papers

Publications (148)

eess.SP2022

Waveform Design for Mutual Interference Mitigation in Automotive Radar

Arindam Bose, Bo Tang, Wenjie Huang +2

The mutual interference between similar radar systems can result in reduced radar sensitivity and increased false alarm rates. To address the synchronous and asynchronous interfere…

cs.CL2024

NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism

Miao Li, Ming-Bin Chen, Bo Tang +8

We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. Our c…

cs.NI2025

Online Learning-based Adaptive Beam Switching for 6G Networks: Enhancing Efficiency and Resilience

Seyed Bagher Hashemi Natanzi, Zhicong Zhu, Bo Tang

Adaptive beam switching is essential for mission-critical military and commercial 6G networks but faces major challenges from high carrier frequencies, user mobility, and frequent…

cs.CL2026

PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue

Bo Tang, Jianan Yang, Junyi Zhu +7

Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts: representations are typically…

cs.LG2021

Overcome Anterograde Forgetting with Cycled Memory Networks

Jian Peng, Dingqi Ye, Bo Tang +3

Learning from a sequence of tasks for a lifetime is essential for an agent towards artificial general intelligence. This requires the agent to continuously learn and memorize new k…

stat.ML2016

Kernel-based Generative Learning in Distortion Feature Space

Bo Tang, Paul M. Baggenstoss, Haibo He

This paper presents a novel kernel-based generative classifier which is defined in a distortion subspace using polynomial series expansion, named Kernel-Distortion (KD) classifier.…

cs.CL2025

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

Jihao Zhao, Zhiyuan Ji, Zhaoxin Fan +5

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline.…

cs.NI2026

SliceFed: Federated Constrained Multi-Agent DRL for Dynamic Spectrum Slicing in 6G

Hossein Mohammadi, Seyed Bagher Hashemi Natanzi, Ramak Nassiri +3

Dynamic spectrum slicing is a critical enabler for 6G Radio Access Networks (RANs), allowing the coexistence of heterogeneous services. However, optimizing resource allocation in d…

cs.CR2025

A Secure Communication Protocol for Remote Keyless Entry System with Adaptive Adjustment of Transmission Parameters

Jingjing Guo, Bo Tang, Jiayuan Xu +3

Remote Keyless Entry (RKE) systems have become a standard feature in modern vehicles, yet their unidirectional fixed-frequency radio communication renders them vulnerable to replay…

astro-ph.CO2014

Constraints on the CDM model with redshift tomography

Rong-Gen Cai, Zong-Kuan Guo, Bo Tang

Recently released Planck data favor a lower value of the Hubble constant and a higher value of the fraction matter density in the standard CDM model, which are discrepant with…

math.OC2023

Multi-Task Predict-then-Optimize

Bo Tang, Elias B. Khalil

The predict-then-optimize framework arises in a wide variety of applications where the unknown cost coefficients of an optimization problem are first predicted based on contextual…

cs.CL2026

Metis: Memory Foundation Model

Zeyu Zhang, Ziliang Guo, Yihang Sun +14

The paper presents Metis, a memory foundation model that embeds a persistent, dynamically updated memory state within the model backbone, allowing it to store and retrieve informat…

#memory-augmented models#foundation models#native memory#multimodal learning
cs.HC2025

Data Insights as Data: Quick Overview and Exploration of Automated Data Insights

Shangxuan Wu, Wendi Luan, Yong Wang +3

Automated data insight mining and visualization have been widely used in various business intelligence applications (e.g., market analysis and product promotion). However, automate…

cs.CL2026

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Hongyi Liu, Haoyan Yang, Tao Jiang +4

Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact f…

cs.LG2024

DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning

Xuemin Hu, Shen Li, Yingfen Xu +2

Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent ca…

cs.CL2025

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models

Yang Zhang, Yu Yu, Bo Tang +8

With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However,…

cs.LG2021

Interpretable performance analysis towards offline reinforcement learning: A dataset perspective

