Publications (70)
Morley-Wang-Xu element methods with penalty for a fourth order elliptic singular perturbation problem
Wenqing Wang, Xuehai Huang, Kai Tang +1
Two Morley-Wang-Xu element methods with penalty for the fourth order elliptic singular perturbation problem are proposed in this paper, including the interior penalty Morley-Wang-X…
S-GRPO: Unified Post-Training for Large Vision-Language Models
Yuming Yan, Kai Tang, Sihong Chen +4
Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL…
fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculum
Mingxiong Lin, Zhangquan Gong, Maowen Tang +6
Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Optimization (GRPO) serving as the…
Transformer Driven Visual Servoing for Fabric Texture Matching Using Dual-Arm Manipulator
Fuyuki Tokuda, Akira Seino, Akinari Kobayashi +2
In this paper, we propose a method to align and place a fabric piece on top of another using a dual-arm manipulator and a grayscale camera, so that their surface textures are accur…
On mixed curvature for Hermitian manifolds
Kai Tang
In this paper, we consider {\em mixed curvature} for Hermitian manifolds, which is a convex combination of the first Chern Ricci curvature and holomorphic sec…
WoW: Towards a World omniscient World model Through Embodied Interaction
Xiaowei Chi, Peidong Jia, Chun-Kai Fan +33
Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely…
Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
Hanze Li, Jinhao You, Yichen Guo +3
Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations -- content that is misaligne…
High-Resolution Segmentation of Tooth Root Fuzzy Edge Based on Polynomial Curve Fitting with Landmark Detection
Yunxiang Li, Yifan Zhang, Yaqi Wang +7
As the most economical and routine auxiliary examination in the diagnosis of root canal treatment, oral X-ray has been widely used by stomatologists. It is still challenging to seg…
Central frequency measurement of the HLS-II storage ring
Jiajun Zheng, Yongliang Yang, Baogen Sun +3
Central frequency is a key parameter of storage rings. This paper presents the measurement of central frequency of the HLS-II storage ring using the sextupole modulation method. Fi…
Positive curvature operator, projective manifold and rational connectedness
Kai Tang
In his recent work \cite{Y1}, X. Yang proved a conjecture raised by Yau in 1982 (\cite{Yau82}), which states that any compact Kähler manifold with positive holomorphic sectional c…
expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling
Mingxiong Lin, Zhangquan Gong, Maowen Tang +6
Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, where Group Relative Policy Optimization (GRPO) serves as the…
DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model
Jingke Wang, Zhenru Zhao, Shuangming Lei +8
Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow language guidances. However,…
Practical quantum simulation of small-scale non-Hermitian dynamics
Hongfeng Liu, Xiaodong Yang, Kai Tang +5
Non-Hermitian quantum systems have recently attracted considerable attention due to their exotic properties. Though many experimental realizations of non-Hermitian systems have bee…
Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection
Yuhang Yang, Kai Tang, Chao Ye +4
Debt collection is a critical negotiation task in the financial industry, with strong practical relevance and exceptional academic value as a behaviorally rich, high-stakes testbed…
Floquet Engineering of Anisotropic Transverse Interactions in Superconducting Qubits
Yongqi Liang, Wenhui Huang, Libo Zhang +15
Superconducting transmon qubits have established as a leading candidate for quantum computation, as well as a flexible platform for exploring exotic quantum phases and dynamics. Ho…
No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization
Wenhang Shi, Yiren Chen, Shuqing Bian +6
Prompt engineering is crucial for leveraging the full potential of large language models (LLMs). While automatic prompt optimization offers a scalable alternative to costly manual…
Monocular Event-Inertial Odometry with Adaptive decay-based Time Surface and Polarity-aware Tracking
Kai Tang, Xiaolei Lang, Yukai Ma +4
Event cameras have garnered considerable attention due to their advantages over traditional cameras in low power consumption, high dynamic range, and no motion blur. This paper pro…
ChangeAnywhere: Sample Generation for Remote Sensing Change Detection via Semantic Latent Diffusion Model
