arXiv subjects

Qing Jiang

Publications and source records attributed to Qing Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Testing for functional white noise in high dimensions

White noise testing is a fundamental problem in time series analysis. Yet it remains largely unsolved for high-dimensional functional time series, despite the growing attention this area has received in recent years, as existing tests are confined to either univariate functional time series or high-dimensional scalar time series. In this paper, we develop a general error-contamination framework for testing white noise in high-dimensional functional time series. We propose a supremum-type test statistic based on cross-autocovariance functions and develop a parametric bootstrap procedure to approximate its null distribution. By imposing a general high-level condition, we derive a new Gaussian approximation result that ensures size control, and establish an asymptotic power guarantee. We then apply our framework to two concrete applications: (i) white noise test for discretely observed functional time series, and (ii) residual-based goodness-of-fit test for functional factor model. For each problem, we verify the corresponding high-level condition to ensure the theoretical validity of our proposed method. Extensive simulations show that our proposed method achieves good finite-sample performance. The practical utility of our proposed method is further illustrated through applications to two real datasets.

stat.ME↗

arXiv2026

ScaleHP: Scale-Mediated Optimization of Coupled Errors for Metric-Space Hand Pose Estimation

In this paper, we present ScaleHP, a unified framework that explicitly represents per-instance metric scale to resolve the coupled errors in calibrated camera-space hand pose estimation. Under the common root-relative-to-global paradigm, camera-space accuracy depends jointly on relative geometry, root localization, and their scale-dependent composition. ScaleHP treats scale as the shared interface among these terms rather than optimizing them in isolation. Its metric-aware 2D-3D Transformer decoder introduces a dedicated scale token that exchanges information with sparse, semantically indexed 2D/3D joint queries, allowing global metric reasoning and local joint geometry to mutually refine one another. A parameter-free calibrated module then recovers root translation from the predicted unit-scale joints, metric scale, and known camera intrinsics. ScaleHP demonstrates state-of-the-art CS-MPJPE on FreiHand (35.8 mm) and, under benchmark-specific training protocols, state-of-the-art PA-MPJPE on FreiHand, DexYCB, and HO3Dv3 (5.0/4.6/5.9 mm), showing that improved global metric localization is attained together with improved local articulation. Ablations further show that scale-pose interaction improves both camera-space accuracy and relative depth geometry.

cs.CV↗

arXiv2026

SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding

General scene perception has progressed from object recognition toward open-vocabulary grounding, part localization, and affordance prediction. Yet these capabilities are often realized as isolated predictions that localize objects, parts, or interaction points without capturing the structured dependencies needed for interaction-oriented scene understanding. To address this gap, we introduce Hierarchical Scene Parsing, an interaction-oriented parsing task that represents physical scenes as explicit scene -> object -> part -> affordance hierarchies with cross-level bindings. We instantiate this task with SceneParser, a VLM-based parser trained for unified hierarchical generation with structural-completion pseudo labels and curriculum learning. To support training and evaluation, we construct SceneParser-Bench, a large-scale benchmark built with a scalable hierarchical data engine, containing 110K training images, a 5K validation split, 777K objects, 1.14M parts, 1.74M affordance annotations, and 1.74M valid object-part-affordance chain instances. We further introduce Level-1 to Level-3 conditional metrics and ParseRate to evaluate localization, cross-level binding, and hierarchical completeness. Experiments show that existing MLLMs and perception-stitching pipelines struggle with hierarchical parsing on our SceneParser-Bench, while SceneParser achieves stronger structure-aware performance. Besides, ablations, evaluations on COCO and AGD20K, and a downstream planning probe demonstrate that our SceneParser is compatible with conventional tasks and provides an actionable representation for visual understanding.

