Search Results for author: Hao Wang

Found 668 papers, 224 papers with code

融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition)

no code implementations CCL 2021 Hao Wang, Junhui Li, ZhengXian Gong

“在汉语等其他有省略代词习惯的语言中, 通常会删掉可从上下文信息推断出的代词。尽管以Transformer为代表的的神经机器翻译模型取得了巨大的成功, 但这种省略现象依旧对神经机器翻译模型造成了很大的挑战。本文在Transformer基础上提出了一个融合零指代识别的翻译模型, 并引入篇章上下文来丰富指代信息。具体地, 该模型采用联合学习的框架, 在翻译模型基础上, 联合了一个分类任务, 即判别句子中省略代词在句子所表示的成分, 使得模型能够融合零指代信息辅助翻译。通过在中英对话数据集上的实验, 验证了本文提出方法的有效性, 与基准模型相比, 翻译性能提升了1. 48个BLEU值。”

Machine Translation

Toward Knowledge-Enriched Conversational Recommendation Systems

no code implementations NLP4ConvAI (ACL) 2022 Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.

Conversational Recommendation Knowledge Graphs +2

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

1 code implementation ECCV 2020 Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li

However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.

3D Face Reconstruction

TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation

no code implementations5 Feb 2025 Jiaqing Zhang, Mingjia Yin, Hao Wang, Yawen Li, Yuyang Ye, Xingyu Lou, Junping Du, Enhong Chen

In the era of data-centric AI, the focus of recommender systems has shifted from model-centric innovations to data-centric approaches.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

no code implementations5 Feb 2025 Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, Dimitris N. Metaxas

Extensive experiments show that VISTA on average reduces hallucination by abount 40% on evaluated open-ended generation task, and it consistently outperforms existing methods on four benchmarks across four architectures under three decoding strategies.

Transfer Learning of Surrogate Models: Integrating Domain Warping and Affine Transformations

no code implementations30 Jan 2025 Shuaiqun Pan, Diederick Vermetten, Manuel López-Ibáñez, Thomas Bäck, Hao Wang

Surrogate models provide efficient alternatives to computationally demanding real-world processes but often require large datasets for effective training.

Transfer Learning

SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation

1 code implementation28 Jan 2025 Jianing Li, Ming Lu, Hao Wang, Chenyang Gu, Wenzhao Zheng, Li Du, Shanghang Zhang

To utilize these slice features, we propose SliceOcc, an RGB camera-based model specifically tailored for indoor 3D semantic occupancy prediction.

3D Semantic Occupancy Prediction Autonomous Driving +1

THOR: A Generic Energy Estimation Approach for On-Device Training

no code implementations27 Jan 2025 Jiaru Zhang, Zesong Wang, Hao Wang, Tao Song, Huai-an Su, Rui Chen, Yang Hua, Xiangwei Zhou, Ruhui Ma, Miao Pan, Haibing Guan

However, the heterogeneity of devices and the complexity of models challenge the accuracy and generalizability of existing estimation methods.

Scheduling

The silent threat of methane to ecosystems: Insights from mechanistic modelling

no code implementations24 Jan 2025 Pranali Roy Chowdhury, Tianxu Wang, Shohel Ahmed, Hao Wang

This work highlights the urgent need for a better understanding of the fatal role of methane in ecosystems for developing strategies to mitigate its effects amid climate change.

InsTex: Indoor Scenes Stylized Texture Synthesis

no code implementations22 Jan 2025 Yunfan Zhang, Zhiwei Xiong, Zhiqi Shen, Guosheng Lin, Hao Wang, Nicolas Vun

Generating high-quality textures for 3D scenes is crucial for applications in interior design, gaming, and augmented/virtual reality (AR/VR).

Texture Synthesis

Shifts of dominant personality and spatial pattern formation due to spatially heterogeneous pollution

no code implementations22 Jan 2025 Tianxu Wang, Jiwoon Sim, Hao Wang

The spatial pattern of the population is also closely tied to the distribution of toxins.

ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models

1 code implementation20 Jan 2025 Jingwei Yi, Junhao Yin, Ju Xu, Peng Bao, Yongliang Wang, Wei Fan, Hao Wang

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in understanding multimodal inputs and have been widely integrated into Retrieval-Augmented Generation (RAG) based conversational systems.

