Publications (422)
LogicScan: An LLM-driven Framework for Detecting Business Logic Vulnerabilities in Smart Contracts
Jiaqi Gao, Zijian Zhang, Yuqiang Sun +5
Business logic vulnerabilities have become one of the most damaging yet least understood classes of smart contract vulnerabilities. Unlike traditional bugs such as reentrancy or ar…
Learning Site-specific Styles for Multi-institutional Unsupervised Cross-modality Domain Adaptation
Han Liu, Yubo Fan, Zhoubing Xu +2
Unsupervised cross-modality domain adaptation is a challenging task in medical image analysis, and it becomes more challenging when source and target domain data are collected from…
On Sparse Modern Hopfield Model
Jerry Yao-Chieh Hu, Donglin Yang, Dennis Wu +3
We introduce the sparse modern Hopfield model as a sparse extension of the modern Hopfield model. Like its dense counterpart, the sparse modern Hopfield model equips a memory-retri…
CLOAK: A Framework For Development of Confidential Blockchain Smart Contracts
Qian Ren, Han Liu, Yue Li +1
In recent years, as blockchain adoption has been expanding across a wide range of domains, e.g., digital asset, supply chain finance, etc., the confidentiality of smart contracts i…
EQL -- an extremely easy to learn knowledge graph query language, achieving highspeed and precise search
Han Liu, Shantao Liu
EQL, also named as Extremely Simple Query Language, can be widely used in the field of knowledge graph, precise search, strong artificial intelligence, database, smart speaker ,pat…
Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
Han Liu, Vivian Lai, Chenhao Tan
Although AI holds promise for improving human decision making in societally critical domains, it remains an open question how human-AI teams can reliably outperform AI alone and hu…
Graph-Valued Regression
Han Liu, Xi Chen, John Lafferty +1
Undirected graphical models encode in a graph the dependency structure of a random vector . In many applications, it is of interest to model given another random vector…
Data-Centric Visual Development for Self-Driving Labs
Anbang Liu, Guanzhong Hu, Jiayi Wang +2
Self-driving laboratories offer a promising path toward reducing the labor-intensive, time-consuming, and often irreproducible workflows in the biological sciences. Yet their strin…
EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene
Yixiong Huo, Guangfeng Jiang, Hongyang Wei +9
3D Gaussian Splatting (3D GS) has gained popularity due to its faster rendering speed and high-quality novel view synthesis. Some researchers have explored using 3D GS for reconstr…
AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation
Dewei Hu, Hao Li, Han Liu +4
Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to ef…
Device Perspective for Black Phosphorus Field-Effect Transistors: Contact Resistance, Ambipolar and Scaling
Yuchen Du, Han Liu, Yexin Deng +1
Although monolayer black phosphorus (BP) or phosphorene has been successfully exfoliated and its optical properties have been explored, most of electrical performance of the device…
Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance
Chenyu Wang, Weicheng Dai, Han Liu +2
Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans and show strong potential to improve radiology wor…
Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation
Weimin Wu, Alexander C. Furnas, Eddie Yang +5
We propose Sci2Pol-Bench and Sci2Pol-Corpus, the first benchmark and training dataset for evaluating and fine-tuning large language models (LLMs) on policy brief generation from a…
Sharp Computational-Statistical Phase Transitions via Oracle Computational Model
Zhaoran Wang, Quanquan Gu, Han Liu
We study the fundamental tradeoffs between computational tractability and statistical accuracy for a general family of hypothesis testing problems with combinatorial structures. Ba…
Specializing Foundation Models via Mixture of Low-Rank Experts for Comprehensive Head CT Analysis
Youngjin Yoo, Han Liu, Bogdan Georgescu +14
Foundation models pre-trained on large-scale datasets demonstrate strong transfer learning capabilities; however, their adaptation to complex multi-label diagnostic tasks-such as c…
Hidden Clique Inference in Random Ising Model I: the planted random field Curie-Weiss model
Yihan He, Han Liu, Jianqing Fan
We study the problem of testing and recovering the hidden -clique Ferromagnetic correlation in the planted Random Field Curie-Weiss model (a.k.a. the pRFCW model). The pRFCW mod…