cs.CV↗

arXiv2026

Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models

In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing VLA models learn a direct "Sense-to-Act" mapping from multimodal observations to robot actions. While effective within the training distribution, such tightly coupled policies are brittle under out-of-domain (OOD) shifts and difficult to correct when failures occur. Although recent embodied Chain-of-Thought (CoT) approaches expose intermediate reasoning, they still lack a mechanism for incorporating human spatial guidance, limiting their ability to resolve visual ambiguities or recover from mistakes. To address this gap, our framework allows users to optionally guide the policy with spatial priors, such as affordance points, boxes, and traces, which the subsequent reasoning process can directly condition on. Based on these inputs, the model generates a unified spatial-visual Chain-of-Thought that integrates external guidance with internal task planning, aligning human visual intent with autonomous decision-making. For practical deployment, we further couple the reasoning module with a lightweight reactive action head for efficient action execution. Extensive experiments demonstrate the effectiveness of our approach. On the in-domain SimplerEnv WidowX benchmark, our framework achieves a state-of-the-art 81.2% success rate. Under OOD visual shifts and spatial ambiguities, a single visual interaction substantially improves task success over existing methods, highlighting the value of interactive reasoning for failure recovery in embodied control. More details of the project can be found here: https://github.com/FutianLabs/GTA-VLA.

cs.RO↗

arXiv2026

V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators

Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely restricted to the language domain, treating visual input as a static, reasoning-agnostic preamble rather than a dynamic participant. Consequently, current models act as passive observers, unable to re-examine visual details to ground their evolving reasoning states. To overcome this, we propose V-Reflection, a framework that transforms the MLLM into an active interrogator through a "think-then-look" visual reflection mechanism. During reasoning, latent states function as dynamic probes that actively interrogate the visual feature space, grounding each reasoning step for task-critical evidence. Our approach employs a two-stage distillation strategy. First, the Box-Guided Compression Module (BCM) establishes stable pixel-to-latent targets through explicit spatial grounding. Next, a Dynamic Autoregressive Compression (DAC) module maps the model's hidden states into dynamic probes that interrogate the global visual feature map. By distilling the spatial expertise of the BCM teacher into the DAC student, V-Reflection internalizes the ability to localize task-critical evidence. During inference, both modules remain entirely inactive, maintaining a purely end-to-end autoregressive decoding in the latent space with optimal efficiency. Extensive experiments demonstrate the effectiveness of our V-Reflection across six perception-intensive benchmarks, significantly narrowing the fine-grained perception gap. Visualizations confirm that latent reasoning autonomously localizes task-critical visual evidence.

cs.CV↗

arXiv2026

SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs

3D Large Vision-Language Models (3D LVLMs) built upon Large Language Models (LLMs) have achieved remarkable progress across various multimodal tasks. However, their inherited position-dependent modeling mechanism, Rotary Position Embedding (RoPE), remains suboptimal for 3D multimodal understanding. The vanilla RoPE formulation fails to preserve essential three-dimensional spatial structures when encoding 3D tokens, and its relative distance computation overlooks angular dependencies, hindering the model's ability to capture directional variations in visual representations. To overcome these limitations, we introduce Spherical Coordinate-based Positional Embedding (SoPE). Our method maps point-cloud token indices into a 3D spherical coordinate space, enabling unified modeling of spatial locations and directional angles. This formulation preserves the inherent geometric structure of point-cloud data, enhances spatial awareness, and yields more consistent and expressive geometric representations for multimodal learning. In addition, we introduce a multi-scale frequency mixing strategy to fuse feature information across different frequency domains. Experimental results on multiple 3D scene benchmarks validate the effectiveness of our approach, while real-world deployment experiments further demonstrate its strong generalization capability.

