arXiv subjects

Yongqiang Zhao

Publications and source records attributed to Yongqiang Zhao.

At least 19 recordsLinked to original sources

arXiv2026

Evolving Error States: Failure-Aware Progressive Repair for Ultrasound Lesion Segmentation

Reliability under sparse and heterogeneous failures remains a fundamental challenge for medical image segmentation. High average accuracy can conceal a small set of structurally distinct and clinically consequential errors. Existing post-hoc correction methods alleviate this problem, but typically estimate false-positive and false-negative corrections from the same fixed prediction. This ignores the dynamic evolution of error states and limits the correction of complex cases. Inspired by iterative error feedback in structured prediction, we propose Failure-Aware Progressive Repair (FAPR). FAPR represents the current segmentation mask as a dynamic failure state and models each repair operation as a state-transition operator. Each accepted correction forms a new prediction state for subsequent error diagnosis and repair, enabling later operations to adapt to preceding changes. Conditional routing selectively activates necessary state transitions, while failure replay exposes the model to rare error states. By keeping the base segmentor frozen, FAPR preserves its established segmentation capability while improving difficult cases. Across three public ultrasound lesion segmentation benchmarks, FAPR improves mean DSC by 1.52%. On the very-hard subsets of BUSI and TN3K, the average gain reaches 13.77%.

cs.CV↗

arXiv2026

HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation Learning

Despite the importance of tactile sensing for reliable manipulation, most existing Vision-Language-Action (VLA) datasets remain vision-only, and those that do incorporate tactile information typically lack the joint combination of task diversity, language conditioning, and action trajectories. Furthermore, existing teleoperation pipelines rarely provide haptic feedback to the operator, despite its established role in demonstration quality and manipulation stability. In this work, we present HapTile, a contact-grounded visuotactile manipulation dataset that advances beyond vision-only trajectory datasets by embedding physical interaction sensing at two levels: fingertip tactile feedback at the robot end-effector, and haptic-informed demonstrations at the teleoperator side. The data collection platform integrates haptic feedback directly into the teleoperation controller, enabling the operator to perceive contact interactions in real time. It is built around a standard and reproducible robotic system equipped with custom-designed fingertip tactile sensors. The dataset comprises everyday manipulation tasks spanning a broad range of contact-rich skills, including pick-and-place, folding, pressing, stacking, and other routine activities. Each task is paired with language instructions that condition the policy on the manipulation objective, together with synchronized visuotactile observations and action trajectories. In addition, we provide a benchmarking study on contact-rich policy learning using two baseline models to evaluate the effectiveness of the proposed contact-grounded dataset. The dataset and additional details are available on our website: haptile-dataset.github.io.

cs.RO↗

arXiv2026

Visual-Tactile Peg-in-Hole Assembly Learning from Peg-out-of-Hole Disassembly

Peg-in-hole (PiH) assembly is a fundamental yet challenging robotic manipulation task. While reinforcement learning (RL) has shown promise in tackling such tasks, it requires extensive exploration. In this paper, we propose a novel visual-tactile skill learning framework for the PiH task that leverages its inverse task, i.e., peg-out-of-hole (PooH) disassembly, to facilitate PiH learning. Compared to PiH, PooH is inherently easier as it only needs to overcome existing friction without precise alignment, making data collection more efficient. To this end, we formulate both PooH and PiH as Partially Observable Markov Decision Processes (POMDPs) in a unified environment with shared visual-tactile observation space. A visual-tactile PooH policy is first trained; its trajectories, containing kinematic, visual and tactile information, are temporally reversed and action-randomized to provide expert data for PiH. In the policy learning, visual sensing facilitates the peg-hole approach, while tactile measurements compensate for peg-hole misalignment. Experiments across diverse peg-hole geometries show that the visual-tactile policy attains 6.4% lower contact forces than its single-modality counterparts, and that our framework achieves average success rates of 87.5% on seen objects and 77.1% on unseen objects, outperforming direct RL methods that train PiH policies from scratch by 18.1% in success rate. Demos, code, and datasets are available at https://sites.google.com/view/pooh2pih.

