenging tokens that are difficult to predict and confident tokens that can be easily inferred.

Code Generation

ZC3: Zero-Shot Cross-Language Code Clone Detection

1 code implementation26 Aug 2023 Chongyang Tao, Zhi Jin, Fang Liu, Jia Li, Ge Li

In this paper, we propose a novel method named ZC3 for Zero-shot Cross-language Code Clone detection.

Clone Detection Language Modelling

EditSum: A Retrieve-and-Edit Framework for Source Code Summarization

no code implementations26 Aug 2023 Jia Li, Yongmin Li, Ge Li, Xing Hu, Xin Xia, Zhi Jin

Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code.

Code Summarization Informativeness +1

SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases

no code implementations25 Aug 2023 Yang Liu, Jiashun Cheng, Haihong Zhao, Tingyang Xu, Peilin Zhao, Fugee Tsung, Jia Li, Yu Rong

Furthermore, we offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states, which is crucial for model generalization.

Exploiting Diverse Feature for Multimodal Sentiment Analysis

no code implementations25 Aug 2023 Jia Li, Wei Qian, Kun Li, Qi Li, Dan Guo, Meng Wang

Specifically, we achieve the results of 0. 8492 and 0. 8439 for MuSe-Personalisation in terms of arousal and valence CCC.

Multimodal Sentiment Analysis

Relation-Oriented: Toward Causal Knowledge-Aligned AGI

no code implementations31 Jul 2023 Jia Li, Xiang Li

Observation-Oriented paradigm currently dominates relationship learning models, including AI-based ones, which inherently do not account for relationships with temporally nonlinear effects.

Relation Representation Learning

Spectral Normalized-Cut Graph Partitioning with Fairness Constraints

1 code implementation22 Jul 2023 Jia Li, Yanhao Wang, Arpit Merchant

Normalized-cut graph partitioning aims to divide the set of nodes in a graph into $k$ disjoint clusters to minimize the fraction of the total edges between any cluster and all other clusters.

Attribute Fairness +1

Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition

1 code implementation15 Jul 2023 Cheng Chen, Yifan Zhao, Jia Li

Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets.

Contrastive Learning Multi-Label Classification +2

All in One: Multi-task Prompting for Graph Neural Networks

1 code implementation4 Jul 2023 Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan

Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks.

All Meta-Learning +1

Boosting the Generalization Ability for Hyperspectral Image Classification using Spectral-spatial Axial Aggregation Transformer

no code implementations29 Jun 2023 Enzhe Zhao, Zhichang Guo, Shengzhu Shi, Yao Li, Jia Li, Dazhi Zhang

SaaFormer applies a multi-level spectral extraction structure to segment the spectrum into multiple spectrum clips, such that the wavelength continuity of the spectrum across the channel are preserved.

Hyperspectral Image Classification

GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection

1 code implementation NeurIPS 2023 Jianheng Tang, Fengrui Hua, Ziqi Gao, Peilin Zhao, Jia Li

With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a standard comprehensive setting, (2) whether GNNs can outperform traditional algorithms such as tree ensembles, and (3) how about their efficiency on large-scale graphs.

Benchmarking Graph Anomaly Detection

Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning

1 code implementation18 Jun 2023 Yifan Zhao, Tong Zhang, Jia Li, Yonghong Tian

Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains, which are usually infeasible for realistic applications.

cross-domain few-shot learning

Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series

1 code implementation14 Jun 2023 Jiawen Zhang, Shun Zheng, Wei Cao, Jiang Bian, Jia Li

Irregularly sampled multivariate time series are ubiquitous in various fields, particularly in healthcare, and exhibit two key characteristics: intra-series irregularity and inter-series discrepancy.

Irregular Time Series Representation Learning +1

A Graph Transformer-Driven Approach for Network Robustness Learning

no code implementations12 Jun 2023 Yu Zhang, Jia Li, Jie Ding, Xiang Li

Learning and analysis of network robustness, including controllability robustness and connectivity robustness, is critical for various networked systems against attacks.

GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction

2 code implementations2 Jun 2023 Amit Roy, Juan Shu, Jia Li, Carl Yang, Olivier Elshocht, Jeroen Smeets, Pan Li

Graph Anomaly Detection (GAD) is a technique used to identify abnormal nodes within graphs, finding applications in network security, fraud detection, social media spam detection, and various other domains.

Fraud Detection Graph Anomaly Detection +1

EvEval: A Comprehensive Evaluation of Event Semantics for Large Language Models

no code implementations24 May 2023 Zhengwei Tao, Zhi Jin, Xiaoying Bai, Haiyan Zhao, Yanlin Feng, Jia Li, Wenpeng Hu

In this paper, we propose an overarching framework for event semantic processing, encompassing understanding, reasoning, and prediction, along with their fine-grained aspects.

Smart Pressure e-Mat for Human Sleeping Posture and Dynamic Activity Recognition

no code implementations19 May 2023 Liangqi Yuan, Yuan Wei, Jia Li

Deep neural networks (DNNs) are used to fit and train the pressure image stream and recognize the corresponding human behavior.

Activity Recognition

Structured Chain-of-Thought Prompting for Code Generation

no code implementations11 May 2023 Jia Li, Ge Li, Yongmin Li, Zhi Jin

In this paper, we propose Structured CoTs (SCoTs) and present a novel prompting technique for code generation, named SCoT prompting.

Code Generation HumanEval +2

A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment

1 code implementation11 May 2023 Jianheng Tang, Kangfei Zhao, Jia Li

In this paper, we introduce FGWEA, an unsupervised entity alignment framework that leverages the Fused Gromov-Wasserstein (FGW) distance, allowing for a comprehensive comparison of entity semantics and KG structures within a joint optimization framework.

Entity Alignment Knowledge Graphs

Alleviating Over-smoothing for Unsupervised Sentence Representation

1 code implementation9 May 2023 Nuo Chen, Linjun Shou, Ming Gong, Jian Pei, Bowen Cao, Jianhui Chang, Daxin Jiang, Jia Li

Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities.

Contrastive Learning Semantic Textual Similarity +1

StarCoder: may the source be with you!

4 code implementations9 May 2023 Raymond Li, Loubna Ben allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, Qian Liu, Evgenii Zheltonozhskii, Terry Yue Zhuo, Thomas Wang, Olivier Dehaene, Mishig Davaadorj, Joel Lamy-Poirier, João Monteiro, Oleh Shliazhko, Nicolas Gontier, Nicholas Meade, Armel Zebaze, Ming-Ho Yee, Logesh Kumar Umapathi, Jian Zhu, Benjamin Lipkin, Muhtasham Oblokulov, Zhiruo Wang, Rudra Murthy, Jason Stillerman, Siva Sankalp Patel, Dmitry Abulkhanov, Marco Zocca, Manan Dey, Zhihan Zhang, Nour Fahmy, Urvashi Bhattacharyya, Wenhao Yu, Swayam Singh, Sasha Luccioni, Paulo Villegas, Maxim Kunakov, Fedor Zhdanov, Manuel Romero, Tony Lee, Nadav Timor, Jennifer Ding, Claire Schlesinger, Hailey Schoelkopf, Jan Ebert, Tri Dao, Mayank Mishra, Alex Gu, Jennifer Robinson, Carolyn Jane Anderson, Brendan Dolan-Gavitt, Danish Contractor, Siva Reddy, Daniel Fried, Dzmitry Bahdanau, Yacine Jernite, Carlos Muñoz Ferrandis, Sean Hughes, Thomas Wolf, Arjun Guha, Leandro von Werra, Harm de Vries

The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.

8k Code Generation +1

Self-Edit: Fault-Aware Code Editor for Code Generation

1 code implementation6 May 2023 Kechi Zhang, Zhuo Li, Jia Li, Ge Li, Zhi Jin

Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task.