RAG Retrieval

Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems

no code implementations17 Jan 2025 Weibo Gao, Qi Liu, Linan Yue, Fangzhou Yao, Rui Lv, Zheng Zhang, Hao Wang, Zhenya Huang

Personalized learning represents a promising educational strategy within intelligent educational systems, aiming to enhance learners' practice efficiency.

Response Generation

AirRAG: Activating Intrinsic Reasoning for Retrieval Augmented Generation via Tree-based Search

no code implementations17 Jan 2025 Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Jingyi Song, Hao Wang

Leveraging the autonomous decision-making capabilities of large language models (LLMs) demonstrates superior performance in reasoning tasks.

Decision Making RAG +1

Deep Learning for Disease Outbreak Prediction: A Robust Early Warning Signal for Transcritical Bifurcations

no code implementations14 Jan 2025 Reza Miry, Amit K. Chakraborty, Russell Greiner, Mark A. Lewis, Hao Wang, Tianyu Guan, Pouria Ramazi

We employed two simulated datasets to train the model: one representing generated dynamical systems with randomly selected polynomial terms to model new disease behaviors, and another simulating noise-induced disease dynamics to account for noisy measurements.

Time Series Classification

Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding

no code implementations12 Jan 2025 Junlong Ren, Gangjian Zhang, Haifeng Sun, Hao Wang

The data augmentation generates videos with various lengths and target moment locations to diversify temporal distributions.

Data Augmentation Domain Adaptation +2

DVM: Towards Controllable LLM Agents in Social Deduction Games

no code implementations12 Jan 2025 Zheng Zhang, Yihuai Lan, Yangsen Chen, Lei Wang, Xiang Wang, Hao Wang

This control not only ensures that NPCs can adapt to varying difficulty levels during gameplay, but also provides insights into the safety and fairness of LLM agents.

Fairness

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models

no code implementations9 Jan 2025 Peizhuo Lv, Mengjie Sun, Hao Wang, XiaoFeng Wang, Shengzhi Zhang, Yuxuan Chen, Kai Chen, Limin Sun

To address those problems, we propose a novel black-box "knowledge watermark" approach, named RAG-WM, to detect IP infringement of RAGs.

RAG

Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences

no code implementations6 Jan 2025 Xiwen Chen, Peijie Qiu, Wenhui Zhu, Huayu Li, Hao Wang, Aristeidis Sotiras, Yalin Wang, Abolfazl Razi

Since its introduction, the transformer has shifted the development trajectory away from traditional models (e. g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal tokens.

Time Series Time Series Forecasting

Environmental Factors Can Have Opposite Biodiversity Influences on the Community Temporal Stability In Aquatic Ecosystems

no code implementations6 Jan 2025 Zihao Wen, Hang Shan, Hao Wang, Yu Cao, Liang He, Wenjing Ren, Chengjie Yin, Qingchuan Chou, Chaochao Lv, Haojie Su, Tao Tang, Qinghua Cai, Leyi Ni, Wen Xiao, Xiaolin Zhang, Kuanyi Li, Te Cao, Ming-Chih Chiu, Vincent H. Resh, Pablo Urrutia-Cordero

However, we know little about how local environmental conditions can influence these biodiversity drivers, and consequently how they indirectly shape the ecological stability of ecosystems.

DeepFilter: An Instrumental Baseline for Accurate and Efficient Process Monitoring

no code implementations2 Jan 2025 Hao Wang, Zhichao Chen, Licheng Pan, Xiaoyu Jiang, Yichen Song, Qunshan He, Xinggao Liu

Effective process monitoring is increasingly vital in industrial automation for ensuring operational safety, necessitating both high accuracy and efficiency.

Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion

no code implementations1 Jan 2025 Hao Wang, Xiwen Chen, Ashish Bastola, Jiayou Qin, Abolfazl Razi

The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient.

Data Augmentation Diversity +2

Knowledge-Guided Prompt Learning for Deepfake Facial Image Detection

no code implementations1 Jan 2025 Hao Wang, Cheng Deng, Zhidong Zhao

Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images.

Face Swapping

Derivations of Animal Movement Models with Explicit Memory

no code implementations29 Dec 2024 Tianxu Wang, Kyunghan Choi, Hao Wang

These derivations highlight how different ways of using memory lead to distinct mathematical models.

Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation

1 code implementation29 Dec 2024 Hao Zhang, Hao Wang, Xiucai Huang, Wenrui Chen, Zhen Kan

To tackle these challenges, we propose a Temporal-Logic-guided Hybrid policy framework (HyTL) which leverages three-level decision layers to improve the agent's performance.

Reinforcement Learning (RL)

Tracking the Feature Dynamics in LLM Training: A Mechanistic Study

no code implementations23 Dec 2024 Yang Xu, Yi Wang, Hao Wang

Understanding training dynamics and feature evolution is crucial for the mechanistic interpretability of large language models (LLMs).

CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels

no code implementations17 Dec 2024 Shizhuo Deng, Bowen Han, Jiaqi Chen, Hao Wang, Dongyue Chen, Tong Jia

Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain.

Domain Generalization Few-Shot Learning +1

Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks

no code implementations17 Dec 2024 Hao Wang, Boyi Liu, Yufeng Zhang, Jie Chen

Leveraging Qwen2. 5-Coder-32B-Instruct, our approach achieves a pass rate of 0. 305 on LiveCodeBench-Hard, surpassing the pass@100 performance of GPT4o-0513 (0. 245).

Code Generation

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

no code implementations17 Dec 2024 Aldo Pareja, Nikhil Shivakumar Nayak, Hao Wang, KrishnaTeja Killamsetty, Shivchander Sudalairaj, Wenlong Zhao, Seungwook Han, Abhishek Bhandwaldar, Guangxuan Xu, Kai Xu, Ligong Han, Luke Inglis, Akash Srivastava

The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual developers and small organizations face barriers due to limited resources.

MMLU

Improving Automatic Fetal Biometry Measurement with Swoosh Activation Function

no code implementations16 Dec 2024 Shijia Zhou, Euijoon Ahn, Hao Wang, Ann Quinton, Narelle Kennedy, Pradeeba Sridar, Ralph Nanan, Jinman Kim

To address these inadequacies, we propose a novel Swoosh Activation Function (SAF) designed to enhance the regularization of heatmaps produced by landmark detection algorithms.

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

no code implementations11 Dec 2024 Mingkun Lei, Xue Song, Beier Zhu, Hao Wang, Chi Zhang

Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges remain, particularly with overfitting to reference styles, limiting stylistic control, and misaligning with textual content.

Style Transfer

5G NR monostatic positioning with array impairments: Data-and-model-driven framework and experiment results

no code implementations11 Dec 2024 Shengheng Liu, Hao Wang, Mengguan Pan, Peng Liu, Yahui Ma, Yongming Huang

In this article, we present an intelligent framework for 5G new radio (NR) indoor positioning under a monostatic configuration.

An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism

no code implementations8 Dec 2024 Qing Zhang, Haocheng Lv, Jie Liu, Zhiyun Chen, Jianyong Duan, Hao Wang, Li He, Mingying Xv

With the rise of large-scale language models (LLMs), it is currently popular and effective to convert multimodal information into text descriptions for multimodal multi-hop question answering.

Multi-hop Question Answering Multi-Task Learning +1

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

1 code implementation7 Dec 2024 Haizhou Shi, Yibin Wang, Ligong Han, huan zhang, Hao Wang

Estimating the uncertainty of responses of Large Language Models~(LLMs) remains a critical challenge.

Variational Inference

Human Multi-View Synthesis from a Single-View Model:Transferred Body and Face Representations

no code implementations4 Dec 2024 Yu Feng, Shunsi Zhang, Jian Shu, HanFeng Zhao, Guoliang Pang, Chi Zhang, Hao Wang

Specifically, we use a single-view model pretrained on a large-scale human dataset to develop a multi-view body representation, aiming to extend the 2D knowledge of the single-view model to a multi-view diffusion model.

Novel View Synthesis

Geographical Information Alignment Boosts Traffic Analysis via Transpose Cross-attention

no code implementations3 Dec 2024 Xiangyu Jiang, Xiwen Chen, Hao Wang, Abolfazl Razi

This module can efficiently fuse the node feature and geographic position information through a novel Transpose Cross-attention mechanism.

Position severity prediction

FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domain

1 code implementation2 Dec 2024 Zhengnan Li, Haoxuan Li, Hao Wang, Jun Fang, Duoyin Li Yunxiao Qin

In this paper, we investigate the overfitting problem in channel-wise MLPs using Rademacher complexity theory, revealing that extreme values in time series data exacerbate this issue.