cs.RO↗

arXiv2026

ViTac-Tracing: Visual-Tactile Imitation Learning of Deformable Object Tracing

Deformable objects often appear in unstructured configurations. Tracing deformable objects helps bringing them into extended states and facilitating the downstream manipulation tasks. Due to the requirements for object-specific modeling or sim-to-real transfer, existing tracing methods either lack generalizability across different categories of deformable objects or struggle to complete tasks reliably in the real world. To address this, we propose a novel visual-tactile imitation learning method to achieve one-dimensional (1D) and two-dimensional (2D) deformable object tracing with a unified model. Our method is designed from both local and global perspectives based on visual and tactile sensing. Locally, we introduce a weighted loss that emphasizes actions maintaining contact near the center of the tactile image, improving fine-grained adjustment. Globally, we propose a tracing task loss that helps the policy to regulate task progression. On the hardware side, to compensate for the limited features extracted from visual information, we integrate tactile sensing into a low-cost teleoperation system considering both the teleoperator and the robot. Extensive ablation and comparative experiments on diverse 1D and 2D deformable objects demonstrate the effectiveness of our approach, achieving an average success rate of 80% on seen objects and 65% on unseen objects.

cs.RO↗

arXiv2026

Limited Reasoning Space: The cage of long-horizon reasoning in LLMs

The test-time compute strategy, such as Chain-of-Thought (CoT), has significantly enhanced the ability of large language models to solve complex tasks like logical reasoning. However, empirical studies indicate that simply increasing the compute budget can sometimes lead to a collapse in test-time performance when employing typical task decomposition strategies such as CoT. This work hypothesizes that reasoning failures with larger compute budgets stem from static planning methods, which hardly perceive the intrinsic boundaries of LLM reasoning. We term it as the Limited Reasoning Space hypothesis and perform theoretical analysis through the lens of a non-autonomous stochastic dynamical system. This insight suggests that there is an optimal range for compute budgets; over-planning can lead to redundant feedback and may even impair reasoning capabilities. To exploit the compute-scaling benefits and suppress over-planning, this work proposes Halo, a model predictive control framework for LLM planning. Halo is designed for long-horizon tasks with reason-based planning and crafts an entropy-driven dual controller, which adopts a Measure-then-Plan strategy to achieve controllable reasoning. Experimental results demonstrate that Halo outperforms static baselines on complex long-horizon tasks by dynamically regulating planning at the reasoning boundary.

cs.AI↗

arXiv2026

DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows

Autonomous agents are increasingly entrusted with complex, long-horizon tasks, ranging from mathematical reasoning to software generation. While agentic workflows facilitate these tasks by decomposing them into multi-step reasoning chains, reliability degrades significantly as the sequence lengthens. Specifically, minor interpretation errors in natural-language instructions tend to compound silently across steps. We term this failure mode accumulated semantic ambiguity. Existing approaches to mitigate this often lack runtime adaptivity, relying instead on static exploration budgets, reactive error recovery, or single-path execution that ignores uncertainty entirely. We formalize the multi-step reasoning process as a Noisy MDP and propose DenoiseFlow, a closed-loop framework that performs progressive denoising through three coordinated stages: (1)Sensing estimates per-step semantic uncertainty; (2)Regulating adaptively allocates computation by routing between fast single-path execution and parallel exploration based on estimated risk; and (3)Correcting performs targeted recovery via influence-based root-cause localization. Online self-calibration continuously aligns decision boundaries with verifier feedback, requiring no ground-truth labels. Experiments on six benchmarks spanning mathematical reasoning, code generation, and multi-hop QA show that DenoiseFlow achieves the highest accuracy on every benchmark (83.3% average, +1.3% over the strongest baseline) while reducing cost by 40--56% through adaptive branching. Detailed ablation studies further confirm framework-level's robustness and generality. Code is available at https://anonymous.4open.science/r/DenoiseFlow-21D3/.

cs.AI↗

arXiv2025

Layer-wise Noise Guided Selective Wavelet Reconstruction for Robust Medical Image Segmentation