Chenyang Xi, Bo Tang, Jiajun Shen +3

Offline reinforcement learning (RL) has increasingly become the focus of the artificial intelligent research due to its wide real-world applications where the collection of data ma…

cs.SI2024

Efficient and Effective Algorithms for A Family of Influence Maximization Problems with A Matroid Constraint

Yiqian Huang, Shiqi Zhang, Laks V. S. Lakshmanan +3

Influence maximization (IM) is a classic problem that aims to identify a small group of critical individuals, known as seeds, who can influence the largest number of users in a soc…

cs.MA2026

MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems

Wenjun Xiong, Yijin Zhou, Jiaqian Wang +6

LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gi…

cs.DB2025

Privacy-Enhanced Database Synthesis for Benchmark Publishing (Technical Report)

Yunqing Ge, Jianbin Qin, Shuyuan Zheng +7

Benchmarking is crucial for evaluating a DBMS, yet existing benchmarks often fail to reflect the varied nature of user workloads. As a result, there is increasing momentum toward c…

cs.AI2026

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

Junwei Liao, Haoting Shi, Ruiwen Zhou +9

Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation withou…

cs.LG2022

DGI: Easy and Efficient Inference for GNNs

Peiqi Yin, Xiao Yan, Jinjing Zhou +5

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopte…

cs.LG2022

FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation

Xingyu Li, Zhe Qu, Bo Tang +1

Federated Learning (FL) is a decentralized machine learning architecture, which leverages a large number of remote devices to learn a joint model with distributed training data. Ho…

eess.SP2025

Dual-Function Beamforming Design For Multi-Target Localization and Reliable Communications

Bo Tang, Da Li, Wenjun Wu +3

This paper investigates the transmit beamforming design for multiple-input multiple-output systems to support both multi-target localization and multi-user communications. To enhan…

cs.CL2024

Grimoire is All You Need for Enhancing Large Language Models

Ding Chen, Shichao Song, Qingchen Yu +4

In-context Learning (ICL) is one of the key methods for enhancing the performance of large language models on specific tasks by providing a set of few-shot examples. However, the I…

cs.CL2025

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

Xun Liang, Hanyu Wang, Huayi Lai +7

Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottlene…

cs.LG2024

MGSER-SAM: Memory-Guided Soft Experience Replay with Sharpness-Aware Optimization for Enhanced Continual Learning

Xingyu Li, Bo Tang

Deep neural networks suffer from the catastrophic forgetting problem in the field of continual learning (CL). To address this challenge, we propose MGSER-SAM, a novel memory replay…

cs.LG2024

HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning

Hao Wang, Bo Tang, Chi Harold Liu +7

Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day. The bidding strategy hand…

cs.CR2024

Ruledger: Ensuring Execution Integrity in Trigger-Action IoT Platforms

Jingwen Fan, Yi He, Bo Tang +2

Smart home IoT systems utilize trigger-action platforms, e.g., IFTTT, to manage devices from various vendors. However, they may be abused by triggering malicious rule execution wit…

cs.CR2026

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

Seyed Bagher Hashemi Natanzi, Bo Tang

Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environments, robotic systems, securi…

cs.DB2020

RCELF: A Residual-based Approach for Influence Maximization Problem

Xinxun Zeng, Shiqi Zhang, Bo Tang

Influence Maximization Problem (IMP) is selecting a seed set of nodes in the social network to spread the influence as widely as possible. It has many applications in multiple doma…

cs.GT2015

Well-Supported versus Approximate Nash Equilibria: Query Complexity of Large Games

Xi Chen, Yu Cheng, Bo Tang

We study the randomized query complexity of approximate Nash equilibria (ANE) in large games. We prove that, for some constant , any randomized oracle algorithm that computes…

cs.NI2026

FairShare: Auditable Geographic Fairness for Multi-Operator LEO Spectrum Sharing

Seyed Bagher Hashemi Natanzi, Hossein Mohammadi, Vuk Marojevic +1

Dynamic spectrum sharing (DSS) among multi-operator low Earth orbit (LEO) mega-constellations is essential for coexistence, yet prevailing policies focus almost exclusively on inte…

cs.CL2024

Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning

Xun Liang, Simin Niu, Zhiyu li +7

Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs). Nevertheless, constructing and validating…

