Publications (821)
The Tenth NTIRE 2025 Image Denoising Challenge Report
Lei Sun, Hang Guo, Bin Ren +91
This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (Ï = 50), highlighting the proposed methodologies and corresponding results. The primary objective is t…
Anisotropic Electronic Correlations in the Spin Density Wave State of LaNiO
Ge He, Jun Shen, Shiyu Xie +21
The bilayer nickelate superconductor LaNiO undergoes a density wave transition near 150 K that has attracted intensive scrutiny, yet its microscopic origin remains elus…
A Generalized Nyquist-Shannon Sampling Theorem Using the Koopman Operator
Zhexuan Zeng, Jun Liu, Ye Yuan
In the field of signal processing, the sampling theorem plays a fundamental role for signal reconstruction as it bridges the gap between analog and digital signals. Following the c…
Slender Object Scene Segmentation in Remote Sensing Image Based on Learnable Morphological Skeleton with Segment Anything Model
Jun Xie, Wenxiao Li, Faqiang Wang +3
Morphological methods play a crucial role in remote sensing image processing, due to their ability to capture and preserve small structural details. However, most of the existing d…
PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering
Fangzhi Xu, Qika Lin, Tianzhe Zhao +2
Logical reasoning task has attracted great interest since it was proposed. Faced with such a task, current competitive models, even large language models (e.g., ChatGPT and PaLM 2)…
IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
Lanyun Zhu, Deyi Ji, Tianrun Chen +3
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations…
Electronic Nematicity Revealed by Polarized Ultrafast Spectroscopy in Bilayer LaNiO
Qi-Yi Wu, De-Yuan Hu, Chen Zhang +14
We report a polarized ultrafast pump-probe study of the normal-state electronic dynamics in bilayer LaNiO and trilayer LaNiO single crystals at ambient p…
Lyapunov-Barrier Characterization of Robust Reach-Avoid-Stay Specifications for Hybrid Systems
Yiming Meng, Jun Liu
Stability, reachability, and safety are crucial properties of dynamical systems. While verification and control synthesis of reach-avoid-stay objectives can be effectively handled…
Characterization of Safe Stabilization and Control Lyapunov-Barrier Functions via Zubov Equation Formulation
Yiming Meng, Jun Liu
Design and analysis of stabilizing controllers with safety guarantees for nonlinear systems have received considerable attention in recent years. Control Lyapunov-barrier functions…
BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
Jinxiang Lai, Wenlong Wu, Jiawei Zhan +5
Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations. Recent methods have demonstrated the effectiveness of acquiring high-qu…
Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization
Jinhao Li, Jiaming Xu, Shiyao Li +4
Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to…
Invariance of Charge of Laughlin Quasiparticles
V. J. Goldman, I. Karakurt, Jun Liu +1
A Quantum Antidot electrometer has been used in the first direct observation of the fractionally quantized electric charge. In this paper we report experiments performed on the int…
Atomic and Littlewood-Paley Characterizations of Anisotropic Mixed-Norm Hardy Spaces and Their Applications
Long Huang, Jun Liu, Dachun Yang +1
Let , and be the anisotropic mixed-norm Hardy space assoc…
Intermittent Deployment for Large-Scale Multi-Robot Forage Perception: Data Synthesis, Prediction, and Planning
Jun Liu, Murtaza Rangwala, Kulbir Singh Ahluwalia +5
Monitoring the health and vigor of grasslands is vital for informing management decisions to optimize rotational grazing in agriculture applications. To take advantage of forage re…
CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
Xinyu Zhang, Yuxuan Dong, Lingling Zhang +5
Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrele…
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
Xu Lin, Jinlong Peng, Zhenye Gan +2
Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on st…
SGDFuse: SAM-Guided Diffusion Model for High-Fidelity Infrared and Visible Image Fusion
Xiaoyang Zhang, jinjiang Li, Guodong Fan +4
Infrared and visible image fusion (IVIF) is essential for integrating thermal saliency with textural details to support downstream perception. However, most existing approaches suf…
