arXiv subjects

Ziyang Zhou

Publications and source records attributed to Ziyang Zhou.

At least 19 recordsLinked to original sources

arXiv2026

4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields

Building on recent advances in world models, World Action Models (WAMs) jointly model video prediction and action generation. However, they typically represent videos in 2D pixel space, creating a representation gap with 3D space in which robotic actions are executed. Recent 3D approaches introduce 3D information, but fail to fully exploit the dynamics of 3D structures. In this work, we propose 4D-WAM, a model-agnostic training strategy that injects spatiotemporal knowledge from 3D trajectory fields into WAMs through representation alignment. To this end, we introduce two complementary objectives: 1) motion alignment, which aligns temporal feature variations across adjacent frames and encourages the model to build local 4D awareness during training, and 2) destination alignment, which guides the model to infer the final destination from the source frame by minimizing the gap between their attention-like similarity distributions. Together, these objectives provide both local motion supervision and long-horizon goal guidance, enabling WAMs to learn trajectory-level spatiotemporal representations. Extensive in-distribution and out-of-distribution experiments across different base models demonstrate the model's improvements in spatial understanding, execution precision, robustness, generalization, and versatility.

cs.RO↗

arXiv2026

Stochastic Entanglement of Deterministic Origami Tentacles For Robust Robotic Grasping

Origami-inspired robotic grippers have shown promising potential for object manipulation tasks due to their compact volume and mechanical flexibility. However, robust capture of objects with random shapes in dynamic working environments often comes at the cost of additional actuation channels and control complexity. Here, we introduce a tendon-driven, robust origami tentacle gripper by exploiting a synergy between local, deterministic deformation programming and global, stochastic entanglements. Each tentacle features carefully placed holes (for routing an actuation tendon), origami creases, and a tapered shape. By tailoring these design features, one can prescribe the shrinking, bending, and twisting deformation, eventually creating deterministic coiling with a simple tendon pull. Then, when multiple coiling tentacles are placed in proximity, stochastic entanglement emerges, allowing the tentacles to braid, knot, and grip objects with random shapes. We derived a simulation model by integrating origami mechanics with Cosserat rods to correlate origami design, tentacle deformation, and collective grasping performance. Then, we experimentally tested how these entangling origami tentacles can grasp objects under gravity and in water. A stow-and-release deployment mechanism was also tested to simulate in-orbit grasping. Overall, this entanglement-enabled tentacle gripper presents a route toward robust object grasping with simple design and actuation.

cs.RO↗

arXiv2026

Directional Symmetry Breaking of Spherical Active Colloids by Magnetoviscous Coupling

Harnessing active matter calls for strategies that break the directional symmetry of self-propelled motion without altering the propulsion mechanism itself. Here, we show that magnetically inert spherical active colloids can be steered through the anisotropic viscous response of a ferrofluid under a uniform magnetic field. Self-propelled Janus colloids exhibit robust cross-field motion transverse to the magnetic field, although the applied magnetic field directly controls neither the particles nor their propulsion speed. Quantitative measurements reveal an emergent reorientation torque that grows with both propulsion speed and magnetic field strength. A squirmer model in a magnetoviscous medium captures these observations and shows that the torque arises from the coupling between swimmer-generated flow and anisotropic rotational viscosity. Our findings establish a hydrodynamic basis for converting viscous dissipation into directional symmetry breaking through anisotropic rheology, providing a route to field-controlled material transport by active matter.

cond-mat.soft↗

arXiv2026

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary training objectives can improve performance and reduce the number of convergence steps. However, they typically incur significant computational overhead due to the additional losses from auxiliary objectives. To simultaneously achieve the enhanced capabilities of auxiliary training with the simplicity of standard SFT, we decouple the two objectives of auxiliary-objective SFT within the parameter space, namely, enhancing general capabilities and fitting task-specific action distributions. To deliver the goal, we only need to train the model to converge on a small-scale task set using two distinct training strategies, resulting in two finetuned models. The parameters' difference between the two models can then be interpreted as capability vectors provided by auxiliary objectives. These vectors are then merged with pretrained parameters to form a capability-enhanced meta model. Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss, the merged model attains performance comparable to auxiliary finetuned baselines with reduced computational overhead. Internal and external experiments demonstrate that our capability vectors (1) are effective and versatile across diverse models, (2) can generalize to novel environments and embodiments out of the box.

cs.CV↗

arXiv2026

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process

Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4$\times$ faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/.

