Publications (321)
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
Tong Xiao, Xin Xu, Zhenya Huang +4
Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently…
Balanced One-shot Neural Architecture Optimization
Renqian Luo, Tao Qin, Enhong Chen
The ability to rank candidate architectures is the key to the performance of neural architecture search~(NAS). One-shot NAS is proposed to reduce the expense but shows inferior per…
Finding Theme Communities from Database Networks
Lingyang Chu, Zhefeng Wang, Jian Pei +3
Given a database network where each vertex is associated with a transaction database, we are interested in finding theme communities. Here, a theme community is a cohesive subgraph…
Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach
Chuan Qin, Hengshu Zhu, Tong Xu +4
The wide spread use of online recruitment services has led to information explosion in the job market. As a result, the recruiters have to seek the intelligent ways for Person Job…
Fine-Grained Zero-Shot Composed Image Retrieval with Complementary Visual-Semantic Integration
Yongcong Ye, Kai Zhang, Yanghai Zhang +3
Zero-shot composed image retrieval (ZS-CIR) is a rapidly growing area with significant practical applications, allowing users to retrieve a target image by providing a reference im…
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
Fengxian Dong, Zhi Zheng, Xiao Han +5
Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. Traditiona…
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Yubo Huang, Hailong Guo, Fangtai Wu +9
Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon dr…
Variance Reduced Local SGD with Lower Communication Complexity
Xianfeng Liang, Shuheng Shen, Jingchang Liu +3
To accelerate the training of machine learning models, distributed stochastic gradient descent (SGD) and its variants have been widely adopted, which apply multiple workers in para…
Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
Shuochen Liu, Pengfei Luo, Chao Zhang +6
Aiming to identify precise evidence sources from visual documents, visual evidence attribution for visual document retrieval-augmented generation (VD-RAG) ensures reliable and veri…
Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning
Liyang He, Yuren Zhang, Rui Li +3
Deep supervised hashing is essential for efficient storage and search in large-scale image retrieval. Traditional deep supervised hashing models generate single-length hash codes,…
SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation
Rui Zhou, Bo Chen, Qinglin Jia +5
As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate…
Improving Time Series Forecasting via Instance-aware Post-hoc Revision
Zhiding Liu, Mingyue Cheng, Guanhao Zhao +3
Time series forecasting plays a vital role in various real-world applications and has attracted significant attention in recent decades. While recent methods have achieved remarkab…
Dataset Regeneration for Sequential Recommendation
Mingjia Yin, Hao Wang, Wei Guo +5
The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of users. Significant efforts have been…
Model Stealing Attack against Recommender System
Zhihao Zhu, Rui Fan, Chenwang Wu +3
Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as…
Chinese Poetry Generation with Planning based Neural Network
Zhe Wang, Wei He, Hua Wu +4
Chinese poetry generation is a very challenging task in natural language processing. In this paper, we propose a novel two-stage poetry generating method which first plans the sub-…
Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting
Zipeng Gao, Zhi Zheng, Qingrong Xia +5
Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically…
What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
Yuze Zhao, Junpeng Fang, Lu Yu +6
Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the claim that code improves rea…
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
Liyang He, Zhenya Huang, Jiayu Liu +4
Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent…
Deep Technology Tracing for High-tech Companies
Han Wu, Kun Zhang, Guangyi Lv +5
Technological change and innovation are vitally important, especially for high-tech companies. However, factors influencing their future research and development (R&D) trends are b…
A Linear Circuit Model For Social Influence Analysis
Biao Xiang, Enhong Chen, Qi Liu +1
Understanding the behaviors of information propagation is essential for the effective exploitation of social influence in social networks. However, few existing influence models ar…
Large Language Model based Long-tail Query Rewriting in Taobao Search
Wenjun Peng, Guiyang Li, Yue Jiang +6
In the realm of e-commerce search, the significance of semantic matching cannot be overstated, as it directly impacts both user experience and company revenue. Along this line, que…