High Dimensional Semiparametric Latent Graphical Model for Mixed Data
Jianqing Fan, Han Liu, Yang Ning +1
Graphical models are commonly used tools for modeling multivariate random variables. While there exist many convenient multivariate distributions such as Gaussian distribution for…
Survival Prediction of Brain Cancer with Incomplete Radiology, Pathology, Genomics, and Demographic Data
Can Cui, Han Liu, Quan Liu +6
Integrating cross-department multi-modal data (e.g., radiological, pathological, genomic, and clinical data) is ubiquitous in brain cancer diagnosis and survival prediction. To dat…
GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis
Yuqiang Sun, Daoyuan Wu, Yue Xue +5
Smart contracts are prone to various vulnerabilities, leading to substantial financial losses over time. Current analysis tools mainly target vulnerabilities with fixed control or…
The design of ultra-strong laser with one-dimensional function photonic crystal
Xiang-Yao Wu, Ben-Shan Wu, Si-Qi Zhang +7
With the optical kerr effect, the conventional photonic crystal can be turned into the function photonic crystal under the action of pump light. In the paper, we have designed the…
Decoupled Alignment for Robust Plug-and-Play Adaptation
Haozheng Luo, Jiahao Yu, Wenxin Zhang +9
The paper proposes a training-free, plug-and-play method that uses knowledge distillation and model fusion to correct misaligned (shadow-aligned) large language models, improving s…
Attributed Graph Clustering via Adaptive Graph Convolution
Xiaotong Zhang, Han Liu, Qimai Li +1
Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes. Recent progress on graph convolutional networks has proved that g…
Knowledge Over Parameters: Evolving Smart Contract Vulnerability Detection
Yuqiang Sun, Han Liu, Ying Li +4
Smart contract vulnerabilities are predominantly logic bugs whose detection requires structured, step-by-step procedural knowledge of attack patterns and contract semantics. Existi…
Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
Zhaoran Wang, Han Liu, Tong Zhang
We provide theoretical analysis of the statistical and computational properties of penalized -estimators that can be formulated as the solution to a possibly nonconvex optimizat…
Differentially Private Kernel Density Estimation
Erzhi Liu, Jerry Yao-Chieh Hu, Alex Reneau +2
We introduce a refined differentially private (DP) data structure for kernel density estimation (KDE), offering not only improved privacy-utility tradeoff but also better efficienc…
HS-GCN: Hamming Spatial Graph Convolutional Networks for Recommendation
Han Liu, Yinwei Wei, Jianhua Yin +1
An efficient solution to the large-scale recommender system is to represent users and items as binary hash codes in the Hamming space. Towards this end, existing methods tend to co…
Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints
Jaeyeon Jang, Diego Klabjan, Han Liu +5
This paper proposes a novel multi-agent reinforcement learning (MARL) method to learn multiple coordinated agents under directed acyclic graph (DAG) constraints. Unlike existing MA…
High-Temperature Structure Detection in Ferromagnets
Yuan Cao, Matey Neykov, Han Liu
This paper studies structure detection problems in high temperature ferromagnetic (positive interaction only) Ising models. The goal is to distinguish whether the underlying graph…
KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction
Han Liu, Keyan Ding, Peilin Chen +4
Accurate prediction of protein-ligand binding affinity is critical for drug discovery. While recent deep learning approaches have demonstrated promising results, they often rely so…
The huge Package for High-dimensional Undirected Graph Estimation in R
Tuo Zhao, Han Liu, Kathryn Roeder +2
We describe an R package named huge which provides easy-to-use functions for estimating high dimensional undirected graphs from data. This package implements recent results in the…
Hyperbolic Neural Population Geometry Benefits Computation
Dennis Wu, Yi-Chun Hung, Braden Yuille +2
Neural population geometry shapes downstream computation. Recent empirical findings in neurobiology suggest that a hyperbolic structure underlies population activity in the hippoca…
Atomic-Layer-Deposited Al2O3 on Bi2Te3 for Topological Insulator Field-Effect Transistors
Han Liu, Peide D. Ye
We report dual-gate modulation of topological insulator field-effect transistors (TI FETs) made on Bi2Te3 thin flakes with integration of atomic-layer-deposited (ALD) Al2O3 high-k…