Clinical deployment requires segmentation models to stay stable under distribution shifts and perturbations. The mainstream solution is adversarial training (AT) to improve robustness; however, AT often brings a clean--robustness trade-off and high training/tuning cost, which limits scalability and maintainability in medical imaging. We propose \emph{Layer-wise Noise-Guided Selective Wavelet Reconstruction (LNG-SWR)}. During training, we inject small, zero-mean noise at multiple layers to learn a frequency-bias prior that steers representations away from noise-sensitive directions. We then apply prior-guided selective wavelet reconstruction on the input/feature branch to achieve frequency adaptation: suppress noise-sensitive bands, enhance directional structures and shape cues, and stabilize boundary responses while maintaining spectral consistency. The framework is backbone-agnostic and adds low additional inference overhead. It can serve as a plug-in enhancement to AT and also improves robustness without AT. On CT and ultrasound datasets, under a unified protocol with PGD-$L_{\infty}/L_{2}$ and SSAH, LNG-SWR delivers consistent gains on clean Dice/IoU and significantly reduces the performance drop under strong attacks; combining LNG-SWR with AT yields additive gains. When combined with adversarial training, robustness improves further without sacrificing clean accuracy, indicating an engineering-friendly and scalable path to robust segmentation. These results indicate that LNG-SWR provides a simple, effective, and engineering-friendly path to robust medical image segmentation in both adversarial and standard training regimes.

cs.CV↗

arXiv2025

SimTac: A Physics-Based Simulator for Vision-Based Tactile Sensing with Biomorphic Structures

Tactile sensing in biological organisms is deeply intertwined with morphological form, such as human fingers, cat paws, and elephant trunks, which enables rich and adaptive interactions through a variety of geometrically complex structures. In contrast, vision-based tactile sensors in robotics have been limited to simple planar geometries, with biomorphic designs remaining underexplored. To address this gap, we present SimTac, a physics-based simulation framework for the design and validation of biomorphic tactile sensors. SimTac consists of particle-based deformation modeling, light-field rendering for photorealistic tactile image generation, and a neural network for predicting mechanical responses, enabling accurate and efficient simulation across a wide range of geometries and materials. We demonstrate the versatility of SimTac by designing and validating physical sensor prototypes inspired by biological tactile structures and further demonstrate its effectiveness across multiple Sim2Real tactile tasks, including object classification, slip detection, and contact safety assessment. Our framework bridges the gap between bio-inspired design and practical realisation, expanding the design space of tactile sensors and paving the way for tactile sensing systems that integrate morphology and sensing to enable robust interaction in unstructured environments.

cs.RO↗

arXiv2025

ViTacGen: Robotic Pushing with Vision-to-Touch Generation

Robotic pushing is a fundamental manipulation task that requires tactile feedback to capture subtle contact forces and dynamics between the end-effector and the object. However, real tactile sensors often face hardware limitations such as high costs and fragility, and deployment challenges involving calibration and variations between different sensors, while vision-only policies struggle with satisfactory performance. Inspired by humans' ability to infer tactile states from vision, we propose ViTacGen, a novel robot manipulation framework designed for visual robotic pushing with vision-to-touch generation in reinforcement learning to eliminate the reliance on high-resolution real tactile sensors, enabling effective zero-shot deployment on visual-only robotic systems. Specifically, ViTacGen consists of an encoder-decoder vision-to-touch generation network that generates contact depth images, a standardized tactile representation, directly from visual image sequence, followed by a reinforcement learning policy that fuses visual-tactile data with contrastive learning based on visual and generated tactile observations. We validate the effectiveness of our approach in both simulation and real world experiments, demonstrating its superior performance and achieving a success rate of up to 86\%.

