arXiv subjects

Yao Jiang

Publications and source records attributed to Yao Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?

The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM). SaliLLM uncovers a striking capability mismatch: MLLMs outperform state-of-the-art (SOTA) methods in localization, yet remain substantially weaker in segmentation. Further analyses attribute this gap primarily to mismatches between MLLMs and annotations over foreground cardinality, granularity, and extent. Motivated by this diagnosis, we recast zero-shot SOD as protocol-aligned Foreground Organization and introduce the first training-free framework that leverages Gestalt-inspired Collaborative attention for Unified SOD (FOCUS). FOCUS couples top-down Bayesian-surprise calibration of protocol-conditioned foreground granularity with bottom-up propagation of MLLMs evidence over entity-centric perceptual manifolds induced by self-supervised features, yielding coherent object extents as prompts for a general segmenter. Across 13 RGB, RGB-D, and RGB-T SOD benchmarks, FOCUS generally surpasses SOTA methods without training, reducing mean absolute error by 11\%, 34\%, and 48\% compared with fully, weakly, and self-supervised methods, respectively. Our findings signal the renaissance of SOD: from task-specific supervision to zero-shot foreground organization. Code is available in the supplementary material.

cs.CV↗

arXiv2026

Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA

High-resolution visual question answering (HR-VQA) is often treated as a problem of insufficient evidence acquisition, where failing multimodal large language models must inspect images again through cropping, re-encoding, or multi-round search. We show that this view is incomplete: in many cases, fine-grained evidence has already survived visual encoding and become identifiable and influential within an intermediate-layer routing window, but is later diluted before answer generation. We propose Thinking-Once, a \textbf{training-free, single-visual-pass} evidence-routing method that reconstructs question-conditioned attention at this window, preserves core entity tokens and compact background context, and routes this evidence to later layers without extra visual encoding. Across five base models, Thinking-Once consistently improves or matches the corresponding base setting, increasing the average scores on V$^*$Bench, HRBench-4K, and HRBench-8K by \textit{+3.1}, \textit{+3.0}, and \textit{+2.7} points while reducing the average peak memory by about 4,GB. On Qwen2.5-VL-7B, it improves the three benchmarks by \textit{+9.9}, \textit{+4.6}, and \textit{+5.5} points, raising the cross-benchmark mean from 72.5 to 79.1. With the ZwZ-8B base model, Thinking-Once reaches a mean score of 82.7. Against 11 open-source HR-VQA baselines, it obtains the best or tied-best score on all three benchmark averages and the best overall mean; for example, compared with DeepScan, it reduces V$^*$Bench inference time by \textbf{97.2\%} while improving the cross-benchmark mean from 77.8 to 79.1. These results show that HR-VQA can be improved by routing already encoded evidence rather than repeatedly acquiring new visual inputs. Code is available in the appendix.

cs.CV↗

arXiv2026

StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows

Addressing a structural-engineering request requires more than a single answer; it requires a chain of interdependent artifacts: interpreted requirements, a computable model, validation records, solver outputs, applicable engineering checks, and a final report. Evaluations centered on question answering or script generation may therefore reward fluent outputs even when the underlying workflow is incomplete, inconsistent, or non-executable. We present StructureClaw, an artifact-centered workbench in which LLM agents operate through governed engineering skills, typed tools, shared artifact state, and local analysis backends, together with StructureClaw-Bench, an executable benchmark of 150 controlled scenarios spanning standard workflows, interactive robustness, and multimodal structural-model reconstruction. Its analyzable standard and multimodal cases require both strict one-to-one structural-model matching and numerical-response agreement with frozen reference responses from the selected analysis engine; interactive cases instead require positive clarification or recovery evidence together with safe non-execution when appropriate. A trial succeeds only when every fixture-required assertion passes. Across nine text-agent configurations, generic-only execution passed the model-artifact check in 87.0% of retained outcomes but achieved only 22.0% E2E Success, whereas automatic StructureClaw reached 82.9%. Interactive and multimodal evaluations further identify semantic state consistency and executable model reconstruction as the dominant remaining bottlenecks. The code and benchmark are available at https://github.com/structureclaw/structureclaw.