A Safe Screening Rule for Sparse Logistic Regression
Jie Wang, Jiayu Zhou, Jun Liu +2
The l1-regularized logistic regression (or sparse logistic regression) is a widely used method for simultaneous classification and feature selection. Although many recent efforts h…
Monotonicity of the imaginary part of the Riemann function in the region
Jun Liu
This paper proves that the imaginary part of the Riemann function is strictly monotonic with in the region . That leads…
Improved Sufficient Conditions for Exact Convex Relaxation of Storage-Concerned ED
Chao Duan, Lin Jiang, Wanliang Fang +2
To avoid simultaneous charging and discharging of storages, complementarity constraints are introduced to storage-concerned economic dispatch (ED), which makes the problem non-conv…
DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments
Tan Zhang, Quanyou Li, Lu Zhang +3
When a disaster unfolds, responders must answer not only what is happening, but also why it is happening, what will happen next, and what to do now, often from noisy low-altitude U…
Modified multi-dimensional limiting process with enhanced shock stability on unstructured grids
Fan Zhang, Jun Liu, Biaosong Chen
The basic concept of multi-dimensional limiting process (MLP) on unstructured grids is inherited and modified for improving shock stabilities and reducing numerical dissipation on…
Safe and Efficient Screening For Sparse Support Vector Machine
Zheng Zhao, Jun Liu
Screening is an effective technique for speeding up the training process of a sparse learning model by removing the features that are guaranteed to be inactive the process. In this…
Extensive Scaling and Nonuniformity of the Karhunen-Loève Decomposition for the Spiral-Defect Chaos State
Scott M. Zoldi, Jun Liu, Kapil M. S. Bajaj +2
By analyzing large-aspect-ratio spiral-defect-chaos (SDC) convection images, we show that the Karhunen-Loève decomposition (KLD) scales extensively for subsystem-sizes larger than…
One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching
Siyuan Yang, Jun Liu, Shijian Lu +2
One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge…
Distributionally Robust Chance-Constrained Approximate AC-OPF with Wasserstein Metric
Chao Duan, Wanliang Fang, Lin Jiang +2
Chance constrained optimal power flow (OPF) has been recognized as a promising framework to manage the risk from variable renewable energy (VRE). In presence of VRE uncertainties,…
A novel weighting scheme for random -SAT
Zongsheng Gao, Jun Liu, Ke Xu
Consider a random -CNF formula with variables and clauses. For every truth assignment and every clause $c=\ell_{1}\vee\cdots\vee\ell…
Evaluating Large Language Models for Radiology Natural Language Processing
Zhengliang Liu, Tianyang Zhong, Yiwei Li +43
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they hav…
SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation
Hang Zhang, Zhuoling Li, Jun Liu
Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into…
Untargeted Adversarial Attack on Knowledge Graph Embeddings
Tianzhe Zhao, Jiaoyan Chen, Yanchi Ru +3
Knowledge graph embedding (KGE) methods have achieved great success in handling various knowledge graph (KG) downstream tasks. However, KGE methods may learn biased representations…
Role of disorder in determining the vibrational properties of mass-spring networks
Yunhuan Nie, Hua Tong, Jun Liu +2
By introducing four fundamental types of disorders into a two-dimensional triangular lattice separately, we determine the role of each type of disorder in the vibration of the resu…
Resolving the inner jet of PKS 1749+096 with super-resolution VLBA images at 7 mm
Lang Cui, Ru-Sen Lu, Wei Yu +3
High resolution imaging of inner jets in Active Galactic Nuclei (AGNs) with VLBI at millimeter wavelengths provides deep insight into the launching and collimation mechanisms of re…
Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs
Amartya Mukherjee, Jun Liu
This paper proposes an actor-critic algorithm for controlling the temperature of a battery pack using a cooling fluid. This is modeled by a coupled 1D partial differential equation…
Decentralized Autoregressive Generation
Stepan Maschan, Haoxuan Qu, Jun Liu
The decentralization of autoregressive generation has attracted considerable attention in recent years as a solution to scaling bottlenecks. However, despite promising empirical re…