cs.CV↗

arXiv2026

Determinants of Self-Interstitial Energetics in Refractory High-Entropy Alloys

Self-interstitials play a central role in governing the mechanical and anti-irradiation properties of refractory high-entropy alloys (RHEAs), however, the prediction of interstitial formation energies (Ef) is formidable due to the chemically complex environments in RHEAs. Herein, we develop a framework based on the tight-binding model to quantify the effects of complex alloying and lattice distortion on Ef. Our scheme reveals that Ef is jointly determined by the average d-band center of RHEAs and the d-band width of interstitial sites. Notably, the d-band width mainly depends on the interatomic hopping matrix and atomic size-determined coordination number, which together make the metallic bonding around interstitials in RHEAs resemble the distance-dependence law of van der Waals forces. By capturing d-band coupling character, our descriptor describes both interstitial configurations within a universal framework. Our model reveals a new physical picture of interstitial formation, providing a useful tool for the design of high-performance RHEAs.

cond-mat.mtrl-sci↗

arXiv2025

T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection

Object detection methods have evolved from closed-set to open-set paradigms over the years. Current open-set object detectors, however, remain constrained by their exclusive reliance on positive indicators based on given prompts like text descriptions or visual exemplars. This positive-only paradigm experiences consistent vulnerability to visually similar but semantically different distractors. We propose T-Rex-Omni, a novel framework that addresses this limitation by incorporating negative visual prompts to negate hard negative distractors. Specifically, we first introduce a unified visual prompt encoder that jointly processes positive and negative visual prompts. Next, a training-free Negating Negative Computing (NNC) module is proposed to dynamically suppress negative responses during the probability computing stage. To further boost performance through fine-tuning, our Negating Negative Hinge (NNH) loss enforces discriminative margins between positive and negative embeddings. T-Rex-Omni supports flexible deployment in both positive-only and joint positive-negative inference modes, accommodating either user-specified or automatically generated negative examples. Extensive experiments demonstrate remarkable zero-shot detection performance, significantly narrowing the performance gap between visual-prompted and text-prompted methods while showing particular strength in long-tailed scenarios (51.2 AP_r on LVIS-minival). This work establishes negative prompts as a crucial new dimension for advancing open-set visual recognition systems.

cs.CV↗

arXiv2025

Detect Anything via Next Point Prediction

Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low recall rate, duplicate predictions, coordinate misalignment, etc. In this work, we bridge this gap and propose Rex-Omni, a 3B-scale MLLM that achieves state-of-the-art object perception performance. On benchmarks like COCO and LVIS, Rex-Omni attains performance comparable to or exceeding regression-based models (e.g., DINO, Grounding DINO) in a zero-shot setting. This is enabled by three key designs: 1) Task Formulation: we use special tokens to represent quantized coordinates from 0 to 999, reducing the model's learning difficulty and improving token efficiency for coordinate prediction; 2) Data Engines: we construct multiple data engines to generate high-quality grounding, referring, and pointing data, providing semantically rich supervision for training; \3) Training Pipelines: we employ a two-stage training process, combining supervised fine-tuning on 22 million data with GRPO-based reinforcement post-training. This RL post-training leverages geometry-aware rewards to effectively bridge the discrete-to-continuous coordinate prediction gap, improve box accuracy, and mitigate undesirable behaviors like duplicate predictions that stem from the teacher-guided nature of the initial SFT stage. Beyond conventional detection, Rex-Omni's inherent language understanding enables versatile capabilities such as object referring, pointing, visual prompting, GUI grounding, spatial referring, OCR and key-pointing, all systematically evaluated on dedicated benchmarks. We believe that Rex-Omni paves the way for more versatile and language-aware visual perception systems.

cs.CV↗

arXiv2025

An Analytic Model to Determine the Interstitial-Solute Energetics and Underlying Mechanism in Refractory High-Entropy Alloys