cs.SE↗

arXiv2026

Camouflage-aware Image-Text Retrieval via Expert Collaboration

Camouflaged scene understanding (CSU) has attracted significant attention due to its broad practical implications. However, in this field, robust image-text cross-modal alignment remains under-explored, hindering deeper understanding of camouflaged scenarios and their related applications. To this end, we focus on the typical image-text retrieval task, and formulate a new task dubbed ``camouflage-aware image-text retrieval'' (CA-ITR). We first construct a dedicated camouflage image-text retrieval dataset (CamoIT), comprising $\sim$10.5K samples with multi-granularity textual annotations. Benchmark results conducted on CamoIT reveal the underlying challenges of CA-ITR for existing cutting-edge retrieval techniques, which are mainly caused by objects' camouflage properties as well as those complex image contents. As a solution, we propose a camouflage-expert collaborative network (CECNet), which features a dual-branch visual encoder: one branch captures holistic image representations, while the other incorporates a dedicated model to inject representations of camouflaged objects. A novel confidence-conditioned graph attention (C\textsuperscript{2}GA) mechanism is incorporated to exploit the complementarity across branches. Comparative experiments show that CECNet achieves $\sim$29% overall CA-ITR accuracy boost, surpassing seven representative retrieval models. The dataset and code will be available at https://github.com/jiangyao-scu/CA-ITR.

cs.CV↗

arXiv2025

Promoting Segment Anything Model towards Highly Accurate Dichotomous Image Segmentation

The Segment Anything Model (SAM) represents a significant breakthrough into foundation models for computer vision, providing a large-scale image segmentation model. However, despite SAM's zero-shot performance, its segmentation masks lack fine-grained details, particularly in accurately delineating object boundaries. Therefore, it is both interesting and valuable to explore whether SAM can be improved towards highly accurate object segmentation, which is known as the dichotomous image segmentation (DIS) task. To address this issue, we propose DIS-SAM, which advances SAM towards DIS with extremely accurate details. DIS-SAM is a framework specifically tailored for highly accurate segmentation, maintaining SAM's promptable design. DIS-SAM employs a two-stage approach, integrating SAM with a modified advanced network that was previously designed to handle the prompt-free DIS task. To better train DIS-SAM, we employ a ground truth enrichment strategy by modifying original mask annotations. Despite its simplicity, DIS-SAM significantly advances the SAM, HQ-SAM, and Pi-SAM ~by 8.5%, ~6.9%, and ~3.7% maximum F-measure. Our code at https://github.com/Tennine2077/DIS-SAM

cs.CV↗

arXiv2025

Enhancing Adaptivity of Two-Fingered Object Reorientation Using Tactile-based Online Optimization of Deconstructed Actions

Object reorientation is a critical task for robotic grippers, especially when manipulating objects within constrained environments. The task poses significant challenges for motion planning due to the high-dimensional output actions with the complex input information, including unknown object properties and nonlinear contact forces. Traditional approaches simplify the problem by reducing degrees of freedom, limiting contact forms, or acquiring environment/object information in advance, which significantly compromises adaptability. To address these challenges, we deconstruct the complex output actions into three fundamental types based on tactile sensing: task-oriented actions, constraint-oriented actions, and coordinating actions. These actions are then optimized online using gradient optimization to enhance adaptability. Key contributions include simplifying contact state perception, decomposing complex gripper actions, and enabling online action optimization for handling unknown objects or environmental constraints. Experimental results demonstrate that the proposed method is effective across a range of everyday objects, regardless of environmental contact. Additionally, the method exhibits robust performance even in the presence of unknown contacts and nonlinear external disturbances.

cs.RO↗

arXiv2025

Enhancing Regrasping Efficiency Using Prior Grasping Perceptions with Soft Fingertips

Grasping the same object in different postures is often necessary, especially when handling tools or stacked items. Due to unknown object properties and changes in grasping posture, the required grasping force is uncertain and variable. Traditional methods rely on real-time feedback to control the grasping force cautiously, aiming to prevent slipping or damage. However, they overlook reusable information from the initial grasp, treating subsequent regrasping attempts as if they were the first, which significantly reduces efficiency. To improve this, we propose a method that utilizes perception from prior grasping attempts to predict the required grasping force, even with changes in position. We also introduce a calculation method that accounts for fingertip softness and object asymmetry. Theoretical analyses demonstrate the feasibility of predicting grasping forces across various postures after a single grasp. Experimental verifications attest to the accuracy and adaptability of our prediction method. Furthermore, results show that incorporating the predicted grasping force into feedback-based approaches significantly enhances grasping efficiency across a range of everyday objects.