cs.RO↗

arXiv2025

Training Tactile Sensors to Learn Force Sensing from Each Other

Humans achieve stable and dexterous object manipulation by coordinating grasp forces across multiple fingers and palms, facilitated by a unified tactile memory system in the somatosensory cortex. This system encodes and stores tactile experiences across skin regions, enabling the flexible reuse and transfer of touch information. Inspired by this biological capability, we present GenForce, the first framework that enables transferable force sensing across tactile sensors in robotic hands. GenForce unifies tactile signals into shared marker representations, analogous to cortical sensory encoding, allowing force prediction models trained on one sensor to be transferred to others without the need for exhaustive force data collection. We demonstrate that GenForce generalizes across both homogeneous sensors with varying configurations and heterogeneous sensors with distinct sensing modalities and material properties. This transferable force sensing is also demonstrated with high performance in robot force control including daily object grasping, slip detection and avoidance. Our results highlight a scalable paradigm for cross-sensor robotic tactile learning, offering new pathways toward adaptable and tactile memory-driven manipulation in unstructured environments.

cs.RO↗

arXiv2025

ConViTac: Aligning Visual-Tactile Fusion with Contrastive Representations

Vision and touch are two fundamental sensory modalities for robots, offering complementary information that enhances perception and manipulation tasks. Previous research has attempted to jointly learn visual-tactile representations to extract more meaningful information. However, these approaches often rely on direct combination, such as feature addition and concatenation, for modality fusion, which tend to result in poor feature integration. In this paper, we propose ConViTac, a visual-tactile representation learning network designed to enhance the alignment of features during fusion using contrastive representations. Our key contribution is a Contrastive Embedding Conditioning (CEC) mechanism that leverages a contrastive encoder pretrained through self-supervised contrastive learning to project visual and tactile inputs into unified latent embeddings. These embeddings are used to couple visual-tactile feature fusion through cross-modal attention, aiming at aligning the unified representations and enhancing performance on downstream tasks. We conduct extensive experiments to demonstrate the superiority of ConViTac in real world over current state-of-the-art methods and the effectiveness of our proposed CEC mechanism, which improves accuracy by up to 12.0% in material classification and grasping prediction tasks.

cs.CV↗

arXiv2025

Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine

Evidence-based medicine (EBM) plays a crucial role in the application of large language models (LLMs) in healthcare, as it provides reliable support for medical decision-making processes. Although it benefits from current retrieval-augmented generation~(RAG) technologies, it still faces two significant challenges: the collection of dispersed evidence and the efficient organization of this evidence to support the complex queries necessary for EBM. To tackle these issues, we propose using LLMs to gather scattered evidence from multiple sources and present a knowledge hypergraph-based evidence management model to integrate these evidence while capturing intricate relationships. Furthermore, to better support complex queries, we have developed an Importance-Driven Evidence Prioritization (IDEP) algorithm that utilizes the LLM to generate multiple evidence features, each with an associated importance score, which are then used to rank the evidence and produce the final retrieval results. Experimental results from six datasets demonstrate that our approach outperforms existing RAG techniques in application domains of interest to EBM, such as medical quizzing, hallucination detection, and decision support. Testsets and the constructed knowledge graph can be accessed at \href{https://drive.google.com/file/d/1WJ9QTokK3MdkjEmwuFQxwH96j_Byawj_/view?usp=drive_link}{https://drive.google.com/rag4ebm}.

cs.CL↗

arXiv2024

On the multiplicity of the eigenvalues of discrete tori

It is well known that the standard flat torus $\mathbb{T}^2=\mathbb{R}^2/\Z^2$ has arbitrarily large Laplacian-eigenvalue multiplicities. We prove, however, that $24$ is the optimal upper bound for the multiplicities of the nonzero eigenvalues of a $2$-dimensional discrete torus. For general higher dimension discrete tori, we characterize the eigenvalues with large multiplicities. As consequences, we get uniform boundedness results of the multiplicity for a long range and an optimal global bound for the multiplicity. Our main tool of proof is the theory of vanishing sums of roots of unity.

