Searcharxiv⌕ Search

arXiv subjects

Yue Qiu

Publications and source records attributed to Yue Qiu.

At least 19 recordsLinked to original sources
arXiv2026

Beyond Single Object: Learning 3D Relations with Large Language Models

We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison. We propose a framework for detailed object-level reasoning across multiple objects with three components: (1) MO3D (Multi-Object in 3D), an instruction dataset requiring fine-grained multi-object comparison; (2) Multi-3DLLM, using a minimal Patch-Interaction Transformer (PIT) that models inter-/intra-object relationships while preserving local geometry; (3) Mini-apps, two application-driven benchmarks (Shape Mating, Change Captioning) that probe geometric understanding for practical use. Recent 3D-LLMs and 2D-VLMs perform poorly on these tasks, lacking both comparison-centric design and geometric awareness. In contrast, Multi-3DLLM trained on our mixture data learns geometric reasoning, surpasses all baselines on MO3D, and provides positive transfer to single-object classification.

cs.CV↗
arXiv2026

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy reduction, implicitly assuming that low uncertainty is desirable throughout reasoning. We show instead that reasoning efficiency is governed by the trajectory of uncertainty. CoTs with dominant downward entropy trends are substantially shorter. Motivated by this insight, we propose Entropy Trend Reward (ETR), a trajectory-aware objective that encourages progressive uncertainty reduction while allowing limited local exploration. We integrate ETR into Group Relative Policy Optimization (GRPO) and evaluate it across multiple reasoning models and challenging benchmarks. ETR consistently achieves a superior accuracy-efficiency tradeoff, improving DeepSeek-R1-Distill-7B by 9.9% in accuracy while reducing CoT length by 67% across four benchmarks. Code is available at https://github.com/Xuan1030/ETR

cs.AI↗
arXiv2026

A Collaborative Extended Reality Prototype for 3D Surgical Planning and Visualization

We present a collaborative extended reality (XR) prototype for 3D surgical planning and visualization. Our system consists of three key modules: XR-based immersive surgical planning, cloud-based data management, and coordinated stereoscopic 3D displays for interactive visualization. We describe the overall workflow, core functionalities, implementations and setups. By conducting user studies on a liver resection surgical planning case, we demonstrate the effectiveness of our prototype and provide practical insights to inspire future advances in medical XR collaboration.

cs.HC↗
arXiv2025

VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models

Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image, human users naturally use "visual prompts" (VPs), such as bounding boxes, to provide reference. However, no existing benchmark systematically evaluates the ability of MLLMs to interpret such VPs. This gap leaves it unclear whether current MLLMs can effectively recognize VPs, an intuitive prompting method for humans, and use them to solve problems. To address this limitation, we introduce VP-Bench, a benchmark for assessing MLLMs' capability in VP perception and utilization. VP-Bench employs a two-stage evaluation framework: Stage 1 examines models' ability to perceive VPs in natural scenes, using 30k visualized prompts spanning eight shapes and 355 attribute combinations. Stage 2 investigates the impact of VPs on downstream tasks, measuring their effectiveness in real-world problem-solving scenarios. Using VP-Bench, we evaluate 28 MLLMs, including proprietary systems (e.g., GPT-4o) and open-source models (e.g., InternVL3 and Qwen2.5-VL), and provide a comprehensive analysis of factors that affect VP understanding, such as variations in VP attributes, question arrangement, and model scale. VP-Bench establishes a new reference framework for studying how MLLMs comprehend and resolve grounded referring questions.

cs.CV↗
arXiv2025

Explicit Runge-Kutta schemes for Backward Stochastic Differential Equations

The Butcher theory provides a powerful tool for analyzing order conditions of Runge-Kutta schemes for ordinary differential equations (ODEs); however, such a theory has not yet been well established for backward stochastic differential equations (BSDEs) -- motivating the current work to address this gap. Specifically, we propose a new class of explicit Runge-Kutta schemes for BSDEs. These schemes admit a concise formulation that closely mirrors their ODE counterparts. Building on this formulation, we extend the Butcher theory to the proposed schemes, thereby enabling a symbolic derivation of Taylor expansions for the local truncation errors, and yielding the order conditions. Our approach preserves the elegance and generality of the original Butcher theory: it avoids stage-by-stage error expansions and provides a systematic, stage-inductive analysis, applicable to schemes with any number of stages and any target order. Numerical experiments support the theoretical results.

math.NA↗
arXiv2025

Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems

Tensor neural networks (TNNs) have demonstrated their superiority in solving high-dimensional problems. However, similar to conventional neural networks, TNNs are also influenced by the Frequency Principle, which limits their ability to accurately capture high-frequency features of the solution. In this work, we analyze the training dynamics of TNNs by Fourier analysis and enhance their expressivity for high-dimensional multi-scale problems by incorporating random Fourier features. Leveraging the inherent tensor structure of TNNs, we further propose a novel approach to extract frequency features of high-dimensional functions by performing the Discrete Fourier Transform to one-dimensional component functions. This strategy effectively mitigates the curse of dimensionality. Building on this idea, we propose a frequency-adaptive TNNs algorithm, which significantly improves the ability of TNNs in solving complex multi-scale problems. Extensive numerical experiments are performed to validate the effectiveness and robustness of the proposed frequency-adaptive TNNs algorithm.