cs.RO↗

arXiv2026

SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detection

Sarcasm detection is a crucial yet challenging Natural Language Processing task. Existing Large Language Model methods are often limited by single-perspective analysis, static reasoning pathways, and a susceptibility to hallucination when processing complex ironic rhetoric, which impacts their accuracy and reliability. To address these challenges, we propose **SEVADE**, a novel **S**elf-**Ev**olving multi-agent **A**nalysis framework with **D**ecoupled **E**valuation for hallucination-resistant sarcasm detection. The core of our framework is a Dynamic Agentive Reasoning Engine (DARE), which utilizes a team of specialized agents grounded in linguistic theory to perform a multifaceted deconstruction of the text and generate a structured reasoning chain. Subsequently, a separate lightweight rationale adjudicator (RA) performs the final classification based solely on this reasoning chain. This decoupled architecture is designed to mitigate the risk of hallucination by separating complex reasoning from the final judgment. Extensive experiments on four benchmark datasets demonstrate that our framework achieves state-of-the-art performance, with average improvements of **6.75%** in Accuracy and **6.29%** in Macro-F1 score.

cs.CL↗

arXiv2026

Embodying Physical Computing into Soft Robots

Softening and onboarding computers and controllers is one of the final frontiers in soft robotics towards their robustness and intelligence for everyday use. In this regard, embodying soft and physical computing presents exciting potential. Physical computing seeks to encode inputs into a mechanical computing kernel and leverage the internal interactions among this kernel's constituent elements to compute the output. Moreover, such input-to-output evolution can be re-programmable. This perspective paper proposes a framework for embodying physical computing into soft robots and discusses three unique strategies in the literature: analog oscillators, physical reservoir computing, and physical algorithmic computing. These embodied computers enable the soft robot to perform complex behaviors that would otherwise require CMOS-based electronics -- including coordinated locomotion with obstacle avoidance, payload weight and orientation classification, and programmable operation based on logical rules. This paper will detail the working principles of these embodied physical computing methods, survey the current state-of-the-art, and present a perspective for future development.

cs.RO↗

arXiv2026

Temporal-Spatial Decouple before Act: Disentangled Representation Learning for Multimodal Sentiment Analysis

Multimodal Sentiment Analysis integrates Linguistic, Visual, and Acoustic. Mainstream approaches based on modality-invariant and modality-specific factorization or on complex fusion still rely on spatiotemporal mixed modeling. This ignores spatiotemporal heterogeneity, leading to spatiotemporal information asymmetry and thus limited performance. Hence, we propose TSDA, Temporal-Spatial Decouple before Act, which explicitly decouples each modality into temporal dynamics and spatial structural context before any interaction. For every modality, a temporal encoder and a spatial encoder project signals into separate temporal and spatial body. Factor-Consistent Cross-Modal Alignment then aligns temporal features only with their temporal counterparts across modalities, and spatial features only with their spatial counterparts. Factor specific supervision and decorrelation regularization reduce cross factor leakage while preserving complementarity. A Gated Recouple module subsequently recouples the aligned streams for task. Extensive experiments show that TSDA outperforms baselines. Ablation analysis studies confirm the necessity and interpretability of the design.

cs.CL↗

arXiv2026

Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models

Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents. However, existing methods face a core trade-off between the analytical depth of specialized models and the generative fluency of Large Language Models (LLMs). To address this, we propose TRACE, Task-decomposed Reasoning for Affective Communication and Empathy, a novel framework that models empathy as a structured cognitive process by decomposing the task into a pipeline for analysis and synthesis. By building a comprehensive understanding before generation, TRACE unites deep analysis with expressive generation. Experimental results show that our framework significantly outperforms strong baselines in both automatic and LLM-based evaluations, confirming that our structured decomposition is a promising paradigm for creating more capable and interpretable empathetic agents. Our code is available at https://anonymous.4open.science/r/TRACE-18EF/README.md.