cs.CL2024

Xinyu: An Efficient LLM-based System for Commentary Generation

Yiquan Wu, Bo Tang, Chenyang Xi +13

Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skille…

cs.IR2023

Multi-domain Recommendation with Embedding Disentangling and Domain Alignment

Wentao Ning, Xiao Yan, Weiwen Liu +3

Multi-domain recommendation (MDR) aims to provide recommendations for different domains (e.g., types of products) with overlapping users/items and is common for platforms such as A…

cs.DS2023

Efficient Approximation Algorithms for Spanning Centrality

Shiqi Zhang, Renchi Yang, Jing Tang +2

Given a graph , the spanning centrality (SC) of an edge measures the importance of for to be connected. In practice, SC has seen extensive applic…

math.OC2020

Learning Discontinuous Piecewise Affine Fitting Functions using Mixed Integer Programming for Segmentation and Denoising

Ruobing Shen, Bo Tang, Leo Liberti +2

Piecewise affine functions are widely used to approximate nonlinear and discontinuous functions. However, most, if not all existing models only deal with fitting continuous functio…

cs.CL2024

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy

Yu Zhu, Chuxiong Sun, Wenfei Yang +8

Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values. However, existing RLHF methods require…

cs.SI2023

Effective and Efficient PageRank-based Positioning for Graph Visualization

Shiqi Zhang, Renchi Yang, Xiaokui Xiao +2

Graph visualization is a vital component in many real-world applications (e.g., social network analysis, web mining, and bioinformatics) that enables users to unearth crucial insig…

cs.AI2026

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…

cs.DB2025

CheetahGIS: Architecting a Scalable and Efficient Streaming Spatial Query Processing System

Jiaping Cao, Ting Sun, Man Lung Yiu +2

Spatial data analytics systems are widely studied in both the academia and industry. However, existing systems are limited when handling a large number of moving objects and real t…

stat.ML2016

Toward Optimal Feature Selection in Naive Bayes for Text Categorization

Bo Tang, Steven Kay, Haibo He

Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel a…

cs.CL2026

Transformers are Stateless Differentiable Neural Computers

Bo Tang, Weiwei Xie

Differentiable Neural Computers (DNCs) were introduced as recurrent architectures equipped with an addressable external memory supporting differentiable read and write operations.…

cs.CL2026

Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems

Jihao Zhao, Ding Chen, Zhaoxin Fan +5

Existing long-term personalized dialogue systems struggle to reconcile unbounded interaction streams with finite context constraints, often succumbing to memory noise accumulation,…

cs.HC2016

Probabilistic Human Mobility Model in Indoor Environment

Bo Tang, Chao Jiang, Haibo He +1

Understanding human mobility is important for the development of intelligent mobile service robots as it can provide prior knowledge and predictions of human distribution for robot…

cs.LG2023

G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima

Xingyu Li, Bo Tang

Deep neural networks (DNNs) have demonstrated promising results in various complex tasks. However, current DNNs encounter challenges with over-parameterization, especially when the…

cs.LG2022

Generalized Federated Learning via Sharpness Aware Minimization

Zhe Qu, Xingyu Li, Rui Duan +3

Federated Learning (FL) is a promising framework for performing privacy-preserving, distributed learning with a set of clients. However, the data distribution among clients often e…

eess.SP2022

A Probabilistic Model-Based Robust Waveform Design for MIMO Radar Detection

Xuyang Wang, Bo Tang, Ming Zhang

This paper addresses robust waveform design for multiple-input-multiple-output (MIMO) radar detection. A probabilistic model is proposed to describe the target uncertainty. Conside…

cs.CV2022

Connectivity-constrained Interactive Panoptic Segmentation

Ruobing Shen, Bo Tang, Andrea Lodi +2

We address interactive panoptic annotation, where one segment all object and stuff regions in an image. We investigate two graph-based segmentation algorithms that both enforce con…

cs.CL2025

Text2Mem: A Unified Memory Operation Language for Memory Operating System

Yi Wang, Lihai Yang, Boyu Chen +6

Large language model agents increasingly depend on memory to sustain long horizon interaction, but existing frameworks remain limited. Most expose only a few basic primitives such…