cs.LG↗
arXiv2025

Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering

Social intelligence, the ability to interpret emotions, intentions, and behaviors, is essential for effective communication and adaptive responses. As robots and AI systems become more prevalent in caregiving, healthcare, and education, the demand for AI that can interact naturally with humans grows. However, creating AI that seamlessly integrates multiple modalities, such as vision and speech, remains a challenge. Current video-based methods for social intelligence rely on general video recognition or emotion recognition techniques, often overlook the unique elements inherent in human interactions. To address this, we propose the Looped Video Debating (LVD) framework, which integrates Large Language Models (LLMs) with visual information, such as facial expressions and body movements, to enhance the transparency and reliability of question-answering tasks involving human interaction videos. Our results on the Social-IQ 2.0 benchmark show that LVD achieves state-of-the-art performance without fine-tuning. Furthermore, supplementary human annotations on existing datasets provide insights into the model's accuracy, guiding future improvements in AI-driven social intelligence.

cs.CV↗
arXiv2025

CvhSlicer 2.0: Immersive and Interactive Visualization of Chinese Visible Human Data in XR Environments

The study of human anatomy through advanced visualization techniques is crucial for medical research and education. In this work, we introduce CvhSlicer 2.0, an innovative XR system designed for immersive and interactive visualization of the Chinese Visible Human (CVH) dataset. Particularly, our proposed system operates entirely on a commercial XR headset, offering a range of visualization and interaction tools for dynamic 2D and 3D data exploration. By conducting comprehensive evaluations, our CvhSlicer 2.0 demonstrates strong capabilities in visualizing anatomical data, enhancing user engagement and improving educational effectiveness. A demo video is available at https://youtu.be/CfR72S_0N-4

cs.HC↗
arXiv2024

From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning

Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessibility. Previous safe RL methods with natural language constraints typically need to design cost functions manually for each constraint, which requires domain expertise and lacks flexibility. In this paper, we harness the dual role of text in this task, using it not only to provide constraint but also as a training signal. We introduce the Trajectory-level Textual Constraints Translator (TTCT) to replace the manually designed cost function. Our empirical results demonstrate that TTCT effectively comprehends textual constraint and trajectory, and the policies trained by TTCT can achieve a lower violation rate than the standard cost function. Extra studies are conducted to demonstrate that the TTCT has zero-shot transfer capability to adapt to constraint-shift environments.

cs.CL↗
arXiv2024

MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments

We present MS2Mesh-XR, a novel multi-modal sketch-to-mesh generation pipeline that enables users to create realistic 3D objects in extended reality (XR) environments using hand-drawn sketches assisted by voice inputs. In specific, users can intuitively sketch objects using natural hand movements in mid-air within a virtual environment. By integrating voice inputs, we devise ControlNet to infer realistic images based on the drawn sketches and interpreted text prompts. Users can then review and select their preferred image, which is subsequently reconstructed into a detailed 3D mesh using the Convolutional Reconstruction Model. In particular, our proposed pipeline can generate a high-quality 3D mesh in less than 20 seconds, allowing for immersive visualization and manipulation in run-time XR scenes. We demonstrate the practicability of our pipeline through two use cases in XR settings. By leveraging natural user inputs and cutting-edge generative AI capabilities, our approach can significantly facilitate XR-based creative production and enhance user experiences. Our code and demo will be available at: https://yueqiu0911.github.io/MS2Mesh-XR/

cs.CV↗
arXiv2024

Conformal Prediction for Deep Classifier via Label Ranking

Conformal prediction is a statistical framework that generates prediction sets containing ground-truth labels with a desired coverage guarantee. The predicted probabilities produced by machine learning models are generally miscalibrated, leading to large prediction sets in conformal prediction. To address this issue, we propose a novel algorithm named $\textit{Sorted Adaptive Prediction Sets}$ (SAPS), which discards all the probability values except for the maximum softmax probability. The key idea behind SAPS is to minimize the dependence of the non-conformity score on the probability values while retaining the uncertainty information. In this manner, SAPS can produce compact prediction sets and communicate instance-wise uncertainty. Extensive experiments validate that SAPS not only lessens the prediction sets but also broadly enhances the conditional coverage rate of prediction sets.

cs.LG↗
arXiv2024

Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation

Multi-class multi-instance segmentation is the task of identifying masks for multiple object classes and multiple instances of the same class within an image. The foundational Segment Anything Model (SAM) is designed for promptable multi-class multi-instance segmentation but tends to output part or sub-part masks in the "everything" mode for various real-world applications. Whole object segmentation masks play a crucial role for indoor scene understanding, especially in robotics applications. We propose a new domain invariant Real-to-Simulation (Real-Sim) fine-tuning strategy for SAM. We use object images and ground truth data collected from Ai2Thor simulator during fine-tuning (real-to-sim). To allow our Segment Any Object Model (SAOM) to work in the "everything" mode, we propose the novel nearest neighbour assignment method, updating point embeddings for each ground-truth mask. SAOM is evaluated on our own dataset collected from Ai2Thor simulator. SAOM significantly improves on SAM, with a 28% increase in mIoU and a 25% increase in mAcc for 54 frequently-seen indoor object classes. Moreover, our Real-to-Simulation fine-tuning strategy demonstrates promising generalization performance in real environments without being trained on the real-world data (sim-to-real). The dataset and the code will be released after publication.