cs.RO↗

arXiv2025

Modeling, Simulation, and Application of Spatio-Temporal Characteristics Detection in Incipient Slip

Incipient slip detection provides critical feedback for robotic grasping and manipulation tasks. However, maintaining its adaptability under diverse object properties and complex working conditions remains challenging. This article highlights the importance of completely representing spatio-temporal features of slip, and proposes a novel approach for incipient slip modeling and detection. Based on the analysis of localized displacement phenomenon, we establish the relationship between the characteristic strain rate extreme events and the local slip state. This approach enables the detection of both the spatial distribution and temporal dynamics of stick-slip regions. Also, the proposed method can be applied to strain distribution sensing devices, such as vision-based tactile sensors. Simulations and prototype experiments validated the effectiveness of this approach under varying contact conditions, including different contact geometries, friction coefficients, and combined loads. Experiments demonstrated that this method not only accurately and reliably delineates incipient slip, but also facilitates friction parameter estimation and adaptive grasping control.

cs.RO↗

arXiv2024

Learning Gentle Grasping from Human-Free Force Control Demonstration

Humans can steadily and gently grasp unfamiliar objects based on tactile perception. Robots still face challenges in achieving similar performance due to the difficulty of learning accurate grasp-force predictions and force control strategies that can be generalized from limited data. In this article, we propose an approach for learning grasping from ideal force control demonstrations, to achieve similar performance of human hands with limited data size. Our approach utilizes objects with known contact characteristics to automatically generate reference force curves without human demonstrations. In addition, we design the dual convolutional neural networks (Dual-CNN) architecture which incorporats a physics-based mechanics module for learning target grasping force predictions from demonstrations. The described method can be effectively applied in vision-based tactile sensors and enables gentle and stable grasping of objects from the ground. The described prediction model and grasping strategy were validated in offline evaluations and online experiments, and the accuracy and generalizability were demonstrated.

cs.RO↗

arXiv2024

An Adaptive Grasping Force Tracking Strategy for Nonlinear and Time-Varying Object Behaviors

Accurate grasp force control is one of the key skills for ensuring successful and damage-free robotic grasping of objects. Although existing methods have conducted in-depth research on slip detection and grasping force planning, they often overlook the issue of adaptive tracking of the actual force to the target force when handling objects with different material properties. The optimal parameters of a force tracking controller are significantly influenced by the object's stiffness, and many adaptive force tracking algorithms rely on stiffness estimation. However, real-world objects often exhibit viscous, plastic, or other more complex nonlinear time-varying behaviors, and existing studies provide insufficient support for these materials in terms of stiffness definition and estimation. To address this, this paper introduces the concept of generalized stiffness, extending the definition of stiffness to nonlinear time-varying grasp system models, and proposes an online generalized stiffness estimator based on Long Short-Term Memory (LSTM) networks. Based on generalized stiffness, this paper proposes an adaptive parameter adjustment strategy using a PI controller as an example, enabling dynamic force tracking for objects with varying characteristics. Experimental results demonstrate that the proposed method achieves high precision and short probing time, while showing better adaptability to non-ideal objects compared to existing methods. The method effectively solves the problem of grasp force tracking in unknown, nonlinear, and time-varying grasp systems, demonstrating the generalization capability of our neural network and enhancing the robotic grasping ability in unstructured environments.