cs.LG2025

PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions

Renjie Liu, Haitian Jiang, Xiao Yan +2

GraphRAG enhances large language models (LLMs) to generate quality answers for user questions by retrieving related facts from external knowledge graphs. However, current GraphRAG…

cs.CL2026

From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents

Bo Tang, Yang Zhang, Guomian Zhuang +8

Existing memory systems for long-horizon LLM agents often retrieve prior traces as passive context rather than converting them into executable capabilities. In this paper, we propo…

cs.LG2024

Off-Policy Primal-Dual Safe Reinforcement Learning

Zifan Wu, Bo Tang, Qian Lin +5

Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly s…

hep-lat2026

LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research

Haofei Gao, Tingjia Miao, Wenkai Jin +12

LQCDMaster is an AI-driven scientific computing agent that translates natural‑language lattice QCD research tasks into fully executable PyQUDA workflows, automating code generation…

#lattice qcd#scientific computing#AI agents#code generation
cs.CL2024

Attention Heads of Large Language Models: A Survey

Zifan Zheng, Yezhaohui Wang, Yuxin Huang +5

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become…

cs.GT2015

Tight Bounds for the Price of Anarchy of Simultaneous First Price Auctions

George Christodoulou, Annamária Kovács, Alkmini Sgouritsa +1

We study the Price of Anarchy of simultaneous first-price auctions for buyers with submodular and subadditive valuations. The current best upper bounds for the Bayesian Price of An…

physics.optics2024

A programmable topological photonic chip

Tianxiang Dai, Anqi Ma, Jun Mao +12

Controlling topological phases of light has allowed experimental observations of abundant topological phenomena and development of robust photonic devices. The prospect of more sop…

cs.IR2024

Debiasing Recommendation with Personal Popularity

Wentao Ning, Reynold Cheng, Xiao Yan +4

Global popularity (GP) bias is the phenomenon that popular items are recommended much more frequently than they should be, which goes against the goal of providing personalized rec…

cs.IT2023

Relative Entropy-Based Waveform Optimization for Rician Target Detection with Dual-Function Radar Communication Systems

Xuyang Wang, Bo Tang, Wenjun Wu +1

In this paper, we consider waveform design for dualfunction radar-communication systems based on multiple-inputmultiple-out arrays. To achieve better Rician target detection perfor…

eess.SP2023

Constant-Modulus Waveform Design for Dual-Function Radar-Communication Systems in the Presence of Clutter

Wenjun Wu, Bo Tang, Xuyang Wang

We investigate the constant-modulus (CM) waveform design for dual-function radar communication systems in the presence of clutter.To minimize the interference power and enhance the…

cs.SI2022

Measuring Friendship Closeness: A Perspective of Social Identity Theory

Shiqi Zhang, Jiachen Sun, Wenqing Lin +2

Measuring the closeness of friendships is an important problem that finds numerous applications in practice. For example, online gaming platforms often host friendship-enhancing ev…

cs.LG2024

CaVE: A Cone-Aligned Approach for Fast Predict-then-optimize with Binary Linear Programs

Bo Tang, Elias B. Khalil

The end-to-end predict-then-optimize framework, also known as decision-focused learning, has gained popularity for its ability to integrate optimization into the training procedure…

cs.RO2023

How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence

Xuemin Hu, Shen Li, Tingyu Huang +3

Safety and cost are two important concerns for the development of autonomous driving technologies. From the academic research to commercial applications of autonomous driving vehic…

cs.CV2025

CapeNext: Rethinking and Refining Dynamic Support Information for Category-Agnostic Pose Estimation

Yu Zhu, Dan Zeng, Shuiwang Li +3

Recent research in Category-Agnostic Pose Estimation (CAPE) has adopted fixed textual keypoint description as semantic prior for two-stage pose matching frameworks. While this para…

cs.CL2024

: Language Modeling with Explicit Memory

Hongkang Yang, Zehao Lin, Wenjin Wang +13

The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory h…

cs.GT2015

On the Efficiency of the Proportional Allocation Mechanism for Divisible Resources