Hidden Clique Inference in Random Ising Model II: the planted Sherrington-Kirkpatrick model
Yihan He, Han Liu, Jianqing Fan
We study the problem of testing and recovering -clique Ferromagnetic mean shift in the planted Sherrington-Kirkpatrick model (i.e., a type of spin glass model) with spins. T…
Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e
Chenwei Xu, Jerry Yao-Chieh Hu, Aakaash Narayanan +21
We introduce a novel Proximal Policy Optimization (PPO) algorithm aimed at addressing the challenge of maintaining a uniform proton beam intensity delivery in the Muon to Electron…
Learning Human-Compatible Representations for Case-Based Decision Support
Han Liu, Yizhou Tian, Chacha Chen +3
Algorithmic case-based decision support provides examples to help human make sense of predicted labels and aid human in decision-making tasks. Despite the promising performance of…
How2Sketch: Generating Easy-To-Follow Tutorials for Sketching 3D Objects
James W. Hennessey, Han Liu, Holger Winnemöller +2
Accurately drawing 3D objects is difficult for untrained individuals, as it requires an understanding of perspective and its effects on geometry and proportions. Step-by-step tutor…
Nonconvex Statistical Optimization: Minimax-Optimal Sparse PCA in Polynomial Time
Zhaoran Wang, Huanran Lu, Han Liu
Sparse principal component analysis (PCA) involves nonconvex optimization for which the global solution is hard to obtain. To address this issue, one popular approach is convex rel…
On Stein's Identity and Near-Optimal Estimation in High-dimensional Index Models
Zhuoran Yang, Krishnakumar Balasubramanian, Han Liu
We consider estimating the parametric components of semi-parametric multiple index models in a high-dimensional and non-Gaussian setting. Such models form a rich class of non-linea…
EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM
Henry Peng Zou, Gavin Heqing Yu, Ziwei Fan +5
In e-commerce, accurately extracting product attribute values from multimodal data is crucial for improving user experience and operational efficiency of retailers. However, previo…
Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation
Guo Ye, Zexi Zhang, Xu Zhao +4
Vision-Language-Action (VLA) models have shown remarkable generalization by mapping web-scale knowledge to robotic control, yet they remain blind to physical contact. Consequently,…
Combinatorial Inference for Graphical Models
Matey Neykov, Junwei Lu, Han Liu
We propose a new family of combinatorial inference problems for graphical models. Unlike classical statistical inference where the main interest is point estimation or parameter te…
Phosphorene: A New 2D Material with High Carrier Mobility
Han Liu, Adam T. Neal, Zhen Zhu +2
Preceding the current interest in layered materials for electronic applications, research in the 1960's found that black phosphorus combines high carrier mobility with a fundamenta…
Discrete Flow Matching Policy Optimization
Maojiang Su, Po-Chung Hsieh, Weimin Wu +4
We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) models under a broad…
AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
Zhenyu Pan, Yiting Zhang, Zhuo Liu +13
LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and…
Switching Mechanism in Single-Layer Molybdenum Disulfide Transistors: an Insight into Current Flow across Schottky Barriers
Han Liu, Mengwei Si, Yexin Deng +6
In this article, we study the properties of metal contacts to single-layer molybdenum disulfide (MoS2) crystals, revealing the nature of switching mechanism in MoS2 transistors. On…
Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning
Qinjie Lin, Han Liu, Biswa Sengupta
We propose SwitchTT, a multi-task extension to Trajectory Transformer but enhanced with two striking features: (i) exploiting a sparsely activated model to reduce computation cost…
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
Jerry Yao-Chieh Hu, Pei-Hsuan Chang, Robin Luo +4
We introduce an Outlier-Efficient Modern Hopfield Model (termed ) and use it to address the outlier inefficiency problem of {training} gigantic transformer-base…
Contact Research Strategy for Emerging Molybdenum Disulfide and Other Two-Dimensional Field-effect Transistors
Yuchen Du, Lingming Yang, Han Liu +1
Layered two-dimensional (2D) semiconducting transition metal dichalcogenides (TMD) have been widely isolated, synthesized, and characterized recently. Numerous 2D materials are ide…
EANS: Reducing Energy Consumption for UAV with an Environmental Adaptive Navigation Strategy