The solution and diffusion of interstitial non-metallic solutes (INSs) like H, He, O, C, N, P, and S is common in refractory high-entropy alloys (RHEAs) and essentially controls the RHEAs properties. However, the disorder local chemical environments of RHEAs hinder the quantitative prediction of the stability and diffusivity of INSs and the understanding of the underlying mechanism. Based on the tight-binding models, we propose an analytic model for determining the stability and diffusivity of INSs in RHEAs, by approximating the bonding length between INSs and their neighbors with the atomic radius of the neighbors in elemental states. This predictive model identifies that the energetics of INSs depends linearly on the d-band width of their neighbors, with the slope determined by the valence of INSs. Our scheme provides an electronic-level understanding of INSs in RHEAs and explains key experimental observations, which can serve as an effective tool for designing advanced RHEAs.

cond-mat.mtrl-sci↗

arXiv2025

Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding box prediction task, offering limited interpretability and struggling to reject expressions with no matching object. In this work, we propose Rex-Thinker, a model that formulates object referring as an explicit CoT reasoning task. Given a referring expression, we first identify all candidate object instances corresponding to the referred object category. Rex-Thinker then performs step-by-step reasoning over each candidate to assess whether it matches the given expression, before making a final prediction. To support this paradigm, we construct a large-scale CoT-style referring dataset named HumanRef-CoT by prompting GPT-4o on the HumanRef dataset. Each reasoning trace follows a structured planning, action, and summarization format, enabling the model to learn decomposed, interpretable reasoning over object candidates. We then train Rex-Thinker in two stages: a cold-start supervised fine-tuning phase to teach the model how to perform structured reasoning, followed by GRPO-based RL learning to improve accuracy and generalization. Experiments show that our approach outperforms standard baselines in both precision and interpretability on in-domain evaluation, while also demonstrating improved ability to reject hallucinated outputs and strong generalization in out-of-domain settings.

cs.CV↗

arXiv2025

Safe Individualized Treatment Rules with Controllable Harm Rates

Estimating individualized treatment rules (ITRs) is crucial for tailoring interventions in precision medicine. Typical ITR estimation methods rely on conditional average treatment effects (CATEs) to guide treatment assignments. However, such methods overlook individual-level harm within covariate-specific subpopulations, potentially leading many individuals to experience worse outcomes under CATE-based ITRs. In this article, we aim to estimate ITRs that maximize the reward while ensuring that the harm rate induced by the ITR remains below a pre-specified threshold. We first derive the explicit form of the oracle ITR. However, the oracle ITR is not achievable without strong assumptions, as the harm rate is generally unidentifiable due to its dependence on the joint distribution of potential outcomes. To address this, we propose two strategies for estimating ITRs with a harm rate constraint under partial identification and establish their large-sample properties. By accounting for both reward and harm, our method provides a reliable solution for developing ITRs in high-stakes domains where harm is a critical consideration. Extensive simulations demonstrate the effectiveness of the proposed methods in controlling harm rates. We apply the proposed method to analyze two real-world datasets from a new perspective, assessing the potential reduction in harm rate compared with historical interventions.

stat.ME↗

arXiv2025

Referring to Any Person

Humans are undoubtedly the most important participants in computer vision, and the ability to detect any individual given a natural language description, a task we define as referring to any person, holds substantial practical value. However, we find that existing models generally fail to achieve real-world usability, and current benchmarks are limited by their focus on one-to-one referring, that hinder progress in this area. In this work, we revisit this task from three critical perspectives: task definition, dataset design, and model architecture. We first identify five aspects of referable entities and three distinctive characteristics of this task. Next, we introduce HumanRef, a novel dataset designed to tackle these challenges and better reflect real-world applications. From a model design perspective, we integrate a multimodal large language model with an object detection framework, constructing a robust referring model named RexSeek. Experimental results reveal that state-of-the-art models, which perform well on commonly used benchmarks like RefCOCO/+/g, struggle with HumanRef due to their inability to detect multiple individuals. In contrast, RexSeek not only excels in human referring but also generalizes effectively to common object referring, making it broadly applicable across various perception tasks. Code is available at https://github.com/IDEA-Research/RexSeek

