Searcharxiv⌕ Search

arXiv subjects

Zhenyu Lu

Publications and source records attributed to Zhenyu Lu.

16 recordsLinked to original sources
arXiv2026

Vision-Based Tactile Intelligence for Robotics: Sensing, Learning, and Embodied Manipulation

Tactile sensing is essential for robots in contact-rich tasks, yet many tactile sensors still provide sparse, low-dimensional signals that do not capture sufficient information for complex robotic perception and interaction. Vision-based tactile sensors (VBTSs) offer a powerful alternative by con-verting contact-induced deformation of a soft interface into im-ages. The image-based formulation gives VBTSs high-resolution, information-rich tactile observations that enable complex robotic tasks. This review surveys the full VBTS pipeline and treats sensing hardware, learning methods, simulation, and datasets as an integrated sensing-and-learning system. We 1) organize representative VBTSs into a hardware taxonomy structured by deformable elastomer design, sensor size and shape, and optical system design to guide future sensor development; 2) present a hierarchical view of learning-based tactile intelligence from low-level signal understanding to task-level policies and foundation models; and 3) examine simulation platforms and tactile datasets as a scaling layer, together with sim-to-real transfer and cross-sensor adaptation for training, benchmarking, and deployment. Finally, we identify open challenges and future directions for VBTSs in robotics. By providing a holistic view of how hardware, AI architectures, simulation, and datasets interact, this review aims to advance tactile intelligence for contact-rich robotic tasks.

cs.RO↗
arXiv2026

Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs

Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require costly training. Furthermore, directly adapting training-free LLM reasoning mechanisms to the multimodal setting yields unstable performance. We identify that this failure stems from their reliance on token-level entropy, which fundamentally conflates perceptual ambiguity (e.g., unclear visual details) with logical uncertainty (e.g., complex reasoning steps). To overcome this bottleneck, we present a novel training-free inference strategy for MLLMs that explicitly decouples perception and reasoning. We propose a novel metric, the vision-to-text attention ratio, to dynamically gauge the model's cognitive focus. Guided by this metric, our proposed framework, Attention-Guided Switching (AGS), adaptively triggers latent reasoning for perceptual tokens to preserve high-fidelity visual information in the continuous space, while enforcing explicit text generation for logical tokens to maintain structural anchoring. Extensive experiments demonstrate that our method achieves state-of-the-art performance, significantly improving both accuracy and inference efficiency by reducing autoregressive steps and latency. Code is released at https://github.com/swordAndSnow/MM26-AGS.

cs.MM↗
arXiv2026

CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception

High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency. Visual expert-assisted search is efficient but prone to blind spots when proposals fail, whereas scan-based search guarantees coverage at the cost of computational redundancy and semantic fragmentation. To address this dilemma, we introduce CVSearch, a training-free adaptive framework that dynamically schedules search strategies via an Assess-then-Search workflow. Specifically, CVSearch first invokes expert-assisted search when global information is insufficient, and only triggers a novel semantic-aware scanning mechanism upon failure. Distinct from rigid grid partitioning, this efficient scanning paradigm incorporates Semantic Guided Adaptive Patching to decompose images into semantically consistent regions, effectively mitigating object fragmentation. Furthermore, we devise a Dynamic Bottom-Up Search strategy driven by a Visual Complexity prior to enable efficient and precise iterative exploration of local details. Extensive experiments on HR benchmarks demonstrate that CVSearch achieves state-of-the-art accuracy while substantially improving search efficiency. Code is released at https://github.com/liliupeng28/ICML26-CVSearch.