Kai Tang, Jin Chen
Remote sensing change detection (CD) is a pivotal technique that pinpoints changes on a global scale based on multi-temporal images. With the recent expansion of deep learning, sup…
Quasi-positive mixed curvature, vanishing theorems, and rational connectedness
Kai Tang
In this paper, we consider {\em mixed curvature} , which is a convex combination of Ricci curvature and holomorphic sectional curvature introduced by Chu-Lee-Tam…
Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation
Dayuan Chen, Kai Tang, Yukuan Zhang +2
This paper presents a phase-conditioned, force-aware framework for robust deformable object manipulation. Standard imitation learning policies such as Action Chunking with Transfor…
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
Kai Tang, Jinhao You, Bohua Zhang +6
Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering. However, they remain su…
Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecasting
Qi Xiong, Kai Tang, Minbo Ma +3
Long-term time series forecasting (LTSF) is a critical task across diverse domains. Despite significant advancements in LTSF research, we identify a performance bottleneck in exist…
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
Yichen Guo, Kai Tang, Fenglai Lin +5
Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucination, generating content inconsistent with the input image. Recent…
rank-3 generalized Clifford manifold and its twistor space
Guangzhen Ren, Kai Tang, Qingyan Wu
We introduce the notion of a rank-3 generalized Clifford manifold, defined by a triple of generalized complex structures satisfying Clifford-type relations. We show that every such…
Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM
Xiaolei Lang, Jiajun Lv, Kai Tang +5
This paper presents the first photo-realistic LiDAR-Inertial-Camera Gaussian Splatting SLAM system that simultaneously addresses visual quality, geometric accuracy, and real-time p…
TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motion
Weishi Mi, Yong Bao, Xiaowei Chi +7
The vision-language-action (VLA) paradigm has enabled powerful robotic control by leveraging vision-language models, but its reliance on large-scale, high-quality robot data limits…
On almost nonpositive -Ricci curvature
Kai Tang
Motivated by the recent work of Chu-Lee-Tam on the nefness of canonical line bundle for compact Kähler manifolds with nonpositive -Ricci curvature, we consider a natural notion…
Geodesic Distance Field-based Curved Layer Volume Decomposition for Multi-Axis Support-free Printing
Yamin Li, Dong He, Xiangyu Wang +1
This paper presents a new curved layer volume decomposition method for multi-axis support-free printing of freeform solid parts. Given a solid model to be printed that is represent…
Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
Kai Tang, Jinhao You, Yichen Guo +8
Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucinations, where generated content is inconsistent with the input image…
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Tao Chen, Gangwei Jiang, Pengyu Cheng +10
Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current rew…
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
Dongxu Zhang, Yiding Sun, Zihao Guo +5
Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may…
Hardware-Efficient Stabilization of Entanglement via Engineered Dissipation in Superconducting Circuits
Changling Chen, Kai Tang, Yuxuan Zhou +8
Generation and preservation of quantum entanglement are among the primary tasks in quantum information processing. State stabilization via quantum bath engineering offers a resourc…
Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering
Tianyi Chen, Haobo Wang, Kai Tang +5
Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining robustness against missing vi…
MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
Chenxi Li, Yichen Guo, Benfang Qian +5
Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatic…
GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling
Guangcheng Zhu, Shenzhi Yang, Haobo Wang +9
Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation cost…
Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs
Yuming Yan, Shuo Yang, Kai Tang +7
Vision-Language Models (VLMs) demonstrate remarkable general-purpose capabilities but often fall short in specialized domains such as medical imaging or geometric problem-solving.…
SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
Xiaojun Hou, Jiazheng Xing, Yijie Qian +8
Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was i…
Experimental quantum simulation of non-Hermitian dynamical topological states using stochastic Schrödinger equation
Zidong Lin, Lin Zhang, Xinyue Long +8
Noise is ubiquitous in real quantum systems, leading to non-Hermitian quantum dynamics, and may affect the fundamental states of matter. Here we report in experiment a quantum simu…
AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy
Yunxiang Li, Guodong Zeng, Yifan Zhang +10
Accurate evaluation of the treatment result on X-ray images is a significant and challenging step in root canal therapy since the incorrect interpretation of the therapy results wi…
Superconducting nanowire single photon detector at 532 nm and demonstration in satellite laser ranging
Hao Li, Sijing Chen, Lixing You +10
Superconducting nanowire single-photon detectors (SNSPDs) at a wavelength of 532 nm were designed and fabricated aiming to satellite laser ranging (SLR) applications. The NbN SNSPD…
The -Bochner formulas for holomorphic mappings between Hermitian manifolds and their applications
Kai Tang
In this paper, we derive some -Bochner formulas for holomorphic maps between Hermitian manifolds. As applications, we prove some Schwarz lemma type est…
MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware
Xianpeng Zhang, Jiahua Yang, Dongyu Chen +7
The paper presents a benchmark for multimodal long-document summarization and a two-stage training framework (MMLDSum-LLM) that incorporates visual-alignment and keyword-aware loss…
From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space
Yue Xu, Yutao Sun, Yihao Liu +7
Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a cons…
Hermitian manifolds with nonpositive holomorphic sectional curvature
Kai Tang
We study compact Kähler manifolds admitting Hermitian metrics with nonpositive holomorphic sectional curvature. We prove that the canonical bundle of such a manifold is nef, remov…
TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
Saisai Yang, Qingyi Huang, Jing Yuan +13
Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significant…
Experimental Realization of a Quantum Refrigerator Driven by Indefinite Causal Orders
Xinfang Nie, Xuanran Zhu, Keyi Huang +11
Indefinite causal order (ICO) is playing a key role in recent quantum technologies. Here, we experimentally study quantum thermodynamics driven by ICO on nuclear spins using the nu…
Constant th-mixed curvature
Weiguo Chen, Kai Tang
In this paper, we consider general th-mixed curvature () for Hermitian manifolds, which is a convex combination of the th Chern Ricci cur…
Entanglement-Enhanced Quantum Metrology in Colored Noise by Quantum Zeno Effect
Xinyue Long, Wan-Ting He, Na-Na Zhang +9
In open quantum systems, the precision of metrology inevitably suffers from the noise. {In Markovian open quantum dynamics, the precision can not be improved by using entangled pro…
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Chang Wu, Junfeng Fang, Houcheng Jiang +5
Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deploym…
--Quasi-Negative Curvature and Positivity of the Canonical Bundle
Kyle Broder, Kai Tang
A recent theorem of Diverio--Trapani and Wu--Yau asserts that a compact Kähler manifold with a Kähler metric of quasi-negative holomorphic sectional curvature is projective and c…
STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
Yichen Guo, Hanze Li, Zonghao Zhang +3
Although large vision-language models (LVLMs) leverage rich visual token representations to achieve strong performance on multimodal tasks, these tokens also introduce significant…
Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning
Minbo Ma, Kai Tang, Huan Li +3
Multivariate Time Series Forecasting (MTSF) has long been a key research focus. Traditionally, these studies assume a fixed number of variables, but in real-world applications, Cyb…
Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast
Kangcheng Liu, Xinhu Zheng, Chaoqun Wang +3
Contrastive learning has recently demonstrated great potential for unsupervised pre-training in 3D scene understanding tasks. However, most existing work randomly selects point fea…
Transverse beam size measurement system using visible synchrotron radiation at HLS II
Kai Tang, Bao-Gen Sun, Yong-Liang Yang +6