cs.RO↗

arXiv2024

Effectiveness Assessment of Recent Large Vision-Language Models

The advent of large vision-language models (LVLMs) represents a remarkable advance in the quest for artificial general intelligence. However, the model's effectiveness in both specialized and general tasks warrants further investigation. This paper endeavors to evaluate the competency of popular LVLMs in specialized and general tasks, respectively, aiming to offer a comprehensive understanding of these novel models. To gauge their effectiveness in specialized tasks, we employ six challenging tasks in three different application scenarios: natural, healthcare, and industrial. These six tasks include salient/camouflaged/transparent object detection, as well as polyp detection, skin lesion detection, and industrial anomaly detection. We examine the performance of three recent open-source LVLMs, including MiniGPT-v2, LLaVA-1.5, and Shikra, on both visual recognition and localization in these tasks. Moreover, we conduct empirical investigations utilizing the aforementioned LVLMs together with GPT-4V, assessing their multi-modal understanding capabilities in general tasks including object counting, absurd question answering, affordance reasoning, attribute recognition, and spatial relation reasoning. Our investigations reveal that these LVLMs demonstrate limited proficiency not only in specialized tasks but also in general tasks. We delve deep into this inadequacy and uncover several potential factors, including limited cognition in specialized tasks, object hallucination, text-to-image interference, and decreased robustness in complex problems. We hope that this study can provide useful insights for the future development of LVLMs, helping researchers improve LVLMs for both general and specialized applications.

cs.CV↗

arXiv2024

EasyCalib: Simple and Low-Cost In-Situ Calibration for Force Reconstruction with Vision-Based Tactile Sensors

For elastomer-based tactile sensors, represented by visuotactile sensors, routine calibration of mechanical parameters (Young's modulus and Poisson's ratio) has been shown to be important for force reconstruction. However, the reliance on existing in-situ calibration methods for accurate force measurements limits their cost-effective and flexible applications. This article proposes a new in-situ calibration scheme that relies only on comparing contact deformation. Based on the detailed derivations of the normal contact and torsional contact theories, we designed a simple and low-cost calibration device, EasyCalib, and validated its effectiveness through extensive finite element analysis. We also explored the accuracy of EasyCalib in the practical application and demonstrated that accurate contact distributed force reconstruction can be realized based on the mechanical parameters obtained. EasyCalib balances low hardware cost, ease of operation, and low dependence on technical expertise and is expected to provide the necessary accuracy guarantees for wide applications of visuotactile sensors in the wild.

cs.RO↗

arXiv2024

Incipient Slip-Based Rotation Measurement via Visuotactile Sensing During In-Hand Object Pivoting

In typical in-hand manipulation tasks represented by object pivoting, the real-time perception of rotational slippage has been proven beneficial for improving the dexterity and stability of robotic hands. An effective strategy is to obtain the contact properties for measuring rotation angle through visuotactile sensing. However, existing methods for rotation estimation did not consider the impact of the incipient slip during the pivoting process, which introduces measurement errors and makes it hard to determine the boundary between stable contact and macro slip. This paper describes a generalized 2-d contact model under pivoting, and proposes a rotation measurement method based on the line-features in the stick region. The proposed method was applied to the Tac3D vision-based tactile sensors using continuous marker patterns. Experiments show that the rotation measurement system could achieve an average static measurement error of 0.17 degree and an average dynamic measurement error of 1.34 degree. Besides, the proposed method requires no training data and can achieve real-time sensing during the in-hand object pivoting.

cs.RO↗

arXiv2023

Real-time and Robust Feature Detection of Continuous Marker Pattern for Dense 3-D Deformation Measurement

Visuotactile sensing technology has received much attention in recent years. This article proposes a feature detection method applicable to visuotactile sensors based on continuous marker patterns (CMP) to measure 3-d deformation. First, we construct the feature model of checkerboard-like corners under contact deformation, and design a novel double-layer circular sampler. Then, we propose the judging criteria and response function of corner features by analyzing sampling signals' amplitude-frequency characteristics and circular cross-correlation behavior. The proposed feature detection algorithm fully considers the boundary characteristics retained by the corners with geometric distortion, thus enabling reliable detection at a low calculation cost. The experimental results show that the proposed method has significant advantages in terms of real-time and robustness. Finally, we have achieved the high-density 3-d contact deformation visualization based on this detection method. This technique is able to clearly record the process of contact deformation, thus enabling inverse sensing of dynamic contact processes.