Code Generation HumanEval

Data Imputation from the Perspective of Graph Dirichlet Energy

1 code implementation10 Apr 2023 Weiqi Zhang, Guanlue Li, Jianheng Tang, Jia Li, Fugee Tsung

In our study, we examine this prevalent strategy through the lens of graph Dirichlet energy.

Imputation

Passive Radio Frequency-based 3D Indoor Positioning System via Ensemble Learning

no code implementations25 Mar 2023 Liangqi Yuan, Houlin Chen, Robert Ewing, Jia Li

Passive radio frequency (PRF)-based indoor positioning systems (IPS) have attracted researchers' attention due to their low price, easy and customizable configuration, and non-invasive design.

Ensemble Learning

Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers

1 code implementation16 Mar 2023 Jia Li, Yin Chen, Xuesong Zhang, Jiantao Nie, Ziqiang Li, Yangchen Yu, Yan Zhang, Richang Hong, Meng Wang

In this paper, we present our advanced solutions to the two sub-challenges of Affective Behavior Analysis in the wild (ABAW) 2023: the Emotional Reaction Intensity (ERI) Estimation Challenge and Expression (Expr) Classification Challenge.

Classification

A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data

2 code implementations12 Mar 2023 Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet

This observation allows us to provide an approximation bound for the distance between the fixed-point set of BAPG and the critical point set of GW.

Computational Efficiency

Decision Support System for Chronic Diseases Based on Drug-Drug Interactions

1 code implementation4 Mar 2023 Tian Bian, Yuli Jiang, Jia Li, Tingyang Xu, Yu Rong, Yi Su, Timothy Kwok, Helen Meng, Hong Cheng

Many patients with chronic diseases resort to multiple medications to relieve various symptoms, which raises concerns about the safety of multiple medication use, as severe drug-drug antagonism can lead to serious adverse effects or even death.

counterfactual Diagnostic +1

Knowledge Graph Completion with Counterfactual Augmentation

no code implementations25 Feb 2023 Heng Chang, Jie Cai, Jia Li

With a carefully designed instantiation of a causal model on the knowledge graph, we generate the counterfactual relations to answer the question by regarding the representations of entity pair given relation as context, structural information of relation-aware neighborhood as treatment, and validity of the composed triplet as the outcome.

counterfactual Knowledge Graph Completion +2

Natural Response Generation for Chinese Reading Comprehension

1 code implementation17 Feb 2023 Nuo Chen, Hongguang Li, Yinan Bao, Baoyuan Wang, Jia Li

To this end, we construct a new dataset called Penguin to promote the research of MRC, providing a training and test bed for natural response generation to real scenarios.

Chinese Reading Comprehension Machine Reading Comprehension +1

Bridge the Gap between Language models and Tabular Understanding

no code implementations16 Feb 2023 Nuo Chen, Linjun Shou, Ming Gong, Jian Pei, Chenyu You, Jianhui Chang, Daxin Jiang, Jia Li

For instance, TPLMs jointly pre-trained with table and text input could be effective for tasks also with table-text joint input like table question answering, but it may fail for tasks with only tables or text as input such as table retrieval.

Contrastive Learning Language Modeling +3

Syntax and Domain Aware Model for Unsupervised Program Translation

no code implementations8 Feb 2023 Fang Liu, Jia Li, Li Zhang

The experimental results on function translation tasks between Python, Java, and C++ show that SDA-Trans outperforms many large-scale pre-trained models, especially for unseen language translation.

Cross-Lingual Transfer Translation

Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport

1 code implementation30 Jan 2023 Jianheng Tang, Weiqi Zhang, Jiajin Li, Kangfei Zhao, Fugee Tsung, Jia Li

As the graphs to be aligned are usually constructed from different sources, the inconsistency issues of structures and features between two graphs are ubiquitous in real-world applications.