cs.CV↗
arXiv2024

Resolution invariant deep operator network for PDEs with complex geometries

Neural operators (NO) are discretization invariant deep learning methods with functional output and can approximate any continuous operator. NO have demonstrated the superiority of solving partial differential equations (PDEs) over other deep learning methods. However, the spatial domain of its input function needs to be identical to its output, which limits its applicability. For instance, the widely used Fourier neural operator (FNO) fails to approximate the operator that maps the boundary condition to the PDE solution. To address this issue, we propose a novel framework called resolution-invariant deep operator (RDO) that decouples the spatial domain of the input and output. RDO is motivated by the Deep operator network (DeepONet) and it does not require retraining the network when the input/output is changed compared with DeepONet. RDO takes functional input and its output is also functional so that it keeps the resolution invariant property of NO. It can also resolve PDEs with complex geometries whereas NO fail. Various numerical experiments demonstrate the advantage of our method over DeepONet and FNO.

math.NA↗
arXiv2024

Koopman operator learning using invertible neural networks

In Koopman operator theory, a finite-dimensional nonlinear system is transformed into an infinite but linear system using a set of observable functions. However, manually selecting observable functions that span the invariant subspace of the Koopman operator based on prior knowledge is inefficient and challenging, particularly when little or no information is available about the underlying systems. Furthermore, current methodologies tend to disregard the importance of the invertibility of observable functions, which leads to inaccurate results. To address these challenges, we propose the so-called FlowDMD, aka Flow-based Dynamic Mode Decomposition, that utilizes the Coupling Flow Invertible Neural Network (CF-INN) framework. FlowDMD leverages the intrinsically invertible characteristics of the CF-INN to learn the invariant subspaces of the Koopman operator and accurately reconstruct state variables. Numerical experiments demonstrate the superior performance of our algorithm compared to state-of-the-art methodologies.

math.NA↗
arXiv2024

Sparse discovery of differential equations based on multi-fidelity Gaussian process

Sparse identification of differential equations aims to compute the analytic expressions from the observed data explicitly. However, there exist two primary challenges. Firstly, it exhibits sensitivity to the noise in the observed data, particularly for the derivatives computations. Secondly, existing literature predominantly concentrates on single-fidelity (SF) data, which imposes limitations on its applicability due to the computational cost. In this paper, we present two novel approaches to address these problems from the view of uncertainty quantification. We construct a surrogate model employing the Gaussian process regression (GPR) to mitigate the effect of noise in the observed data, quantify its uncertainty, and ultimately recover the equations accurately. Subsequently, we exploit the multi-fidelity Gaussian processes (MFGP) to address scenarios involving multi-fidelity (MF), sparse, and noisy observed data. We demonstrate the robustness and effectiveness of our methodologies through several numerical experiments.

math.NA↗
arXiv2023

Constrained Spin Systems and KNdS Black Holes

Kerr-Newman de Sitter (KNdS) spacetimes have a rich thermodynamic structure that involves multiple horizons, and so differs in key respects from asymptotically flat or AdS black holes. In this paper, we show that certain features of KNdS spacetimes can be reproduced by a constrained system of $N$ non-interacting spins in a magnetic field. Both the KNdS and spin systems have bounded energy and entropy, a maximum of the entropy in the interior of the energy range, and a symmetry that maps lower energy states to higher energy states with the same entropy. Consequently, both systems have a temperature that can be positive or negative, where the gravitational temperature is defined analogously to that of the spins. We find that the number of spins $N$ corresponds to $1/Λ$ for black holes with very small charge $q$ and rotation parameter $a$, and scales like $\sqrt{(a^2+q^2)/Λ}$ for larger values of $a$ and $q$. By studying constrained spin systems, we provide insight into the thermodynamics of KNdS spacetimes and its quantum mechanical description.

hep-th↗
arXiv2023

Augmented Message Passing Stein Variational Gradient Descent

Stein Variational Gradient Descent (SVGD) is a popular particle-based method for Bayesian inference. However, its convergence suffers from the variance collapse, which reduces the accuracy and diversity of the estimation. In this paper, we study the isotropy property of finite particles during the convergence process and show that SVGD of finite particles cannot spread across the entire sample space. Instead, all particles tend to cluster around the particle center within a certain range and we provide an analytical bound for this cluster. To further improve the effectiveness of SVGD for high-dimensional problems, we propose the Augmented Message Passing SVGD (AUMP-SVGD) method, which is a two-stage optimization procedure that does not require sparsity of the target distribution, unlike the MP-SVGD method. Our algorithm achieves satisfactory accuracy and overcomes the variance collapse problem in various benchmark problems.

cs.LG↗