QuesNet: A Unified Representation for Heterogeneous Test Questions
Yu Yin, Qi Liu, Zhenya Huang +4
Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many s…
Modeling Earth-Scale Human-Like Societies with One Billion Agents
Haoxiang Guan, Jiyan He, Liyang Fan +10
Understanding the dynamic evolution of complex social phenomena requires both high-fidelity modeling of human behavior and large-scale simulations. Traditional agent-based models (…
GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data
Cheng He, Xu Huang, Gangwei Jiang +7
Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General T…
ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments
Tingyue Pan, Mingyue Cheng, Daoyu Wang +4
Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literature exploration. H…
DIET: Learning to Distill Dataset Continually for Recommender Systems
Jiaqing Zhang, Hao Wang, Mingjia Yin +6
Modern deep recommender models are trained under a continual learning paradigm, relying on massive and continuously growing streaming behavioral logs. In large-scale platforms, ret…
Cooperative Retriever and Ranker in Deep Recommenders
Xu Huang, Defu Lian, Jin Chen +3
Deep recommender systems (DRS) are intensively applied in modern web services. To deal with the massive web contents, DRS employs a two-stage workflow: retrieval and ranking, to ge…
Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems
Binbin Jin, Enhong Chen, Hongke Zhao +4
In the area of community question answering (CQA), answer selection and answer ranking are two tasks which are applied to help users quickly access valuable answers. Existing solut…
MDAP: A Multi-view Disentangled and Adaptive Preference Learning Framework for Cross-Domain Recommendation
Junxiong Tong, Mingjia Yin, Hao Wang +3
Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios. However, CDR faces challenges s…
BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature
Jiaxian Yan, Jintao Zhu, Yuhang Yang +8
Protein-ligand bioactivity data published in the literature are essential for drug discovery, yet manual curation struggles to keep pace with rapidly growing literature. Automated…
Performance Enhancement Factors of ERP Projects in a Telecom Public Sector Organization of Pakistan : An Exploratory Study
Shafqat Ali Shad, Enhong Chen, Faisal Malik Faisal Azeem
Public sector organizations are treated in a different manner, as Information technology/information system has become necessity in a highly competitive environment. Importance of…
Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
Derong Xu, Ziheng Zhang, Zhihong Zhu +9
Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has p…
Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement
Yuxuan Gu, Yi Jin, Ben Wang +6
In this work, we observe that the generators, which are pre-trained on massive natural images, inherently hold the promising potential for superior low-light image enhancement agai…
A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation
Luankang Zhang, Hao Wang, Suojuan Zhang +5
Cross-domain recommendation (CDR), aiming to extract and transfer knowledge across domains, has attracted wide attention for its efficacy in addressing data sparsity and cold-start…
ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
Zhongkai Hao, Chengqiang Lu, Zheyuan Hu +5
Molecular property prediction (e.g., energy) is an essential problem in chemistry and biology. Unfortunately, many supervised learning methods usually suffer from the problem of sc…
Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models
Zhixiang Wei, Xiaoxiao Ma, Ruishen Yan +5
Vision Foundation Models(VFMs) have achieved remarkable success in various computer vision tasks. However, their application to semantic segmentation is hindered by two significant…
Tracking Top-K Influential Vertices in Dynamic Networks
Yu Yang, Zhefeng Wang, Tianyuan Jin +2
Influence propagation in networks has enjoyed fruitful applications and has been extensively studied in literature. However, only very limited preliminary studies tackled the chall…
Boosting Factorization Machines via Saliency-Guided Mixup
Chenwang Wu, Defu Lian, Yong Ge +3
Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive fea…
Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective
Likang Wu, Zhi Li, Hongke Zhao +2
In the online innovation market, the fund-raising performance of the start-up project is a concerning issue for creators, investors and platforms. Unfortunately, existing studies a…
EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction
Qi Liu, Zhenya Huang, Yu Yin +4
For offering proactive services to students in intelligent education, one of the fundamental tasks is predicting their performance (e.g., scores) on future exercises, where it is n…
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