An interferometer system and an imaging system using visible synchrotron radiation (SR) have been installed in HLS II storage ring. Simulations of these two systems are given using…
Characterization and Optimization of Tunable Couplers via Adiabatic Control in Superconducting Circuits
Xuan Zhang, Xu Zhang, Changling Chen +6
In the pursuit of scalable superconducting quantum computing, tunable couplers have emerged as a pivotal component, offering the flexibility required for complex quantum operations…
Economic Potential for Hybrid Electric Vehicles in Urban Signal-free Intersections with Decentralized MPC
Kai Tang, Weijie Wang, Xiao Pan +2
The development of electric and connected vehicles as well as automated driving technologies are key towards the smart city, with convenient urban mobility and high energy economy…
Seam-to-Graph Reconstruction for Garment Configuration Alignment
Xuzhao Huang, Kai Tang, Fuyuki Tokuda +2
Seams encode rich structural information about garments but are frequently partially observable in robotic manipulation scenarios. To robustly leverage seam information, we propose…
Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization
Dongyu Chen, Jian Ma, Xianpeng Zhang +5
Optimization is fundamental across numerous disciplines, typically following an iterative process of refining an initial solution to enhance performance. This principle is equally…
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
Kai Tang, Peidong Jia, Zhong Chu +15
Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However, existing safe reinforcement…
RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer
Jinhao You, Shuo Lyu, Zhuohang Lyu +5
Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability…
RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator
Kai Tang, Dipankar Bhattacharya, Hang Xu +3
Robotic fabric manipulation remains challenging due to fabric deformability and occlusions from wrinkles and the manipulator. This paper defines Random-to-Target Fabric Flattening…
On the weighted orthogonal Ricci curvature
Kyle Broder, Kai Tang
We introduce the weighted orthogonal Ricci curvature -- a two-parameter version of Ni--Zheng's orthogonal Ricci curvature. This curvature serves as a very natural object in the stu…
Multi-Axis Support-Free Printing of Freeform Parts with Lattice Infill Structures
Yamin Li, Kai Tang, Dong He +1
In additive manufacturing, infill structures are commonly used to reduce the weight and cost of a solid part. Currently, most infill structure generation methods are based on the c…
Realization of Precise Perforating Using Dynamic Threshold and Physical Plausibility Algorithm for Self-Locating Perforating in Oil and Gas Wells
Si-Yu Xiao, Guo-Hui Ren, Tian-Hao Mao +9
Accurate depth measurement is critical for targeting designated perforation intervals to maximize hydrocarbon recovery. While next-generation automated wireless perforating techniq…
CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Values
Kai Tang, Ji Zhang, Hua Meng +5
Multivariate time series forecasting (MTSF) is a critical task with broad applications in domains such as meteorology, transportation, and economics. Nevertheless, pervasive missin…
On Hermitian manifolds with vanishing curvature
Kyle Broder, Kai Tang
We show that Hermitian metrics with vanishing holomorphic curvature on compact complex manifolds with pseudoeffective canonical bundle are conformally balanced. Pluriclosed metrics…
Coco-LIC: Continuous-Time Tightly-Coupled LiDAR-Inertial-Camera Odometry using Non-Uniform B-spline
Xiaolei Lang, Chao Chen, Kai Tang +4
In this paper, we propose an efficient continuous-time LiDAR-Inertial-Camera Odometry, utilizing non-uniform B-splines to tightly couple measurements from the LiDAR, IMU, and camer…
Control-enhanced quantum metrology under Markovian noise
Yue Zhai, Xiaodong Yang, Kai Tang +5
Quantum metrology is supposed to significantly improve the precision of parameter estimation by utilizing suitable quantum resources. However, the predicted precision can be severe…
Beam size and position measurement based on logarithm processing algorithm in HLS II
Chaocai Cheng, Baogen Sun, Yongliang Yang +9
A logarithm processing algorithm to measure beam transverse size and position is proposed and preliminary experimental results in Hefei Light Source II (HLS II) are given. The algo…
AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model
Zhiwei Jin, Xiaohui Song, Nan Wang +36
In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hu…