cs.RO↗

arXiv2023

Guided Focal Stack Refinement Network for Light Field Salient Object Detection

Light field salient object detection (SOD) is an emerging research direction attributed to the richness of light field data. However, most existing methods lack effective handling of focal stacks, therefore making the latter involved in a lot of interfering information and degrade the performance of SOD. To address this limitation, we propose to utilize multi-modal features to refine focal stacks in a guided manner, resulting in a novel guided focal stack refinement network called GFRNet. To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features. In GRFM, all-in-focus (AiF) and depth modalities are utilized to refine focal stacks separately, leading to two novel sub-modules for different modalities, namely AiF-based refinement module (ARM) and depth-based refinement module (DRM). Such refinement modules enhance structural and positional information of salient objects in focal stacks, and are able to improve SOD accuracy. Experimental results on four benchmark datasets demonstrate the superiority of our GFRNet model against 12 state-of-the-art models.

cs.CV↗

arXiv2022

Bulk-LDOS Correspondence in Topological Insulators

Seeking the criterion for diagnosing topological phases in real materials has been one of the major tasks in topological physics. Currently, bulk-boundary correspondence based on spectral measurements of in gap topological boundary states and the fractional corner anomaly derived from the measurement of the fractional spectral charge are two main approaches to characterize topologically insulating phases. However, these two methods require a complete band-gap with either in-gap states or strict spatial symmetry of the overall sample which significantly limits their applications to more generalized cases. Here we propose and demonstrate an approach to link the non-trivial hierarchical bulk topology to the multidimensional partition of local-density of states (LDOS) respectively, denoted as the bulk-LDOS correspondence. Specifically, in a finite-size topologically nontrivial photonic crystal, we observe that the distribution of LDOS is divided into three partitioned regions of the sample - the two-dimensional interior bulk area (avoiding edge and corner areas), one-dimensional edge region (avoiding the corner area), and zero-dimensional corner sites. In contrast, the LDOS is distributed across the entire two-dimensional bulk area across the whole spectrum for the topologically trivial cases. Moreover, we present the universality of this criterion by validating this correspondence in both a higher-order topological insulator without a complete band gap and with disorders. Our findings provide a general way to distinguish topological insulators and unveil the unexplored features of topological directional band-gap materials without in-gap states.

cond-mat.mes-hall↗

arXiv2022

The mechanism of Li deposition on the Cu substrates in the anode-free Li metal batteries

Due to the rapid growth in the demand for high-energy-density Li batteries and insufficient global Li reserves, the anode-free Li metal batteries are receiving increasing attention. Various strategies, such as surface modification and structural design of Cu current collectors, have been proposed to stabilize the anode-free Li metal batteries. Unfortunately, the mechanism of Li deposition on the Cu surfaces with the different Miller indices is poorly understood, especially on the atomic scale. Here, a large-scale molecular dynamics simulation of Li deposition on the Cu substrates was performed in the anode-free Li metal batteries. The results show that the Li layers on the Cu (100), Cu (110), and Cu (111) surfaces are closer to the structures of Li (110), Li (100), and Li (110) surfaces, respectively. The mechanism was studied through the surface similarity analysis, potential energy surfaces, and lattice features. Finally, a proposal to reduce the fraction of the (110) facet in commercial Cu foils was made to improve the reversibility and stability of Li plating/stripping in the anode-free Li metal batteries.

cond-mat.mtrl-sci↗

arXiv2022

Tac3D: A Novel Vision-based Tactile Sensor for Measuring Forces Distribution and Estimating Friction Coefficient Distribution

The importance of force perception in interacting with the environment was proven years ago. However, it is still a challenge to measure the contact force distribution accurately in real-time. In order to break through this predicament, we propose a new vision-based tactile sensor, the Tac3D sensor, for measuring the three-dimensional contact surface shape and contact force distribution. In this work, virtual binocular vision is first applied to the tactile sensor, which allows the Tac3D sensor to measure the three-dimensional tactile information in a simple and efficient way and has the advantages of simple structure, low computational costs, and inexpensive. Then, we used contact surface shape and force distribution to estimate the friction coefficient distribution in contact region. Further, combined with the global position of the tactile sensor, the 3D model of the object with friction coefficient distribution is reconstructed. These reconstruction experiments not only demonstrate the excellent performance of the Tac3D sensor but also imply the possibility to optimize the action planning in grasping based on the friction coefficient distribution of the object.

cs.RO↗