Time Series Time Series Forecasting +1

Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy

no code implementations30 Nov 2024 Tingjia Shen, Hao Wang, Chuhan Wu, Jin Yao Chin, Wei Guo, Yong liu, Huifeng Guo, Defu Lian, Ruiming Tang, Enhong Chen

In response, we introduce the Performance Law for SR models, which aims to theoretically investigate and model the relationship between model performance and data quality.

Sequential Recommendation

Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition

1 code implementation28 Nov 2024 Hongda Liu, Yunfan Liu, Min Ren, Hao Wang, Yunlong Wang, Zhenan Sun

In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal representations.

Action Recognition Skeleton Based Action Recognition

Diversification quotient based on expectiles

no code implementations22 Nov 2024 Xia Han, Liyuan Lin, Hao Wang, Ruodu Wang

A diversification quotient (DQ) quantifies diversification in stochastic portfolio models based on a family of risk measures.

SEMPose: A Single End-to-end Network for Multi-object Pose Estimation

no code implementations21 Nov 2024 Xin Liu, Hao Wang, Shibei Xue, Dezong Zhao

On the LM-O and YCB-V datasets, our method outperforms other RGB-based single-model methods, achieving higher accuracy.

Object Pose Estimation

RobustFormer: Noise-Robust Pre-training for images and videos

no code implementations20 Nov 2024 Ashish Bastola, Nishant Luitel, Hao Wang, Danda Pani Paudel, Roshani Poudel, Abolfazl Razi

While deep learning models are powerful tools that revolutionized many areas, they are also vulnerable to noise as they rely heavily on learning patterns and features from the exact details of the clean data.

Automated 3D Physical Simulation of Open-world Scene with Gaussian Splatting

no code implementations19 Nov 2024 Haoyu Zhao, Hao Wang, Xingyue Zhao, Hongqiu Wang, Zhiyu Wu, Chengjiang Long, Hua Zou

Recent advancements in 3D generation models have opened new possibilities for simulating dynamic 3D object movements and customizing behaviors, yet creating this content remains challenging.

3D Generation Large Language Model +2

A Hybrid Loss Framework for Decomposition-based Time Series Forecasting Methods: Balancing Global and Component Errors

no code implementations18 Nov 2024 Ronghui Han, Duanyu Feng, Hongyu Du, Hao Wang

To investigate this, we conduct a study on the impact of overall loss on existing time series methods with sequence decomposition.

Time Series Time Series Forecasting

NeuroNURBS: Learning Efficient Surface Representations for 3D Solids

no code implementations16 Nov 2024 Jiajie Fan, Babak Gholami, Thomas Bäck, Hao Wang

Boundary Representation (B-Rep) is the de facto representation of 3D solids in Computer-Aided Design (CAD).

Representation Learning

Partial Scene Text Retrieval

1 code implementation15 Nov 2024 Hao Wang, Minghui Liao, Zhouyi Xie, Wenyu Liu, Xiang Bai

To address this issue, we propose a Ranking MIL (RankMIL) approach to adaptively filter those noisy samples.

Multiple Instance Learning Text Retrieval

Methane projections from Canada's oil sands tailings using scientific deep learning reveal significant underestimation

no code implementations11 Nov 2024 Esha Saha, Oscar Wang, Amit K. Chakraborty, Pablo Venegas Garcia, Russell Milne, Hao Wang

Bitumen extraction for the production of synthetic crude oil in Canada's Athabasca Oil Sands industry has recently come under spotlight for being a significant source of greenhouse gas emission.

GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes

no code implementations4 Nov 2024 Gaochao Song, Chong Cheng, Hao Wang

In this paper we present a novel method for efficient and effective 3D surface reconstruction in open scenes.

3DGS NeRF +1

Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning

no code implementations4 Nov 2024 Guangxuan Xu, Kai Xu, Shivchander Sudalairaj, Hao Wang, Akash Srivastava

In this paper, we introduce Dr. SoW (Density Ratio of Strong over Weak) a cost-effective method that eliminates the reliance for human annotation by leveraging off-the-shelf LLMs for preference data annotation.

Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling

1 code implementation4 Nov 2024 Weibo Gao, Qi Liu, Linan Yue, Fangzhou Yao, Hao Wang, Yin Gu, Zheng Zhang

Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states (i. e., knowledge proficiency) in the context of intelligent education.

cognitive diagnosis Disentanglement +1

Towards Convexity in Anomaly Detection: A New Formulation of SSLM with Unique Optimal Solutions

no code implementations31 Oct 2024 Hongying Liu, Hao Wang, Haoran Chu, Yibo Wu

An unsolved issue in widely used methods such as Support Vector Data Description (SVDD) and Small Sphere and Large Margin SVM (SSLM) for anomaly detection is their nonconvexity, which hampers the analysis of optimal solutions in a manner similar to SVMs and limits their applicability in large-scale scenarios.

Anomaly Detection

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training

no code implementations25 Oct 2024 Kristjan Greenewald, Yuancheng Yu, Hao Wang, Kai Xu

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure.

Designing a Dataset for Convolutional Neural Networks to Predict Space Groups Consistent with Extinction Laws

no code implementations21 Oct 2024 Hao Wang, Jiajun Zhong, Yikun Li, Junrong Zhang, Rong Du

In this paper, a dataset of one-dimensional powder diffraction patterns was designed with new strategy to train Convolutional Neural Networks for predicting space groups.

Synthetic Data Generation for Residential Load Patterns via Recurrent GAN and Ensemble Method

no code implementations20 Oct 2024 Xinyu Liang, Ziheng Wang, Hao Wang

Our developed ERGAN can capture diverse load patterns across various households, thereby enhancing the realism and diversity of the synthetic data generated.

Diversity Generative Adversarial Network +1

A Prompt Refinement-based Large Language Model for Metro Passenger Flow Forecasting under Delay Conditions

no code implementations19 Oct 2024 Ping Huang, Yuxin He, Hao Wang, Jingjing Chen, Qin Luo

Accurate short-term forecasts of passenger flow in metro systems under delay conditions are crucial for emergency response and service recovery, which pose significant challenges and are currently under-researched.

Descriptive Few-Shot Learning +4

MambaBEV: An efficient 3D detection model with Mamba2

no code implementations16 Oct 2024 Zihan You, Hao Wang, Qichao Zhao, Jinxiang Wang

However, current temporal fusion model use convolutional layer or deformable self-attention is not conducive to the exchange of global information of BEV space and has more computational cost.

3D Object Detection Autonomous Driving +2

On Calibration of LLM-based Guard Models for Reliable Content Moderation

1 code implementation14 Oct 2024 Hongfu Liu, Hengguan Huang, Hao Wang, Xiangming Gu, Ye Wang

Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails.

Blocking

Occluded Human Pose Estimation based on Limb Joint Augmentation

no code implementations13 Oct 2024 Gangtao Han, Chunxiao Song, Song Wang, Hao Wang, Enqing Chen, Guanghui Wang

In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies.

Pose Estimation

BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models

no code implementations13 Oct 2024 Xinyuan Wang, Victor Shea-Jay Huang, Renmiao Chen, Hao Wang, Chengwei Pan, Lei Sha, Minlie Huang

Existing jailbreak strategies mainly focus on maximizing attack success rate (ASR), frequently neglecting other critical factors, including the relevance of the jailbreak response to the query and the level of stealthiness.

Evolutionary Algorithms

Anderson Acceleration in Nonsmooth Problems: Local Convergence via Active Manifold Identification

no code implementations12 Oct 2024 Kexin Li, Luwei Bai, Xiao Wang, Hao Wang

Anderson acceleration is an effective technique for enhancing the efficiency of fixed-point iterations; however, analyzing its convergence in nonsmooth settings presents significant challenges.

Meta-Transfer Learning Empowered Temporal Graph Networks for Cross-City Real Estate Appraisal

no code implementations11 Oct 2024 Weijia Zhang, Jindong Han, Hao liu, Wei Fan, Hao Wang, Hui Xiong

To this end, we propose Meta-Transfer Learning Empowered Temporal Graph Networks (MetaTransfer) to transfer valuable knowledge from multiple data-rich metropolises to the data-scarce city to improve valuation performance.

Meta-Learning Multi-Task Learning

MDAP: A Multi-view Disentangled and Adaptive Preference Learning Framework for Cross-Domain Recommendation

1 code implementation8 Oct 2024 Junxiong Tong, Mingjia Yin, Hao Wang, Qiushi Pan, Defu Lian, Enhong Chen

Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios.