Tian Liu, Han Liu, Boyang Li +2
Unmanned Aerial Vehicles (UAVS) are limited by the onboard energy. Refinement of the navigation strategy directly affects both the flight velocity and the trajectory based on the a…
Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation
Xin Yu, Qi Yang, Han Liu +10
2D single-slice abdominal computed tomography (CT) enables the assessment of body habitus and organ health with low radiation exposure. However, single-slice data necessitates the…
Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs
Qimai Li, Xiaotong Zhang, Han Liu +2
Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that com…
Homotopy Parametric Simplex Method for Sparse Learning
Haotian Pang, Robert Vanderbei, Han Liu +1
High dimensional sparse learning has imposed a great computational challenge to large scale data analysis. In this paper, we are interested in a broad class of sparse learning appr…
MVDLite: a Fast Validation Algorithm for Model View Definition Rules
Han Liu, Ge Gao, Hehua Zhang +3
Model View Definition (MVD) is the standard methodology to define the data exchange requirements and rule constraints for Building Information Models (BIMs). In this paper, the MVD…
Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Bi-parametric MRI Datasets
Hao Li, Han Liu, Heinrich von Busch +16
Our hypothesis is that UDA using diffusion-weighted images, generated with a unified model, offers a promising and reliable strategy for enhancing the performance of supervised lea…
Graph Estimation From Multi-attribute Data
Mladen Kolar, Han Liu, Eric P. Xing
Many real world network problems often concern multivariate nodal attributes such as image, textual, and multi-view feature vectors on nodes, rather than simple univariate nodal at…
Biomedical image analysis competitions: The state of current participation practice
Matthias Eisenmann, Annika Reinke, Vivienn Weru +352
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known abou…
An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling
Han Liu, Feng Zhang, Xiaotong Zhang +2
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Si…
Compressive Network Analysis
Xiaoye Jiang, Yuan Yao, Han Liu +1
Modern data acquisition routinely produces massive amounts of network data. Though many methods and models have been proposed to analyze such data, the research of network data is…
Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification
Han Liu, Bogdan Georgescu, Yanbo Zhang +8
3D medical image classification is essential for modern clinical workflows. Medical foundation models (FMs) have emerged as a promising approach for scaling to new tasks, yet curre…
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
Haoran Lu, Songling Liu, Yue Chen +15
Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed…
Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
Feiyang Huang, Yuqiang Sun, Fan Zhang +3
Large Language Models (LLMs) have shown promising performance in software vulnerability detection, particularly after domain-specific Supervised Fine-Tuning (SFT). However, it rema…
Label-Wise Document Pre-Training for Multi-Label Text Classification
Han Liu, Caixia Yuan, Xiaojie Wang
A major challenge of multi-label text classification (MLTC) is to stimulatingly exploit possible label differences and label correlations. In this paper, we tackle this challenge b…
Fast and Low-Cost Genomic Foundation Models via Outlier Removal
Haozheng Luo, Chenghao Qiu, Maojiang Su +5
To address the challenge of scarce computational resources in genomic modeling, we introduce GERM, a genomic foundation model with strong compression performance and fast adaptabil…
On Semiparametric Exponential Family Graphical Models
Zhuoran Yang, Yang Ning, Han Liu
We propose a new class of semiparametric exponential family graphical models for the analysis of high dimensional mixed data. Different from the existing mixed graphical models, we…
Cell-JEPA: Latent Representation Learning for Single-Cell Transcriptomics
Ali ElSheikh, Rui-Xi Wang, Weimin Wu +9
Single-cell foundation models learn by reconstructing masked gene expression, implicitly treating technical noise as signal. With dropout rates exceeding 90%, reconstruction object…
Joint measurement of time-frequency entanglement via sum frequency generation
Han Liu, Amr S. Helmy
We propose, analyze, and evaluate a technique for the joint measurement of time-frequency entanglement between two photons. In particular, we show that the frequency sum and time d…