George Christodoulou, Alkmini Sgouritsa, Bo Tang

We study the efficiency of the proportional allocation mechanism, that is widely used to allocate divisible resources. Each agent submits a bid for each divisible resource and rece…

cs.DB2026

Efficient and Effective In-place Graph-based Vector Index Updates

Haotian Liu, Yujun He, Bo Tang

In the era of Large Language Models (LLMs), efficient vector updates are critical for capturing real-time information from rapidly evolving data. However, it is not trivial to proc…

cs.DB2022

Manu: A Cloud Native Vector Database Management System

Rentong Guo, Xiaofan Luan, Long Xiang +12

With the development of learning-based embedding models, embedding vectors are widely used for analyzing and searching unstructured data. As vector collections exceed billion-scale…

cs.CL2025

Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception

Jihao Zhao, Zhiyuan Ji, Yuchen Feng +5

While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucia…

cs.LG2025

DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training

Renjie Liu, Yichuan Wang, Xiao Yan +5

Graph neural networks (GNNs) are machine learning models specialized for graph data and widely used in many applications. To train GNNs on large graphs that exceed CPU memory, seve…

astro-ph.CO2013

Constraining the Anisotropic Expansion of Universe

Rong-Gen Cai, Yin-Zhe Ma, Bo Tang +1

We study the possibly existing anisotropy in the accelerating expansion universe with the Union2 Type Ia supernovae data and Gamma-ray burst data. We construct a direction-dependen…

quant-ph2021

A generalised multipath delayed-choice experiment on a large-scale quantum nanophotonic chip

Xiaojiong Chen, Yaohao Deng, Shuheng Liu +15

Famous double-slit or double-path experiments, implemented in a Young's or Mach-Zehnder interferometer, have confirmed the dual nature of quantum matter, When a stream of photons,…

cs.SI2023

Capacity Constrained Influence Maximization in Social Networks

Shiqi Zhang, Yiqian Huang, Jiachen Sun +3

Influence maximization (IM) aims to identify a small number of influential individuals to maximize the information spread and finds applications in various fields. It was first int…

cs.LG2025

Adversarial Preference Learning for Robust LLM Alignment

Yuanfu Wang, Pengyu Wang, Chenyang Xi +13

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to th…

cs.CV2025

Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles

Zifu Wang, Junyi Zhu, Bo Tang +4

The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-on…

physics.ins-det2025

Design, fabrication and initial test of a novel 3D-Trench sensor utilizing 8-inch CMOS compatible technology

Manwen Liu, Huimin Ji, Wenzheng Cheng +10

The 3D silicon sensor has demonstrated excellent performances (signal collection, detection efficiency, power consumption, etc.) comparable or even better with respect to the tradi…

cs.AI2025

AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference

Yangshen Deng, Zhengxin You, Long Xiang +13

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specificall…

cs.SE2026

Maximizing Parallel Execution of Series-Parallel Task Graphs for Safety-Critical Embedded Control

Jinghao Sun, Zhenchu Hu, Ye Ma +3

Safety-critical embedded control programs must complete each control cycle within a bounded period. Sequential execution on conventional processors can become a bottleneck when the…

math.OC2026

Learned Pairwise Deep Dual-Optimal Inequalities for Stabilizing Column Generation

Zhengzhong Ricky You, Bo Tang, Haoran Liu +1

The paper proposes a learning framework called L-PDDOIs that predicts pairwise orderings of dual variables to create deep dual-optimal inequalities, which stabilize column generati…

#column generation#vehicle routing#dual optimal inequalities#machine learning
cs.CL2024

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs

Xun Liang, Hanyu Wang, Shichao Song +5

Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LL…

cs.LG2025

Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees

Bo Tang, Elias B. Khalil, Ján Drgoňa

Mixed-integer nonlinear programs (MINLPs) arise in domains such as energy systems, process engineering, and transportation, and are notoriously difficult to solve at scale due to t…

cs.LG2024

Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving

Xuemin Hu, Pan Chen, Yijun Wen +2

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of in…

cs.CL2025

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning

Qingchen Yu, Zifan Zheng, Ding Chen +4

The evaluation of large language models (LLMs) has traditionally relied on static benchmarks, a paradigm that poses two major limitations: (1) predefined test sets lack adaptabilit…

stat.ML2016

FSMJ: Feature Selection with Maximum Jensen-Shannon Divergence for Text Categorization