Graph Embedding

E2NeRF: Event Enhanced Neural Radiance Fields from Blurry Images

1 code implementation ICCV 2023 Yunshan Qi, Lin Zhu, Yu Zhang, Jia Li

To solve this problem, we propose a novel Event-Enhanced NeRF (E2NeRF) by utilizing the combination data of a bio-inspired event camera and a standard RGB camera.

Camera Pose Estimation Deblurring +4

Part-guided Relational Transformers for Fine-grained Visual Recognition

1 code implementation28 Dec 2022 Yifan Zhao, Jia Li, Xiaowu Chen, Yonghong Tian

This framework, namely PArt-guided Relational Transformers (PART), is proposed to learn the discriminative part features with an automatic part discovery module, and to explore the intrinsic correlations with a feature transformation module by adapting the Transformer models from the field of natural language processing.

Fine-Grained Image Classification Fine-Grained Visual Recognition +1

Parsing Objects at a Finer Granularity: A Survey

no code implementations28 Dec 2022 Yifan Zhao, Jia Li, Yonghong Tian

Fine-grained visual parsing, including fine-grained part segmentation and fine-grained object recognition, has attracted considerable critical attention due to its importance in many real-world applications, e. g., agriculture, remote sensing, and space technologies.

Fine-Grained Visual Recognition Human Part Segmentation +3

Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax

no code implementations12 Dec 2022 Yang Liu, Yu Rong, Zhuoning Guo, Nuo Chen, Tingyang Xu, Fugee Tsung, Jia Li

To address these challenges, we formulate the micro perspective mobility modeling into computing the relevance score between a diffusion and a location, conditional on a geometric graph.

Handling Missing Data via Max-Entropy Regularized Graph Autoencoder

no code implementations30 Nov 2022 Ziqi Gao, Yifan Niu, Jiashun Cheng, Jianheng Tang, Tingyang Xu, Peilin Zhao, Lanqing Li, Fugee Tsung, Jia Li

In this work, we present a regularized graph autoencoder for graph attribute imputation, named MEGAE, which aims at mitigating spectral concentration problem by maximizing the graph spectral entropy.

Attribute Imputation

The Stack: 3 TB of permissively licensed source code

no code implementations20 Nov 2022 Denis Kocetkov, Raymond Li, Loubna Ben allal, Jia Li, Chenghao Mou, Carlos Muñoz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, Harm de Vries

Large Language Models (LLMs) play an ever-increasing role in the field of Artificial Intelligence (AI)--not only for natural language processing but also for code understanding and generation.

HumanEval mbpp

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

1 code implementation3 Nov 2022 Haojie Zhang, Ge Li, Jia Li, Zhongjin Zhang, Yuqi Zhu, Zhi Jin

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently.

Language Modeling Language Modelling

Poison Attack and Defense on Deep Source Code Processing Models

no code implementations31 Oct 2022 Jia Li, Zhuo Li, Huangzhao Zhang, Ge Li, Zhi Jin, Xing Hu, Xin Xia

The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples.

Clone Detection Code Repair +1

CodeEditor: Learning to Edit Source Code with Pre-trained Models

1 code implementation31 Oct 2022 Jia Li, Ge Li, Zhuo Li, Zhi Jin, Xing Hu, Kechi Zhang, Zhiyi Fu

Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.

Language Modeling Language Modelling +1

View-aware Salient Object Detection for 360° Omnidirectional Image

no code implementations27 Sep 2022 Junjie Wu, Changqun Xia, Tianshu Yu, Jia Li

Inspired by humans' observing process, we propose a view-aware salient object detection method based on a Sample Adaptive View Transformer (SAVT) module with two sub-modules to mitigate these issues.