Jie Wang, Hanzhu Chen, Qitan Lv +7
Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity…
A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
Cheng He, Xijie Liang, Zengrong Zheng +6
Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often e…
Pre-trained Language Model and Knowledge Distillation for Lightweight Sequential Recommendation
Li Li, Mingyue Cheng, Zhiding Liu +3
Sequential recommendation models user interests based on historical behaviors to provide personalized recommendation. Previous sequential recommendation algorithms primarily employ…
KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification
Likang Wu, Junji Jiang, Hongke Zhao +4
Recently, Zero-Shot Node Classification (ZNC) has been an emerging and crucial task in graph data analysis. This task aims to predict nodes from unseen classes which are unobserved…
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
Shuochen Liu, Junyi Zhu, Long Shu +11
Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. Existing evaluations of this capability typically interle…
Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks
Yichao Du, Zhirui Zhang, Linan Yue +5
To protect privacy and meet legal regulations, federated learning (FL) has gained significant attention for training speech-to-text (S2T) systems, including automatic speech recogn…
Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce
Zhiding Liu, Ben Chen, Mingyue Cheng +6
Search-based recommendation is one of the most critical application scenarios in e-commerce platforms. Users' complex search contexts--such as spatiotemporal factors, historical in…
Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness
Dazhong Shen, Chuan Qin, Chao Wang +3
As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. However, when t…
Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions
Zaiyi Chen, Zhuoning Yuan, Jinfeng Yi +3
Although stochastic gradient descent (SGD) method and its variants (e.g., stochastic momentum methods, AdaGrad) are the choice of algorithms for solving non-convex problems (especi…
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
Derong Xu, Shuochen Liu, Pengfei Luo +8
Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interacti…
Activity Maximization by Effective Information Diffusion in Social Networks
Zhefeng Wang, Yu Yang, Jian Pei +1
In a social network, even about the same information the excitements between different pairs of users are different. If you want to spread a piece of new information and maximize t…
Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations
Likang Wu, Zhaopeng Qiu, Zhi Zheng +2
Large Language Models (LLMs) have revolutionized natural language processing tasks, demonstrating their exceptional capabilities in various domains. However, their potential for be…
Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification
Yaoyang Luo, Zhi Zheng, Ziwei Zhao +5
Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.…
A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference
Chao Zhang, Shiwei Wu, Sirui Zhao +2
Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant introduces a groundbreaking scenario. In this scenario, through learning instructional videos, AI…
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
Liyang He, Chenglong Liu, Rui Li +4
Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual la…
FuXi-: Scaling Recommendation Model with Feature Interaction Enhanced Transformer
Yufei Ye, Wei Guo, Jin Yao Chin +8
Inspired by scaling laws and large language models, research on large-scale recommendation models has gained significant attention. Recent advancements have shown that expanding se…
Enhancing CTR Prediction with De-correlated Expert Networks
Jiancheng Wang, Mingjia Yin, Hao Wang +1
Modeling feature interactions is essential for accurate click-through rate (CTR) prediction in advertising systems. Recent studies have adopted the Mixture-of-Experts (MoE) approac…
Bridging User Dynamics: Transforming Sequential Recommendations with Schrödinger Bridge and Diffusion Models
Wenjia Xie, Rui Zhou, Hao Wang +2
Sequential recommendation has attracted increasing attention due to its ability to accurately capture the dynamic changes in user interests. We have noticed that generative models,…
Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis
Kai Zhang, Kun Zhang, Mengdi Zhang +4
Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in the given sentence. While pre-trained language models such as BERT have achieved gre…
WESE: Weak Exploration to Strong Exploitation for LLM Agents
Xu Huang, Weiwen Liu, Xiaolong Chen +5
Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning…
Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation
Junliang Guo, Xu Tan, Linli Xu +3
Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup b…