Decoder feature selection +1

Variational Language Concepts for Interpreting Foundation Language Models

1 code implementation4 Oct 2024 Hengyi Wang, Shiwei Tan, Zhiqing Hong, Desheng Zhang, Hao Wang

Foundation Language Models (FLMs) such as BERT and its variants have achieved remarkable success in natural language processing.

An Adaptive Re-evaluation Method for Evolution Strategy under Additive Noise

no code implementations25 Sep 2024 Catalin-Viorel Dinu, Yash J. Patel, Xavier Bonet-Monroig, Hao Wang

Solving for the maximum of the lower bound, we obtain a simple expression of the optimal re-evaluation number.

Asynchronous Fractional Multi-Agent Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing

no code implementations25 Sep 2024 Lyudong Jin, Ming Tang, JiaYu Pan, Meng Zhang, Hao Wang

In the realm of emerging real-time networked applications like cyber-physical systems (CPS), the Age of Information (AoI) has merged as a pivotal metric for evaluating the timeliness.

Deep Reinforcement Learning Edge-computing +2

Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions

no code implementations25 Sep 2024 Kun Zhou, You Zhang, Shengkui Zhao, Hao Wang, Zexu Pan, Dianwen Ng, Chong Zhang, Chongjia Ni, Yukun Ma, Trung Hieu Nguyen, Jia Qi Yip, Bin Ma

Current emotional text-to-speech (TTS) systems face challenges in mimicking a broad spectrum of human emotions due to the inherent complexity of emotions and limitations in emotional speech datasets and models.

Attribute Dimensionality Reduction +5

The signal synchronization function of myelin

no code implementations25 Sep 2024 Zhuonan Yu, Peijun Qin, Ruibing Sun, Sara Khademi, Zhen Xu, Qinchao Sun, Yanlong Tai, Bing Song, Tianruo Guo, Hao Wang

Conventionally, myelin is considered as an insulating layer to achieve saltatory conduction for the enhancement of the neural signal speed, which serves as the foundation of neuroscience.

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

1 code implementation21 Sep 2024 Yuqing Huang, Rongyang Zhang, Xuesong He, Xuyang Zhi, Hao Wang, Xin Li, Feiyang Xu, Deguang Liu, Huadong Liang, Yi Li, Jian Cui, Zimu Liu, Shijin Wang, Guoping Hu, Guiquan Liu, Qi Liu, Defu Lian, Enhong Chen

To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks.

Few-Shot Learning Instruction Following

EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models

no code implementations20 Sep 2024 Yuyan Chen, Hao Wang, Songzhou Yan, Sijia Liu, Yueze Li, Yi Zhao, Yanghua Xiao

The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition.

Emotional Intelligence Emotion Recognition +2

D2Vformer: A Flexible Time Series Prediction Model Based on Time Position Embedding

no code implementations17 Sep 2024 Xiaobao Song, Hao Wang, Liwei Deng, Yuxin He, Wenming Cao, Chi-Sing Leungc

Time position embeddings capture the positional information of time steps, often serving as auxiliary inputs to enhance the predictive capabilities of time series models.

Position Time Series +1

Multi-Weather Image Restoration via Histogram-Based Transformer Feature Enhancement

no code implementations10 Sep 2024 Yang Wen, Anyu Lai, Bo Qian, Hao Wang, Wuzhen Shi, Wenming Cao

In this paper, we propose a Task Sequence Generator module that, in conjunction with the Task Intra-patch Block, effectively extracts task-specific features embedded in degraded images.

Autonomous Driving Image Restoration

Cooptimizing Safety and Performance with a Control-Constrained Formulation

1 code implementation10 Sep 2024 Hao Wang, Adityaya Dhande, Somil Bansal

In this work, we use the general framework of constrained optimal control, but given the safety state constraint, we convert it into an equivalent control constraint, resulting in a state and time-dependent control-constrained optimal control problem.

Multiple weather images restoration using the task transformer and adaptive mixup strategy

no code implementations5 Sep 2024 Yang Wen, Anyu Lai, Bo Qian, Hao Wang, Wuzhen Shi, Wenming Cao

In this paper, we introduce a novel multi-task severe weather removal model that can effectively handle complex weather conditions in an adaptive manner.

Autonomous Driving Rain Removal +1

Zeroshot Listwise Learning to Rank Algorithm for Recommendation

no code implementations5 Sep 2024 Hao Wang

Learning to rank is a rare technology compared with other techniques such as deep neural networks.

Information Retrieval Learning-To-Rank +1