cs.CV↗
arXiv2026

SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end yet opaque "black boxes". Conversely, textual localization readout is merely readable, not truly interpretable, often functioning as an unconstrained post-hoc step. To bridge this interpretability gap, we propose SegCompass, an end-to-end model that leverages a Sparse Autoencoder (SAE) to forge an explicit, interpretable, and differentiable alignment pathway. Given an image-instruction pair, SegCompass first generates a chain-of-thought (CoT) trace. The core of our method is an SAE that maps both the CoT and visual tokens into a shared, high-dimensional sparse concept space. A query codebook selects salient concepts from this space, which are then spatially grounded by a slot mapper into a multi-slot heatmap that guides the final mask decoder. The entire model is trained jointly, unifying reinforcement learning for the reasoning path with standard segmentation supervision. This SAE-driven interface provides a "white-box" connection that is significantly more traceable than latent queries and more coherent than textual readouts. Extensive experiments on five challenging benchmarks demonstrate that SegCompass matches or surpasses state-of-the-art performance. Crucially, our visual and quantitative analyses show a strong correlation between the quality of the learned sparse concepts and final mask accuracy, confirming that SegCompass achieves superior results through its enhanced and inspectable alignment. Code is available at https://github.com/ZhenyuLU-Heliodore/SegCompass.

cs.CV↗
arXiv2026

Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data

Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A key challenge is context selection: providing insufficient context limits reasoning, while including all available data leads to inefficiency and degraded generation quality. We propose Wearable As Graph (WAG), a graph-based context retrieval framework that enables query-adaptive reasoning over wearable data with LLMs. WAG organizes wearable metrics and user-specific signals into a personalized knowledge graph, and retrieves a query-conditioned subgraph to support downstream generation. The retrieval process integrates global relationships, capturing prior knowledge and population- and individual-level patterns via hierarchical Bayesian modeling, with local relationships that reflect short-term signal deviations. A query openness signal further controls retrieval breadth. We evaluate WAG on over 10,000 data-grounded queries from real-world wearable datasets. Across LLM-based and human evaluations, WAG achieves an approximately 70% win rate over baseline and standard RAG methods, demonstrating the effectiveness of structured, query-adaptive context retrieval for LLM-driven analysis of wearable data.

cs.IR↗
arXiv2025

CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation

Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)-based positional perception model that bridges language reasoning to segmentation through a differentiable and interpretable positional prior instantiated as a heatmap. By making the reasoning process clear via MCoT and expressing it as a dense, differentiable heatmap, this interface enhances interpretability and diagnostic analysis and yields more concentrated evidence on the target. A learnable concentration token aggregates features of the image and reasoning text to generate this positional prior, which is decoded to precise masks through a lightweight decoder, providing a direct connection between reasoning and segmentation. Across the RefCOCO series and ReasonSeg, CoPRS matches or surpasses the best reported metrics on each standard split under comparable protocols, with performance at or above the prior state of the art across both validation and test partitions. Extensive experiments demonstrate a strong positive correlation among the CoT trajectory, the generated heatmap, and the decoded mask, supporting an interpretable alignment between the reasoning output and downstream mask generation. Collectively, these findings support the utility of this paradigm in bridging reasoning and segmentation and show advantages in concentration driven by reasoning and in more precise mask prediction. Code has been released at https://github.com/ZhenyuLU-Heliodore/CoPRS.

cs.CV↗
arXiv2025

Open-Vocabulary Spatio-Temporal Scene Graph for Robot Perception and Teleoperation Planning

Teleoperation via natural-language reduces operator workload and enhances safety in high-risk or remote settings. However, in dynamic remote scenes, transmission latency during bidirectional communication creates gaps between remote perceived states and operator intent, leading to command misunderstanding and incorrect execution. To mitigate this, we introduce the Spatio-Temporal Open-Vocabulary Scene Graph (ST-OVSG), a representation that enriches open-vocabulary perception with temporal dynamics and lightweight latency annotations. ST-OVSG leverages LVLMs to construct open-vocabulary 3D object representations, and extends them into the temporal domain via Hungarian assignment with our temporal matching cost, yielding a unified spatio-temporal scene graph. A latency tag is embedded to enable LVLM planners to retrospectively query past scene states, thereby resolving local-remote state mismatches caused by transmission delays. To further reduce redundancy and highlight task-relevant cues, we propose a task-oriented subgraph filtering strategy that produces compact inputs for the planner. ST-OVSG generalizes to novel categories and enhances planning robustness against transmission latency without requiring fine-tuning. Experiments show that our method achieves 74 percent node accuracy on the Replica benchmark, outperforming ConceptGraph. Notably, in the latency-robustness experiment, the LVLM planner assisted by ST-OVSG achieved a planning success rate of 70.5 percent.