Correlation between the spin Hall angle and the structural phases of early 5d transition metals
Jun Liu, Tadakatsu Ohkubo, Seiji Mitani +2
We have studied the relationship between the structure and the spin Hall angle of the early 5d transition metals in X/CoFeB/MgO (X=Hf, Ta, W, Re) heterostructures. Spin Hall magnet…
Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
Yudai Pan, Jun Liu, Lingling Zhang +3
Relation reasoning in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm is learning the embeddings of relations and e…
Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Hang Zhang, Wenxiao Zhang, Haoxuan Qu +1
Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI)…
MobileViM: A Light-weight and Dimension-independent Vision Mamba for 3D Medical Image Analysis
Wei Dai, Jun Liu
Efficient evaluation of three-dimensional (3D) medical images is crucial for diagnostic and therapeutic practices in healthcare. Recent years have seen a substantial uptake in appl…
Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images
Kelei He, Wei Zhao, Xingzhi Xie +8
Understanding chest CT imaging of the coronavirus disease 2019 (COVID-19) will help detect infections early and assess the disease progression. Especially, automated severity asses…
Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation
Jun Liu, Xue-Cheng Tai, Shousheng Luo
Convex Shapes (CS) are common priors for optic disc and cup segmentation in eye fundus images. It is important to design proper techniques to represent convex shapes. So far, it is…
The Chiral Anomaly and Ultrahigh Mobility in Crystalline HfTe5
Huichao Wang, Chao-Kai Li, Haiwen Liu +11
HfTe5 is predicted to be a promising platform for studying topological phases. Here through an electrical transport study, we present the first observation of chiral anomaly and ul…
Recognizing Actions from Robotic View for Natural Human-Robot Interaction
Ziyi Wang, Peiming Li, Hong Liu +5
Natural Human-Robot Interaction (N-HRI) requires robots to recognize human actions at varying distances and states, regardless of whether the robot itself is in motion or stationar…
Parallel-in-Time Iterative Methods for Pricing American Options
Xian-Ming Gu, Jun Liu, Cornelis W. Oosterlee
For pricing American options, %after suitable discretization in space and time, a sequence of discrete linear complementarity problems (LCPs) or equivalently Hamilton-Jacobi-Bellma…
A Globally Asymptotically Stable Planar Homogeneous Polynomial Vector Field With No Polynomial Lyapunov Function
Jun Liu, Maxwell Fitzsimmons
We disprove the conjecture that every globally asymptotically stable homogeneous polynomial vector field admits a homogeneous polynomial Lyapunov function. The counterexample is a…
Single-shot fourth-order auto-correlator
Peng Wang, Xiong Shen, Jun Liu +1
The temporal contrast is one of the most important parameters of an ultra-high intense laser pulse. Third-order auto-correlator or cross-correlator have been widely used to charact…
Littlewood-Paley Characterizations of HajÅasz-Sobolev and Triebel-Lizorkin Spaces via Averages on Balls
Der-Chen Chang, Jun Liu, Dachun Yang +1
Let and . In this article, the authors characterize the Triebel-Lizorkin space with smoothness order via…
Multi-Task Feature Learning Via Efficient l2,1-Norm Minimization
Jun Liu, Shuiwang Ji, Jieping Ye
The problem of joint feature selection across a group of related tasks has applications in many areas including biomedical informatics and computer vision. We consider the l2,1-nor…
A residual-based non-orthogonality correction for force-balanced unstructured Volume-of-Fluid methods
Jun Liu, Tobias Tolle, Tomislav Maric
Non-orthogonality errors in unstructured Finite Volume methods for simulating incompressible two-phase flows may break the force-balanced discretization. We show that applying the…
RIS Empowered Near-Field Covert Communications
Jun Liu, Gang Yang, Yuanwei Liu +1
This paper studies an extremely large-scale reconfigurable intelligent surface (XL-RIS) empowered covert communication system in the near-field region. Alice covertly transmits mes…
Dynamics and geometry of the inner sub-parsec-scale jet in 3C 279 observed with the Event Horizon Telescope