Typical dynamics of plane rational maps with equal degrees
Jeffrey Diller, Han Liu, Roland Roeder
Let be a rational map with algebraic and topological degrees both equal to . Little is known in general about the ergodic pro…
APT: Atomic Physical Transitions for Causal Video-Language Understanding
Shang Wu, Haoran Lu, Songling Liu +7
Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the proc…
Some Two-Step Procedures for Variable Selection in High-Dimensional Linear Regression
Jian Zhang, Xinge Jessie Jeng, Han Liu
We study the problem of high-dimensional variable selection via some two-step procedures. First we show that given some good initial estimator which is -consistent b…
Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
Wan Zhang, Qinjie Lin, Chan Lee +3
Forecasting multiple time-series with high-dimensional covariates presents a core challenge: unifying common temporal patterns while retaining meaningful series-specific informatio…
"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
Vivian Lai, Han Liu, Chenhao Tan
To support human decision making with machine learning models, we often need to elucidate patterns embedded in the models that are unsalient, unknown, or counterintuitive to humans…
Estimating and Inferring the Maximum Degree of Stimulus-Locked Time-Varying Brain Connectivity Networks
Kean Ming Tan, Junwei Lu, Tong Zhang +1
Neuroscientists have enjoyed much success in understanding brain functions by constructing brain connectivity networks using data collected under highly controlled experimental set…
Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey
Chengyuan Deng, Yiqun Duan, Xin Jin +15
Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns…
Large Covariance Estimation through Elliptical Factor Models
Jianqing Fan, Han Liu, Weichen Wang
We proposed a general Principal Orthogonal complEment Thresholding (POET) framework for large-scale covariance matrix estimation based on an approximate factor model. A set of high…
Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
Yutai Hou, Wanxiang Che, Yongkui Lai +4
In this paper, we explore the slot tagging with only a few labeled support sentences (a.k.a. few-shot). Few-shot slot tagging faces a unique challenge compared to the other few-sho…
Statistical Limits of Convex Relaxations
Zhaoran Wang, Quanquan Gu, Han Liu
Many high dimensional sparse learning problems are formulated as nonconvex optimization. A popular approach to solve these nonconvex optimization problems is through convex relaxat…
On well-posedness of generalized Hall-magneto-hydrodynamics
Mimi Dai, Han Liu
We obtain local well-posedness result for the generalized Hall-magneto-hydrodynamics system in Besov spaces ${\dot B^{-(2α_1-γ)}_{\infty, \infty}} \times {\dot B^{-(2α_2-β)}_{\…
Are Hallucinations Bad Estimations?
Hude Liu, Jerry Yao-Chieh Hu, Jennifer Yuntong Zhang +2
We formalize hallucinations in generative models as failures to link an estimate to any plausible cause. Under this interpretation, we show that even loss-minimizing optimal estima…
MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation
Xiaochen Wang, Bao Hoang, Han Liu +2
Retrieval-augmented generation (RAG) over knowledge graphs has emerged as a promising approach for grounding large language models, yet existing benchmarks largely overlook the cha…
IntuiTF: MLLM-Guided Transfer Function Optimization for Direct Volume Rendering
Yiyao Wang, Bo Pan, Ke Wang +8
Direct volume rendering (DVR) is a fundamental technique for visualizing volumetric data, where transfer functions (TFs) play a crucial role in extracting meaningful structures. Ho…
SPINE: Bridging the Cyber-Physical Gap with Agentic AI
Minkyu Ham, Dongho Kim, Chan Lee +7
Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven…
EASYFLOW: Keep Ethereum Away From Overflow
Jianbo Gao, Han Liu, Chao Liu +3
While Ethereum smart contracts enabled a wide range of blockchain applications, they are extremely vulnerable to different forms of security attacks. Due to the fact that transacti…
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
Carson Eisenach, Haichuan Yang, Ji Liu +1
Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over $\ma…
Distributed Estimation and Inference with Statistical Guarantees
Heather Battey, Jianqing Fan, Han Liu +2
This paper studies hypothesis testing and parameter estimation in the context of the divide and conquer algorithm. In a unified likelihood based framework, we propose new test stat…