cs.RO↗
arXiv2024

Continual Gesture Learning without Data via Synthetic Feature Sampling

Data-Free Class Incremental Learning (DFCIL) aims to enable models to continuously learn new classes while retraining knowledge of old classes, even when the training data for old classes is unavailable. Although explored primarily with image datasets by researchers, this study focuses on investigating DFCIL for skeleton-based gesture classification due to its significant real-world implications, particularly considering the growing prevalence of VR/AR headsets where gestures serve as the primary means of control and interaction. In this work, we made an intriguing observation: skeleton models trained with base classes(even very limited) demonstrate strong generalization capabilities to unseen classes without requiring additional training. Building on this insight, we developed Synthetic Feature Replay (SFR) that can sample synthetic features from class prototypes to replay for old classes and augment for new classes (under a few-shot setting). Our proposed method showcases significant advancements over the state-of-the-art, achieving up to 15% enhancements in mean accuracy across all steps and largely mitigating the accuracy imbalance between base classes and new classes.

cs.CV↗
arXiv2024

BrewCLIP: A Bifurcated Representation Learning Framework for Audio-Visual Retrieval

Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly. Generally, pipeline models outperform end-to-end models, but the intermediate transcription necessarily discards some potentially useful non-textual information. In addition to textual information, speech can convey details such as accent, mood, and and emphasis, which should be effectively captured in the encoded representation. In this paper, we investigate whether non-textual information, which is overlooked by pipeline-based models, can be leveraged to improve speech-image matching performance. We thoroughly analyze and compare End-to-End models, pipeline models, and our proposed dual-channel model for robust audio-image retrieval on a variety of datasets. Our approach achieves a substantial performance gain over the previous state-of-the-art by leveraging strong pretrained models, a prompting mechanism and a bifurcated design.

cs.SD↗
arXiv2024

TacShade A New 3D-printed Soft Optical Tactile Sensor Based on Light, Shadow and Greyscale for Shape Reconstruction

In this paper, we present the TacShade a newly designed 3D-printed soft optical tactile sensor. The sensor is developed for shape reconstruction under the inspiration of sketch drawing that uses the density of sketch lines to draw light and shadow, resulting in the creation of a 3D-view effect. TacShade, building upon the strengths of the TacTip, a single-camera tactile sensor of large in-depth deformation and being sensitive to edge and surface following, improves the structure in that the markers are distributed within the gap of papillae pins. Variations in light, dark, and grey effects can be generated inside the sensor through external contact interactions. The contours of the contacting objects are outlined by white markers, while the contact depth characteristics can be indirectly obtained from the distribution of black pins and white markers, creating a 2.5D visualization. Based on the imaging effect, we improve the Shape from Shading (SFS) algorithm to process tactile images, enabling a coarse but fast reconstruction for the contact objects. Two experiments are performed. The first verifies TacShade s ability to reconstruct the shape of the contact objects through one image for object distinction. The second experiment shows the shape reconstruction capability of TacShade for a large panel with ridged patterns based on the location of robots and image splicing technology.

eess.IV↗
arXiv2023

SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering

Visual question answering (VQA) is a critical multimodal task in which an agent must answer questions according to the visual cue. Unfortunately, language bias is a common problem in VQA, which refers to the model generating answers only by associating with the questions while ignoring the visual content, resulting in biased results. We tackle the language bias problem by proposing a self-supervised counterfactual metric learning (SC-ML) method to focus the image features better. SC-ML can adaptively select the question-relevant visual features to answer the question, reducing the negative influence of question-irrelevant visual features on inferring answers. In addition, question-irrelevant visual features can be seamlessly incorporated into counterfactual training schemes to further boost robustness. Extensive experiments have proved the effectiveness of our method with improved results on the VQA-CP dataset. Our code will be made publicly available.

cs.CV↗
arXiv2023

Data-driven Moving Horizon Estimation for Angular Velocity of Space Noncooperative Target in Eddy Current De-tumbling Mission