Bo Tang, Haibo He

In this paper, we present a new wrapper feature selection approach based on Jensen-Shannon (JS) divergence, termed feature selection with maximum JS-divergence (FSMJ), for text cat…

stat.ML2016

EEF: Exponentially Embedded Families with Class-Specific Features for Classification

Bo Tang, Steven Kay, Haibo He +1

In this letter, we present a novel exponentially embedded families (EEF) based classification method, in which the probability density function (PDF) on raw data is estimated from…

cs.DC2022

On the Convergence of Multi-Server Federated Learning with Overlapping Area

Zhe Qu, Xingyu Li, Jie Xu +3

Multi-server Federated learning (FL) has been considered as a promising solution to address the limited communication resource problem of single-server FL. We consider a typical mu…

eess.SP2023

Co-Design for Spectral Coexistence between RIS-aided MIMO Radar and MIMO Communication Systems

Da Li, Bo Tang, Xuyang Wang +2

Reconfigurable intelligent surface (RIS) refers to a signal reflection surface containing a large number of low-cost passive reflecting elements. RIS can improve the performance of…

cs.CR2026

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

Yining Chen, Jihao Zhao, Bo Tang +5

As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. Howev…

eess.SP2020

Polyphase Waveform Design for MIMO Radar Space Time Adaptive Processing

Bo Tang, Jonathan Tuck, Peter Stoica

We consider the design of polyphase waveforms for ground moving target detection with airborne multiple-input-multiple-output (MIMO) radar. Due to the constant-modulus and finite-a…

cs.PF2026

SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving

Quqing Zhang, Kai Chen, Ning Liao +5

In long-context LLM serving, the prefill stage often dominates time-to-first-token and computational cost. Although Prefix Cache in vLLM/PagedAttention has been widely used to reus…

cs.GT2015

On the Efficiency of All-Pay Mechanisms

George Christodoulou, Alkmini Sgouritsa, Bo Tang

We study the inefficiency of mixed equilibria, expressed as the price of anarchy, of all-pay auctions in three different environments: combinatorial, multi-unit and single-item auc…

cs.LG2021

Reviewing continual learning from the perspective of human-level intelligence

Yifan Chang, Wenbo Li, Jian Peng +7

Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for l…

eess.SP2023

Exploring the Potential of Integrated Optical Sensing and Communication (IOSAC) Systems with Si Waveguides for Future Networks

Xiangpeng Ou, Ying Qiu, Ming Luo +17

Advanced silicon photonic technologies enable integrated optical sensing and communication (IOSAC) in real time for the emerging application requirements of simultaneous sensing an…

cs.NE2026

Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation

Bo Tang, Weiwei Xie

Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in deep recurrent architectures…

cs.CL2025

SurveyX: Academic Survey Automation via Large Language Models

Xun Liang, Jiawei Yang, Yezhaohui Wang +11

Large Language Models (LLMs) have demonstrated exceptional comprehension capabilities and a vast knowledge base, suggesting that LLMs can serve as efficient tools for automated sur…

cs.LG2021

Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation

Jian Peng, Bo Tang, Hao Jiang +4

Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequen…

cs.LG2023

AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning

Xingyu Li, Bo Tang, Haifeng Li

Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner. Ho…

physics.optics2023

Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks

Chuyu Zhong, Kun Liao, Tianxiang Dai +18

Optical neural networks (ONNs) herald a new era in information and communication technologies and have implemented various intelligent applications. In an ONN, the activation funct…

eess.SY2016

Detection of False Data Injection Attacks in Smart Grid under Colored Gaussian Noise

Bo Tang, Jun Yan, Steven Kay +1

In this paper, we consider the problems of state estimation and false data injection detection in smart grid when the measurements are corrupted by colored Gaussian noise. By model…