2k ERP +4

Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images

1 code implementation15 Aug 2022 Ruining Deng, Can Cui, Lucas W. Remedios, Shunxing Bao, R. Michael Womick, Sophie Chiron, Jia Li, Joseph T. Roland, Ken S. Lau, Qi Liu, Keith T. Wilson, Yaohong Wang, Lori A. Coburn, Bennett A. Landman, Yuankai Huo

Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotations.

whole slide images

Generating Negative Samples for Sequential Recommendation

no code implementations7 Aug 2022 Yongjun Chen, Jia Li, Zhiwei Liu, Nitish Shirish Keskar, Huan Wang, Julian McAuley, Caiming Xiong

Due to the dynamics of users' interests and model updates during training, considering randomly sampled items from a user's non-interacted item set as negatives can be uninformative.

Sequential Recommendation

Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis

1 code implementation5 Aug 2022 Jia Li, Ziyang Zhang, Junjie Lang, Yueqi Jiang, Liuwei An, Peng Zou, Yangyang Xu, Sheng Gao, Jie Lin, Chunxiao Fan, Xiao Sun, Meng Wang

In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges.

Data Augmentation Humor Detection +1

Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers

no code implementations22 Jul 2022 Jia Li, Jiantao Nie, Dan Guo, Richang Hong, Meng Wang

PF-ViT aims to separate and recognize the disturbance-agnostic emotion from a static facial image via generating its corresponding poker face, without the need for paired images.

Disentanglement Face Generation +2

Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

1 code implementation20 Jul 2022 Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Jiajun Shen, Jia Li, Xiaojuan Qi

With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i. e., ultra-high-definition) images.

4k Image Enhancement +2

Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning

1 code implementation26 Jun 2022 Jiashun Cheng, Man Li, Jia Li, Fugee Tsung

Graph self-supervised learning (SSL) has been vastly employed to learn representations from unlabeled graphs.

Contrastive Learning Decoder +1

Deep Learning Eliminates Massive Dust Storms from Images of Tianwen-1

no code implementations21 Jun 2022 Hongyu Li, Jia Li, Xin Ren, Long Xu

Inspired by the haze formation process on Earth, we formulate a similar visual degradation process on clean images and synthesize dusty images sharing a similar feature distribution with realistic dusty images.

Image Dehazing

Semi-Supervised Hierarchical Graph Classification

no code implementations11 Jun 2022 Jia Li, Yongfeng Huang, Heng Chang, Yu Rong

We study the node classification problem in the hierarchical graph where a 'node' is a graph instance.

Graph Classification Graph Learning +1

MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation

1 code implementation31 May 2022 Wenzhuo Yang, Jia Li, Caiming Xiong, Steven C. H. Hoi

Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions.

BIG-bench Machine Learning counterfactual +1

Fast and Provably Convergent Algorithms for Gromov-Wasserstein in Graph Data

no code implementations17 May 2022 Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet

In this paper, we study the design and analysis of a class of efficient algorithms for computing the Gromov-Wasserstein (GW) distance tailored to large-scale graph learning tasks.

Graph Learning

Pyramid Grafting Network for One-Stage High Resolution Saliency Detection

1 code implementation CVPR 2022 Chenxi Xie, Changqun Xia, Mingcan Ma, Zhirui Zhao, Xiaowu Chen, Jia Li

An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process.

Ranked #8 on RGB Salient Object Detection on UHRSD (using extra training data)

4k 8k +5

Video Demoireing with Relation-Based Temporal Consistency

1 code implementation CVPR 2022 Peng Dai, Xin Yu, Lan Ma, Baoheng Zhang, Jia Li, Wenbo Li, Jiajun Shen, Xiaojuan Qi

Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.

Relation

ELECRec: Training Sequential Recommenders as Discriminators

1 code implementation5 Apr 2022 Yongjun Chen, Jia Li, Caiming Xiong

A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training.

Sequential Recommendation

Improving Contrastive Learning with Model Augmentation

1 code implementation25 Mar 2022 Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong

However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.

Contrastive Learning Data Augmentation +3

ConTinTin: Continual Learning from Task Instructions

no code implementations ACL 2022 Wenpeng Yin, Jia Li, Caiming Xiong

This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction.