Analytical and Empirical Study of Herding Effects in Recommendation Systems
Hong Xie, Mingze Zhong, Defu Lian +2
Online rating systems are often used in numerous web or mobile applications, e.g., Amazon and TripAdvisor, to assess the ground-truth quality of products. Due to herding effects, t…
TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation
Jiaqing Zhang, Mingjia Yin, Hao Wang +5
In the era of data-centric AI, the focus of recommender systems has shifted from model-centric innovations to data-centric approaches. The success of modern AI models is built on l…
Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
Kai Cheng, Hao Wang, Wei Guo +4
Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked l…
Empowering Sequential Recommendation from Collaborative Signals and Semantic Relatedness
Mingyue Cheng, Hao Zhang, Qi Liu +6
Sequential recommender systems (SRS) could capture dynamic user preferences by modeling historical behaviors ordered in time. Despite effectiveness, focusing only on the \textit{co…
Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
Haocheng Yu, Yaxiong Wu, Hao Wang +6
Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendat…
Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction
Xiang Xu, Hao Wang, Wei Guo +6
Click-through Rate (CTR) prediction is crucial for online personalization platforms. Recent advancements have shown that modeling rich user behaviors can significantly improve the…
Large Language Models for Generative Information Extraction: A Survey
Derong Xu, Wei Chen, Wenjun Peng +7
Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable c…
ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
Yuqing Huang, Rongyang Zhang, Xuesong He +15
There is a growing interest in the role that LLMs play in chemistry which lead to an increased focus on the development of LLMs benchmarks tailored to chemical domains to assess th…
A Comprehensive Survey on Cross-Domain Recommendation: Taxonomy, Progress, and Prospects
Hao Zhang, Mingyue Cheng, Qi Liu +5
Recommender systems (RS) have become crucial tools for information filtering in various real world scenarios. And cross domain recommendation (CDR) has been widely explored in rece…
Survey of Computerized Adaptive Testing: A Machine Learning Perspective
Yan Zhuang, Qi Liu, Haoyang Bi +12
Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual perfo…
MER-CLIP: AU-Guided Vision-Language Alignment for Micro-Expression Recognition
Shifeng Liu, Xinglong Mao, Sirui Zhao +3
As a critical psychological stress response, micro-expressions (MEs) are fleeting and subtle facial movements revealing genuine emotions. Automatic ME recognition (MER) holds valua…
A DeepLearning Framework for Dynamic Estimation of Origin-Destination Sequence
Zheli Xiong, Defu Lian, Enhong Chen +2
OD matrix estimation is a critical problem in the transportation domain. The principle method uses the traffic sensor measured information such as traffic counts to estimate the tr…
A Machine Learning-enhanced Robust P-Phase Picker for Real-time Seismic Monitoring
Dazhong Shen, Qi Zhang, Tong Xu +7
Identifying the arrival times of seismic P-phases plays a significant role in real-time seismic monitoring, which provides critical guidance for emergency response activities. Whil…
DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing
Xinjie Sun, Kai Zhang, Qi Liu +4
Knowledge Tracing (KT) predicts future performance by modeling students' historical interactions, and understanding students' affective states can enhance the effectiveness of KT,…
VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction
Dan Li, Yang Yang, Hongyin Tang +4
With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching. Howev…
Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
Yuze Zhao, Tianyun Ji, Wenjun Feng +6
The reasoning abilities are one of the most enigmatic and captivating aspects of large language models (LLMs). Numerous studies are dedicated to exploring and expanding the boundar…
Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
Lin Chen, Huaian Chen, Zhixiang Wei +4
Adversarial learning has achieved remarkable performances for unsupervised domain adaptation (UDA). Existing adversarial UDA methods typically adopt an additional discriminator to…
SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
Kai Zhang, Hao Qian, Qi Liu +4
Recent studies in recommender systems have managed to achieve significantly improved performance by leveraging reviews for rating prediction. However, despite being extensively stu…
R-Net: Relation of Relation Learning Network for Sentence Semantic Matching
Kun Zhang, Le Wu, Guangyi Lv +3
Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recentl…
Long-term Joint Scheduling for Urban Traffic
Xianfeng Liang, Likang Wu, Joya Chen +7