Hendrik Mueller, Sebastiano D. von Fellenberg, Ai-Ling Zeng +275
The 2021 Event Horizon Telescope observations resolve the innermost jet region of the blazar 3C279 with unprecedented detail. The reconstructed images consistently reveal a compact…
Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
Fangzhi Xu, Zhiyong Wu, Qiushi Sun +6
Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expre…
On Almost Sure Convergence Rates of Stochastic Gradient Methods
Jun Liu, Ye Yuan
The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergen…
ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
Jing Xu, Weiqiang Wang, Cunjian Chen +2
Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production,…
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Jun Liu, Amir Shahroudy, Mauricio Perez +3
Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing depth-…
MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization
Jian Zhang, Zhangqi Wang, Haiping Zhu +6
Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimizatio…
Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt
Yanfeng Shi, Pengfei Cai, Jun Liu +5
Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenge…
Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs
Shihao Qi, Jie Ma, Ziang Yin +5
Existing methods usually leverage a fixed strategy, such as natural language reasoning, code-augmented reasoning, tool-integrated reasoning, or ensemble-based reasoning, to guide L…
Mask-RadarNet: Enhancing Transformer With Spatial-Temporal Semantic Context for Radar Object Detection in Autonomous Driving
Yuzhi Wu, Jun Liu, Guangfeng Jiang +2
As a cost-effective and robust technology, automotive radar has seen steady improvement during the last years, making it an appealing complement to commonly used sensors like camer…
Interstellar Scintillation Monitoring of the RadioAstron Blazars
Jun Liu, Thomas P. Krichbaum, Hayley Bignall +6
The RadioAstron space radio telescope provides a unique opportunity to study the extreme brightness temperatures () in AGNs with unprecedented long baselines of up t…
Development of a simulation and analysis framework for NνDEx experiment
Tianyu Liang, Hulin Wang, Dongliang Zhang +9
NDEx aims to search for the neutrinoless double beta decay in Se using a high pressure SeF gas time projection chamber (TPC). This paper presents a simulation…
Perception Driven Texture Generation
Yanhai Gan, Huifang Chi, Ying Gao +3
This paper investigates a novel task of generating texture images from perceptual descriptions. Previous work on texture generation focused on either synthesis from examples or gen…
STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning
Zinuo Li, Yongxin Guo, Jun Liu +7
Human understanding of video dynamics relies on forming structured representations of entities, actions, and temporal relations before engaging in abstract reasoning. In contrast,…
Fractional spatiotemporal optical vortices
Shunlin Huang, Peng Wang, Yilin Xu +2
Spatiotemporal optical vortices (STOVs) with spiral phase in the space-time domain, which carry intrinsic transverse orbital angular momentum (OAM), introduce a new degree of freed…
H2B: Heartbeat-based Secret Key Generation Using Piezo Vibration Sensors
Qi Lin, Weitao Xu, Jun Liu +4
We present Heartbeats-2-Bits (H2B), which is a system for securely pairing wearable devices by generating a shared secret key from the skin vibrations caused by heartbeat. This wor…
REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching
Han Nie, Bin Luo, Jun Liu +3
We present REMM, a rotation-equivariant framework for end-to-end multimodal image matching, which fully encodes rotational differences of descriptors in the whole matching pipeline…
ParaDiag: parallel-in-time algorithms based on the diagonalization technique
Martin J. Gander, Jun Liu, Shu-Lin Wu +2
In 2008, Maday and Ronquist introduced an interesting new approach for the direct parallel-in-time (PinT) solution of time-dependent PDEs. The idea is to diagonalize the time stepp…
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
Bingxi Zhao, Lin Geng Foo, Ping Hu +3
Recent advances in the intrinsic reasoning capabilities of large language models (LLMs) have given rise to LLM-based agent systems that exhibit near-human performance on a variety…
ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation
Yuheng Xue, Nenglun Chen, Jun Liu +1
Zero-shot 3D part segmentation is a challenging and fundamental task. In this work, we propose a novel pipeline, ZeroPS, which achieves high-quality knowledge transfer from 2D pret…
A ROM-accelerated parallel-in-time preconditioner for solving all-at-once systems from evolutionary PDEs
Jun Liu, Zhu Wang
In this paper we propose to use model reduction techniques for speeding up the diagonalization-based parallel-in-time (ParaDIAG) preconditioner, for iteratively solving all-at-once…
Multi-Glimpse LSTM with Color-Depth Feature Fusion for Human Detection
Hengduo Li, Jun Liu, Guyue Zhang +2
With the development of depth cameras such as Kinect and Intel Realsense, RGB-D based human detection receives continuous research attention due to its usage in a variety of applic…
Gaussian Curvature Filter on 3D Meshes
Wenming Tang, Yuanhao Gong, Kanglin Liu +4
Minimizing the Gaussian curvature of meshes can play a fundamental role in 3D mesh processing. However, there is a lack of computationally efficient and robust Gaussian curvature o…
The 4-error linear complexity distribution for -periodic binary sequences
Jianqin Zhou, Jun Liu, Wanquan Liu
By using the sieve method of combinatorics, we study -error linear complexity distribution of -periodic binary sequences based on Games-Chan algorithm. For , the com…
Achieving electrode smoothing by controlling the nucleation phase of metal deposition through polymer-substrate binding
Ying Xia, Duo Song, Mingyi Zhang +11
Polymer additives [like polyethylene oxide (PEO)] are widely used for smooth electrode deposition in aqueous zinc and a number of other battery systems currently investigated for e…
Pressure-Induced B1 to B2 Phase Transition in CeN Studied by ab initio Correlation Matrix Renormalization Theory Calculations
Jun Liu, Jianhua Zhang, Yongxin Yao +2
We apply correlation matrix renormalization theory (CMRT) to cerium nitride (CeN) under pressure. For B1 (NaCl-type) phase, CMRT gives an equation of state consistent with ambient…
Event Horizon Telescope observations of the jet launching and collimation in Centaurus A
Michael Janssen, Heino Falcke, Matthias Kadler +236
Very-long-baseline interferometry (VLBI) observations of active galactic nuclei at millimeter wavelengths have the power to reveal the launching and initial collimation region of e…
TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction
Xiaoli Liu, Jianqin Yin, Jin Liu +3
Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future…
DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference
Jiancai Ye, Jun Liu, Qingchen Li +5
Although Key-Value (KV) Cache is essential for efficient large language models (LLMs) inference, its growing memory footprint in long-context scenarios poses a significant bottlene…
Nyonic Technical Report
Junfeng Tian, Rui Wang, Cong Li +3
This report details the development and key achievements of our latest language model designed for custom large language models. The advancements introduced include a novel Online…
Deep Convolutional Neural Networks for Map-Type Classification
Xiran Zhou, Wenwen Li, Samantha T. Arundel +1
Maps are an important medium that enable people to comprehensively understand the configuration of cultural activities and natural elements over different times and places. Althoug…
Locating the missing large-scale emission in the jet of M87* with short EHT baselines
Boris Georgiev, Paul Tiede, Sebastiano D. von Fellenberg +280
In Very-Long Baseline Interferometric arrays, nearly co-located stations probe the largest scales and typically cannot resolve the observed source. In the absence of large-scale st…
EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection
Chenyang Zhu, Maorong Wang, Jun Liu +2
The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditional detection paradigms mainly rel…
Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports
Haopeng Li, Andong Deng, Jun Liu +5
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not b…
Quantum phases in a doped Mott insulator on the Shastry-Sutherland lattice
Jun Liu, Nandini Trivedi, Yongbin Lee +2
We propose the projected BCS wave function as the ground state for the doped Mott insulator SrCu2(BO3)2 on the Shastry-Sutherland lattice. At half filling this wave function yields…