Continual Learning

Robust facial expression recognition with global‑local joint representation learning

no code implementations Multimedia Systems 2022 Chunxiao Fan, zhenxing Wang, Jia Li, Shanshan Wang, Xiao Sun

In the proposed method, (1) the topological structure information and texture feature of regions of interest (ROIs) are modeled as graphs and processed with graph convolutional network (GCN) to remain the topological features.

Facial Expression Recognition Facial Expression Recognition (FER) +1

Styleverse: Towards Identity Stylization across Heterogeneous Domains

no code implementations2 Mar 2022 Jia Li, Jie Cao, Junxian Duan, Ran He

We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains.

Style Transfer

Intent Contrastive Learning for Sequential Recommendation

1 code implementation5 Feb 2022 Yongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley, Caiming Xiong

Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.

Contrastive Learning Model Optimization +3

RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems

1 code implementation12 Jan 2022 Zohreh Ovaisi, Shelby Heinecke, Jia Li, Yongfeng Zhang, Elena Zheleva, Caiming Xiong

Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data.

Recommendation Systems

Deconvolutional Networks on Graph Data

no code implementations NeurIPS 2021 Jia Li, Jiajin Li, Yang Liu, Jianwei Yu, Yueting Li, Hong Cheng

In this paper, we consider an inverse problem in graph learning domain -- ``given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?"

Graph Learning Imputation

Receptive Field Broadening and Boosting for Salient Object Detection

no code implementations15 Oct 2021 Mingcan Ma, Changqun Xia, Chenxi Xie, Xiaowu Chen, Jia Li

Moreover, Unlike multi-path parallel training, MHB randomly selects one branch each time for gradient back propagation in a boosting way.

Object object-detection +3

Deconfounded Causal Collaborative Filtering

1 code implementation14 Oct 2021 Shuyuan Xu, Juntao Tan, Shelby Heinecke, Jia Li, Yongfeng Zhang

Experiments on real-world datasets show that our method is able to deconfound unobserved confounders to achieve better recommendation performance.

Collaborative Filtering Recommendation Systems

Transformer-based Dual Relation Graph for Multi-label Image Recognition

1 code implementation ICCV 2021 Jiawei Zhao, Ke Yan, Yifan Zhao, Xiaowei Guo, Feiyue Huang, Jia Li

Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i. e., structural relation graph and semantic relation graph.

Multi-Label Classification Multi-Label Image Recognition +1

Universal Face Restoration With Memorized Modulation

no code implementations3 Oct 2021 Jia Li, Huaibo Huang, Xiaofei Jia, Ran He

Blind face restoration (BFR) is a challenging problem because of the uncertainty of the degradation patterns.

Blind Face Restoration

Self-supervised Learning for Sequential Recommendation with Model Augmentation

no code implementations29 Sep 2021 Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong

However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.

Contrastive Learning Data Augmentation +2

Modeling Dynamic Attributes for Next Basket Recommendation

no code implementations23 Sep 2021 Yongjun Chen, Jia Li, Chenghao Liu, Chenxi Li, Markus Anderle, Julian McAuley, Caiming Xiong

However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.

Attribute Next-basket recommendation

Heterogeneous Relational Complement for Vehicle Re-identification

1 code implementation ICCV 2021 Jiajian Zhao, Yifan Zhao, Jia Li, Ke Yan, Yonghong Tian

The crucial problem in vehicle re-identification is to find the same vehicle identity when reviewing this object from cross-view cameras, which sets a higher demand for learning viewpoint-invariant representations.

Vehicle Re-Identification

Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing

1 code implementation15 Sep 2021 Dong Zhao, Jia Li, Hongyu Li, Long Xu

In this paper, firstly, we propose a new complementary feature enhanced framework, in which the complementary features are learned by several complementary subtasks and then together serve to boost the performance of the primary task.

Image Dehazing Image Generation +2

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