cs.CV↗

arXiv2024

Analytic model for grain-boundary segregation ener-gies in metal polycrystal

Solute segregation at grain boundaries (GBs) of polycrystals strongly impacts the mechanical properties of metals including strength, fracture, embrittlement, and corrosion. However, the complexity of GB structures and the large chemical space of solutes and matrices impede the understanding of segregation. Herein, we identify a physical-based determinant, by unifying the effects of plastic strain and bonding breaking, for determining the segregation energies at GBs. By further combining with the usual coordination number, atomic radius of solutes and matrices, and cohesive energy of matrices, we build an analytic framework to predict segregation energies of polycrystal GBs across various solutes and matrices. These findings indicate an unusual Coulombic-like and localized nature of the bonding at polycrystal GBs and bulk metallic glasses (BMGs). Our scheme not only uncovers the coupling rule of solutes and matrices for GB segregation in polycrystals, but also provides an effective tool for the design of high-performance alloys.

cond-mat.mtrl-sci↗

arXiv2024

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Perception and understanding are two pillars of computer vision. While multimodal large language models (MLLM) have demonstrated remarkable visual understanding capabilities, they arguably lack accurate perception abilities, e.g. the stage-of-the-art model Qwen2-VL only achieves a 43.9 recall rate on the COCO dataset, limiting many tasks requiring the combination of perception and understanding. In this work, we aim to bridge this perception gap from both model designing and data development perspectives. We first introduce ChatRex, an MLLM with a decoupled perception design. Instead of having the LLM directly predict box coordinates, we feed the output boxes from a universal proposal network into the LLM, allowing it to output the corresponding box indices to represent its detection results, turning the regression task into a retrieval-based task that LLM handles more proficiently. From the data perspective, we build a fully automated data engine and construct the Rexverse-2M dataset which possesses multiple granularities to support the joint training of perception and understanding. After a three-stage training approach, ChatRex demonstrates strong perception and understanding performance, and the combination of these two capabilities also unlocks many attractive applications, demonstrating their complementary roles in MLLM. Code is available at https://github.com/IDEA-Research/ChatRex.

cs.CV↗

arXiv2024

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 AP and 5.0 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.

cs.CV↗

arXiv2024

Propagation of Shear Horizontal Acoustic Waves in a Quartz Plate with a Fluid Layer for Liquid Sensor Application

We study the propagation of shear horizontal (SH) acoustic waves in a quartz elastic plate in contact with a viscous fluid layer of a finite thickness as an acoustic wave sensor for measuring fluid viscosity or density. The first order elastic plate theory by Mindlin and the theory of Newtonian fluids are used. An equation for determining the dispersion relations of the SH waves is obtained. Approximate dispersion relations for long waves are given analytically. Numerical results showing the effects of the fluid on SH wave characteristics are presented.

physics.app-ph↗

arXiv2024

Large-scale Multiple Testing of Cross-covariance Functions with Applications to Functional Network Models

The estimation of functional networks through functional covariance and graphical models have recently attracted increasing attention in settings with high dimensional functional data, where the number of functional variables p is comparable to, and maybe larger than, the number of subjects. However, the existing methods all depend on regularization techniques, which make it unclear how the involved tuning parameters are related to the number of false edges. In this paper, we first reframe the functional covariance model estimation as a tuning-free problem of simultaneously testing p(p-1)/2 hypotheses for cross-covariance functions, and introduce a novel multiple testing procedure. We then explore the multiple testing procedure under a general error-contamination framework and establish that our procedure can control false discoveries asymptotically. Additionally, we demonstrate that our proposed methods for two concrete examples: the functional covariance model for discretely observed functional data and, importantly, the more challenging functional graphical model, can be seamlessly integrated into the general error-contamination framework, and, with verifiable conditions, achieve theoretical guarantees on effective false discovery control. Finally, we showcase the superiority of our proposals through extensive simulations and brain connectivity analysis of two neuroimaging datasets.

math.ST↗