math.SP↗

arXiv2024

Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment

This research examines the use of Reinforcement Learning from AI Feedback (RLAIF) techniques to improve healthcare dialogue models, with the aim of tackling the challenges of preference-aligned data annotation while reducing the reliance on medical experts. We argue that the primary challenges in current RLAIF research for healthcare are the limitations of automated evaluation methods and the difficulties in accurately representing physician preferences. To address these challenges, we present a new evaluation framework based on standardized patient examinations. This framework is designed to objectively assess the effectiveness of large language models (LLMs) in guiding users and following instructions, enabling a comprehensive comparison across different models. Furthermore, our investigation of effective ways to express physician preferences using Constitutional AI algorithms highlighted the particular effectiveness of flowcharts. Utilizing this finding, we introduce an innovative agent-based approach for annotating preference data. This approach autonomously creates medical dialogue flows tailored to the patient's condition, demonstrates strong generalization abilities, and reduces the need for expert involvement. Our results show that the agent-based approach outperforms existing RLAIF annotation methods in standardized patient examinations and surpasses current open source medical dialogue LLMs in various test scenarios.

cs.CL↗

arXiv2024

Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback

The use of large language models in medical dialogue generation has garnered significant attention, with a focus on improving response quality and fluency. While previous studies have made progress in optimizing model performance for single-round medical Q&A tasks, there is a need to enhance the model's capability for multi-round conversations to avoid logical inconsistencies. To address this, we propose an approach called preference learning from process feedback~(PLPF), which integrates the doctor's diagnostic logic into LLMs. PLPF involves rule modeling, preference data generation, and preference alignment to train the model to adhere to the diagnostic process. Experimental results using Standardized Patient Testing show that PLPF enhances the diagnostic accuracy of the baseline model in medical conversations by 17.6%, outperforming traditional reinforcement learning from human feedback. Additionally, PLPF demonstrates effectiveness in both multi-round and single-round dialogue tasks, showcasing its potential for improving medical dialogue generation.

cs.CL↗

arXiv2024

Inter and Intra Prior Learning-based Hyperspectral Image Reconstruction Using Snapshot SWIR Metasurface

Shortwave-infrared(SWIR) spectral information, ranging from 1 μm to 2.5μm, overcomes the limitations of traditional color cameras in acquiring scene information. However, conventional SWIR hyperspectral imaging systems face challenges due to their bulky setups and low acquisition speeds. This work introduces a snapshot SWIR hyperspectral imaging system based on a metasurface filter and a corresponding filter selection method to achieve the lowest correlation coefficient among these filters. This system offers the advantages of compact size and snapshot imaging. We propose a novel inter and intra prior learning unfolding framework to achieve high-quality SWIR hyperspectral image reconstruction, which bridges the gap between prior learning and cross-stage information interaction. Additionally, We design an adaptive feature transfer mechanism to adaptively transfer the contextual correlation of multi-scale encoder features to prevent detailed information loss in the decoder. Experiment results demonstrate that our method can reconstruct hyperspectral images with high speed and superior performance over existing methods.

cs.CV↗

arXiv2024

FOTS: A Fast Optical Tactile Simulator for Sim2Real Learning of Tactile-motor Robot Manipulation Skills

Simulation is a widely used tool in robotics to reduce hardware consumption and gather large-scale data. Despite previous efforts to simulate optical tactile sensors, there remain challenges in efficiently synthesizing images and replicating marker motion under different contact loads. In this work, we propose a fast optical tactile simulator, named FOTS, for simulating optical tactile sensors. We utilize multi-layer perceptron mapping and planar shadow generation to simulate the optical response, while employing marker distribution approximation to simulate the motion of surface markers caused by the elastomer deformation. Experimental results demonstrate that FOTS outperforms other methods in terms of image generation quality and rendering speed, achieving 28.6 fps for optical simulation and 326.1 fps for marker motion simulation on a single CPU without GPU acceleration. In addition, we integrate the FOTS simulation model with physical engines like MuJoCo, and the peg-in-hole task demonstrates the effectiveness of our method in achieving zero-shot Sim2Real learning of tactile-motor robot manipulation skills. Our code is available at https://github.com/Rancho-zhao/FOTS.

cs.RO↗

arXiv2024

Special values of spectral zeta functions and combinatorics: Sturm-Liouville problems

In this paper, we apply the combinatorial results on counting permutations with fixed pinnacle and vale sets to evaluate the special values of the spectral zeta functions of Sturm-Liouville differential operators. As applications, we get a combinatorial formula for the special values of spectral zeta functions and give a new explicit formula for Bernoulli numbers.

math.CO↗