Recently, the traffic congestion in modern cities has become a growing worry for the residents. As presented in Baidu traffic report, the commuting stress index has reached surpris…
Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding
Derong Xu, Ziheng Zhang, Zhihong Zhu +7
The impressive capabilities of large language models (LLMs) have attracted extensive interests of applying LLMs to medical field. However, the complex nature of clinical environmen…
One Person, One Model--Learning Compound Router for Sequential Recommendation
Zhiding Liu, Mingyue Cheng, Zhi Li +2
Deep learning has brought significant breakthroughs in sequential recommendation (SR) for capturing dynamic user interests. A series of recent research revealed that models with mo…
Mind2Report: A Cognitive Deep Research Agent for Expert-Level Commercial Report Synthesis
Mingyue Cheng, Daoyu Wang, Qi Liu +7
Synthesizing informative commercial reports from massive and noisy web sources is critical for high-stakes business decisions. Although current deep research agents achieve notable…
Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
Haoyu Tang, Ye Liu, Xi Zhao +5
Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking s…
Interactive Graph Convolutional Filtering
Jin Zhang, Defu Lian, Hong Xie +2
Interactive Recommender Systems (IRS) have been increasingly used in various domains, including personalized article recommendation, social media, and online advertising. However,…
SocraticPO: Policy Optimization via Interactive Guidance
Zirui Liu, Jie Ouyang, Qi Liu +8
Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization dir…
Communication-Efficient Distributed Learning with Local Immediate Error Compensation
Yifei Cheng, Li Shen, Linli Xu +6
Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, exis…
CeProAgents: A Hierarchical Agents System for Automated Chemical Process Development
Yuhang Yang, Ruikang Li, Jifei Ma +8
The development of chemical processes, a cornerstone of chemical engineering, presents formidable challenges due to its multi-faceted nature, integrating specialized knowledge, con…
Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model
Luankang Zhang, Kenan Song, Yi Quan Lee +7
In recommendation systems, the traditional multi-stage paradigm, which includes retrieval and ranking, often suffers from information loss between stages and diminishes performance…
Beyond Surrogates: A Quantitative Analysis for Inter-Metric Relationships
Yuanhao Pu, Defu Lian, Enhong Chen
The Consistency property between surrogate losses and evaluation metrics has been extensively studied to ensure that minimizing a loss leads to metric optimality. However, the dire…
TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
Mingyue Cheng, Xiaoyu Tao, Zhiding Liu +4
Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate…
Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
Anjie Qiao, Zhen Wang, Chuan Chen +2
Controllable molecular graph generation is essential for material and drug discovery, where generated molecules must satisfy diverse property constraints. While recent advances in…
What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis
Jiayu Liu, Zhenya Huang, Chaokun Wang +3
Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find th…
Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendation
Tingjia Shen, Hao Wang, Jiaqing Zhang +5
Cross-Domain Sequential Recommendation (CDSR) aims to mine and transfer users' sequential preferences across different domains to alleviate the long-standing cold-start issue. Trad…
Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach
Min Hou, Le Wu, Enhong Chen +3
In fashion recommender systems, each product usually consists of multiple semantic attributes (e.g., sleeves, collar, etc). When making cloth decisions, people usually show prefere…
Locating and Mitigating Gender Bias in Large Language Models
Yuchen Cai, Ding Cao, Rongxi Guo +3
Large language models(LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences. However, this process can inadvertently lead to…
RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery
Hongchao Gu, Dexun Li, Kuicai Dong +6
Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the preci…
A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects
Shulan Ruan, Rongwei Wang, Xuchen Shen +8
Multi-sensor fusion perception (MSFP) is a key technology for embodied AI, which can serve a variety of downstream tasks (e.g., 3D object detection and semantic segmentation) and a…
FuXi-β: Towards a Lightweight and Fast Large-Scale Generative Recommendation Model
Yufei Ye, Wei Guo, Hao Wang +7
Scaling laws for autoregressive generative recommenders reveal potential for larger, more versatile systems but mean greater latency and training costs. To accelerate training and…