A special cross-tie domain wall in helimagnet
Yuan Yao, Bei Ding, Jun Liu +5
A special cross-tie (SCT) domain wall was discovered in the helimagnet MnCoSi alloy via the magnetic vector field tomography in Lorentz transmission electron microscopy (LTEM). Dif…
Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness
Byeongseo Bok, Futa Waseda, Jun Liu +1
Brain decoding aims to uncover neural mechanisms by inferring stimulus-related representations from brain signals. In fMRI studies, this is typically achieved by mapping fMRI respo…
Data-driven optimal control of unknown nonlinear dynamical systems using the Koopman operator
Zhexuan Zeng, Ruikun Zhou, Yiming Meng +1
Nonlinear optimal control is vital for numerous applications but remains challenging for unknown systems due to the difficulties in accurately modelling dynamics and handling compu…
Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1
Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely un…
InstructGIE: Towards Generalizable Image Editing
Zichong Meng, Changdi Yang, Jun Liu +3
Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the ge…
Improving the Reliability for Confidence Estimation
Haoxuan Qu, Yanchao Li, Lin Geng Foo +3
Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to…
A Converse Control Lyapunov Theorem for Joint Safety and Stability
Thanin Quartz, Maxwell Fitzsimmons, Jun Liu
We show that the existence of a strictly compatible pair of control Lyapunov and control barrier functions is equivalent to the existence of a single smooth Lyapunov function that…
ToolFG: Towards Well-Grounded Fine-Grained Image Classification
Yu Xue, Haoxuan Qu, Zhuoling Li +4
Fine-grained image classification (FGIC) has broad applications and has attracted significant research attention. In this paper, we explore a novel paradigm for solving FGIC by pro…
FuXi-ENS: A machine learning model for medium-range ensemble weather forecasting
Xiaohui Zhong, Lei Chen, Hao Li +7
Ensemble forecasting is crucial for improving weather predictions, especially for forecasts of extreme events. Constructing an ensemble prediction system (EPS) based on conventiona…
Broadband multiwavelength properties of the archetypal blazar 3C 279 during the 2017 Event Horizon Telescope campaign
G. Principe, J. C. Algaba, E. Aviano +529
The archetypal blazar 3C 279 hosts a prominent relativistic jet and exhibits strong broadband variability across the electromagnetic spectrum. In April 2017, the Event Horizon Tele…
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
Fangzhi Xu, Hang Yan, Chang Ma +6
Advancing LLM reasoning skills has captivated wide interest. However, current post-training techniques rely heavily on supervisory signals, such as outcome supervision or auxiliary…
Dynamic Automated Deduction by Contradiction Separation: The Standard Extension Algorithm
Yang Xu, Xingxing He, Shuwei Chen +2
Automated deduction seeks to enable machines to reason with mathematical precision and logical completeness. Classical resolution-based systems, such as Prover9, E, and Vampire, re…
Structured Agent Distillation for Large Language Model
Jun Liu, Zhenglun Kong, Peiyan Dong +10
Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks. Yet, their practical de…
Generation of high-energy clean multicolored ultrashort pulses and their application in single-shot temporal contrast measurement
Peng Wang, Xiong Shen, Jun Liu +1
We demonstrate the generation of 100-μJ-level multicolored femtosecond pulses based on a single-stage cascaded four-wave mixing (CFWM) process in a thin glass plate. The generated…
Radio observations of the first three-month Fermi-AGN at 4.8 GHz
Xiang Liu, Hua-Gang Song, Jun Liu +6
Using the Urumqi 25m radio telescope, sources from the first three-month Fermi-LAT detected AGN catalog with declination >0 were observed in 2009 at 4.8 GHz. The radio flux density…
Rank-One Prior: Toward Real-Time Scene Recovery
Jun Liu, Ryan Wen Liu, Jianing Sun +1
Scene recovery is a fundamental imaging task for several practical applications, e.g., video surveillance and autonomous vehicles, etc. To improve visual quality under different we…
LLM Unlearning with LLM Beliefs
Kemou Li, Qizhou Wang, Yue Wang +4
Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods gen…