Angular velocity estimation is critical for eddy current de-tumbling of noncooperative space targets. However, unknown model of the noncooperative target and few observation data make the model-based estimation methods challenged. In this paper, a Data-driven Moving Horizon Estimation method is proposed to estimate the angular velocity of the noncooperative target with de-tumbling torque. In this method, model-free state estimation of the angular velocity can be achieved using only one historical trajectory data that satisfies the rank condition. With local linear approximation, the Willems fundamental lemma is extended to nonlinear autonomous systems, and the rank condition for the historical trajectory data is deduced. Then, a data-driven moving horizon estimation algorithm based on the M step Lyapunov function is designed, and the time-discount robust stability of the algorithm is given. In order to illustrate the effectiveness of the proposed algorithm, experiments and simulations are performed to estimate the angular velocity in eddy current de-tumbling with only de-tumbling torque measurement.

eess.SY↗
arXiv2022

AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation

Unsupervised domain adaption (UDA) is a transfer learning task where the data and annotations of the source domain are available but only have access to the unlabeled target data during training. Most previous methods try to minimise the domain gap by performing distribution alignment between the source and target domains, which has a notable limitation, i.e., operating at the domain level, but neglecting the sample-level differences. To mitigate this weakness, we propose to improve the unsupervised domain adaptation task with an inter-domain sample matching scheme. We apply the widely-used and robust Triplet loss to match the inter-domain samples. To reduce the catastrophic effect of the inaccurate pseudo-labels generated during training, we propose a novel uncertainty measurement method to select reliable pseudo-labels automatically and progressively refine them. We apply the advanced discrete relaxation Gumbel Softmax technique to realise an adaptive Topk scheme to fulfil the functionality. In addition, to enable the global ranking optimisation within one batch for the domain matching, the whole model is optimised via a novel reinforced attention mechanism with supervision from the policy gradient algorithm, using the Average Precision (AP) as the reward. Our model (termed \textbf{\textit{AdaTriplet-RA}}) achieves State-of-the-art results on several public benchmark datasets, and its effectiveness is validated via comprehensive ablation studies. Our method improves the accuracy of the baseline by 9.7\% (ResNet-101) and 6.2\% (ResNet-50) on the VisDa dataset and 4.22\% (ResNet-50) on the Domainnet dataset. {The source code is publicly available at \textit{https://github.com/shuxy0120/AdaTriplet-RA}}.

cs.CV↗
arXiv2022

Causal Effect Estimation using Variational Information Bottleneck

Causal inference is to estimate the causal effect in a causal relationship when intervention is applied. Precisely, in a causal model with binary interventions, i.e., control and treatment, the causal effect is simply the difference between the factual and counterfactual. The difficulty is that the counterfactual may never been obtained which has to be estimated and so the causal effect could only be an estimate. The key challenge for estimating the counterfactual is to identify confounders which effect both outcomes and treatments. A typical approach is to formulate causal inference as a supervised learning problem and so counterfactual could be predicted. Including linear regression and deep learning models, recent machine learning methods have been adapted to causal inference. In this paper, we propose a method to estimate Causal Effect by using Variational Information Bottleneck (CEVIB). The promising point is that VIB is able to naturally distill confounding variables from the data, which enables estimating causal effect by using observational data. We have compared CEVIB to other methods by applying them to three data sets showing that our approach achieved the best performance. We also experimentally showed the robustness of our method.

cs.LG↗
arXiv2012

Crowdsourcing Predictors of Behavioral Outcomes

Generating models from large data sets -- and determining which subsets of data to mine -- is becoming increasingly automated. However choosing what data to collect in the first place requires human intuition or experience, usually supplied by a domain expert. This paper describes a new approach to machine science which demonstrates for the first time that non-domain experts can collectively formulate features, and provide values for those features such that they are predictive of some behavioral outcome of interest. This was accomplished by building a web platform in which human groups interact to both respond to questions likely to help predict a behavioral outcome and pose new questions to their peers. This results in a dynamically-growing online survey, but the result of this cooperative behavior also leads to models that can predict user's outcomes based on their responses to the user-generated survey questions. Here we describe two web-based experiments that instantiate this approach: the first site led to models that can predict users' monthly electric energy consumption; the other led to models that can predict users' body mass index. As exponential increases in content are often observed in successful online collaborative communities, the proposed methodology may, in the future, lead to similar exponential rises in discovery and insight into the causal factors of behavioral outcomes.

cs.CY↗