The Integration of High-k Dielectric on Two-Dimensional Crystals by Atomic Layer Deposition
Han Liu, Kun Xu, Xujie Zhang +1
We investigate the integration of Al2O3 high-k dielectric on two-dimensional (2D) crystals of boron nitride (BN) and molybdenum disulfide (MoS2) by atomic layer deposition (ALD). W…
Semiconducting Black Phosphorus: Synthesis, Transport Properties and Electronic Applications
Han Liu, Yuchen Du, Yexin Deng +1
Phosphorus is one of the most abundant elements preserved in earth, constructing with a fraction of ~0.1% of the earth crust. In general, phosphorus has several allotropes. The two…
Towards Sparse Video Understanding and Reasoning
Chenwei Xu, Zhen Ye, Shang Wu +8
We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames…
Feedback-Based Tree Search for Reinforcement Learning
Daniel R. Jiang, Emmanuel Ekwedike, Han Liu
Inspired by recent successes of Monte-Carlo tree search (MCTS) in a number of artificial intelligence (AI) application domains, we propose a model-based reinforcement learning (RL)…
A convex formulation for high-dimensional sparse sliced inverse regression
Kean Ming Tan, Zhaoran Wang, Tong Zhang +2
Sliced inverse regression is a popular tool for sufficient dimension reduction, which replaces covariates with a minimal set of their linear combinations without loss of informatio…
UAT20: Unifying Liquidity Across Rollups
Yue Li, Han Liu
Ethereum has been a cornerstone of the decentralized ecosystem, with rollup-based scaling solutions like Arbitrum and Optimism significantly expanding its capabilities. These rollu…
On uniqueness and helicity conservation of weak solutions to the electron-MHD system
Mimi Dai, Jacob Krol, Han Liu
We study the weak solutions to the electron-MHD system and obtain a conditional uniqueness result. In addition, we prove conservation of helicity for weak solutions to the electron…
The Effect of Dielectric Capping on Few-Layer Phosphorene Transistors: Tuning the Schottky Barrier Heights
Han Liu, Adam T. Neal, Mengwei Si +2
Phosphorene is a unique single elemental semiconductor with two-dimensional layered structures. In this letter, we study the transistor behavior on mechanically exfoliated few-laye…
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
Dennis Wu, Jerry Yao-Chieh Hu, Teng-Yun Hsiao +1
We propose a two-stage memory retrieval dynamics for modern Hopfield models, termed , with enhanced memory capacity. Our key contribution is a learnable feat…
BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model
Chenwei Xu, Yu-Chao Huang, Jerry Yao-Chieh Hu +4
We introduce the \textbf{B}i-Directional \textbf{S}parse \textbf{Hop}field Network (\textbf{BiSHop}), a novel end-to-end framework for deep tabular learning. BiSHop handles the two…
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Peng Sun, Xinghai Sun, Lei Han +8
Starcraft II (SC2) is widely considered as the most challenging Real Time Strategy (RTS) game. The underlying challenges include a large observation space, a huge (continuous and i…
Enhancing LIDAR performance metrics using continuous-wave photon-pair sources
Han Liu, Daniel Giovannini, Haoyu He +4
In order to enhance LIDAR performance metrics such as target detection sensitivity, noise resilience and ranging accuracy, we exploit the strong temporal correlation within the pho…
TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval
Yuhang Zhang, Keyan Ding, Peilin Chen +5
Enzyme-reaction retrieval is a fundamental problem in computational biology, underpinning enzyme characterization, reaction mechanism elucidation, and the rational design of metabo…
A Real-Time System for Scheduling and Managing UAV Delivery in Urban Areas
Han Liu, Tian Liu, Kai Huang
As urban logistics demand continues to grow, UAV delivery has become a key solution to improve delivery efficiency, reduce traffic congestion, and lower logistics costs. However, t…
MRT: Learning Compact Representations with Mixed RWKV-Transformer for Extreme Image Compression
Han Liu, Hengyu Man, Xingtao Wang +2
Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However,…
Curse of Heterogeneity: Computational Barriers in Sparse Mixture Models and Phase Retrieval
Jianqing Fan, Han Liu, Zhaoran Wang +1
We study the fundamental tradeoffs between statistical accuracy and computational tractability in the analysis of high dimensional heterogeneous data. As examples, we study sparse…