cs.CL↗

arXiv2026

RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection

Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multi-faceted linguistic cues that vary substantially across different sarcastic expressions. Existing approaches, from fine-tuned transformers to large language models, apply a uniform reasoning strategy to all inputs, struggling to address the diverse analytical demands of sarcasm. These demands range from modeling contextual expectation violations to requiring external knowledge grounding or recognizing specific rhetorical patterns. To address this limitation, we introduce RAM-SD, a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection. The framework operates through four stages: (1) contextual retrieval grounds the query in both sarcastic and non-sarcastic exemplars; (2) a meta-planner classifies the sarcasm type and selects an optimal reasoning plan from a predefined set; (3) an ensemble of specialized agents performs complementary, multi-view analysis; and (4) an integrator synthesizes these analyses into a final, interpretable judgment with a natural language explanation. Evaluated on four standard benchmarks, RAM-SD achieves a state-of-the-art Macro-F1 of 77.74%, outperforming the strong GPT-4o+CoC baseline by 7.01 points. Our framework not only sets a new performance benchmark but also provides transparent and interpretable reasoning traces, illuminating the cognitive processes behind sarcasm comprehension.

cs.CL↗

arXiv2026

Spider web-inspired sensing and computation with fiber network physical reservoirs

Physical reservoir computing leverages the intrinsic dynamics of mechanical systems to perform computation through their natural responses to input signals. Here, we study a compliant fiber network inspired by orb-weaving spider webs and investigate how its mechanical design and operating conditions shape its computational capability. Using Cosserat rod-based simulations, we identify how network topology, geometry, actuation, and axial tension impact the nonlinear computation and memory capacity of the network. We further evaluate several readout reduction strategies to assess how computational performance varies with the number and placement of measured outputs. We then experimentally validate these results using a physical fiber-network prototype. Overall, results provide insights and guidance on design, actuation, and sensing choices to enable fiber networks for mechano-intelligent computation. They demonstrate the ability of structured compliant fibers networks to serve as physical reservoirs capable of nonlinear transformation and input-history retention.

eess.SY↗

arXiv2025

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

AI agent frameworks operate in isolation, forcing agents to rediscover solutions and repeat mistakes across different systems. Despite valuable problem-solving experiences accumulated by frameworks like smolagents, OpenHands, and OWL, this knowledge remains trapped within individual systems, preventing the emergence of collective intelligence. Current memory systems focus on individual agents or framework-specific demonstrations, failing to enable cross-architecture knowledge transfer. We introduce AGENT KB, a universal memory infrastructure enabling seamless experience sharing across heterogeneous agent frameworks without retraining. AGENT KB aggregates trajectories into a structured knowledge base and serves lightweight APIs. At inference time, hybrid retrieval operates through two stages: planning seeds agents with cross-domain workflows, while feedback applies targeted diagnostic fixes. A disagreement gate ensures retrieved knowledge enhances rather than disrupts reasoning, addressing knowledge interference in cross-framework transfer. We validate AGENT KB across major frameworks on GAIA, Humanity's Last Exam, GPQA, and SWE-bench. Results show substantial improvements across diverse model families: compared to baseline pass@1, smolagents with AGENT KB achieve up to 18.7pp gains at pass@3 (55.2% -> 73.9%), while OpenHands improves 4.0pp on SWE-bench pass@1 (24.3% -> 28.3%). Similar improvements are observed across all base model families. Ablations confirm that hybrid retrieval and feedback stages are essential, with automatically generated experiences matching manual curation. This establishes the foundation for collective agent intelligence through shared memory infrastructures.

cs.CL↗

arXiv2025

Hyper Yoshimura: How a slight tweak on a classical folding pattern unleashes meta-stability for deployable robots

Deployable structures inspired by origami have provided lightweight, compact, and reconfigurable solutions for various robotic and architectural applications. However, creating an integrated structural system that can effectively balance the competing requirements of high packing efficiency, simple deployment, and precise morphing into multiple load-bearing configurations remains a significant challenge. This study introduces a new class of hyper-Yoshimura origami, which exhibits a wide range of kinematically admissible and locally metastable states, including newly discovered symmetric "self-packing" and asymmetric "pop-out" states. This metastability is achieved by breaking a design rule of Yoshimura origami that has been in place for many decades. To this end, this study derives a new set of mathematically rigorous design rules and geometric formulations. Based on this, forward and inverse kinematic strategies are developed to stack hyper-Yoshimura modules into deployable booms that can approximate complex 3D shapes. Finally, this study showcases the potential of hyper-Yoshimura with a meter-scale pop-up cellphone charging station deployed at our university's bus transit station, along with a 3D-printed, scaled prototype of a space crane that can function as an object manipulator, solar tracking device, or high-load-bearing structure. These results establish hyper-Yoshimura as a promising platform for deployable and adaptable robotic systems in both terrestrial and space environments.

cs.RO↗

arXiv2025

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model's generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization. Our project page is https://zionchow.github.io/ReconVLA/.

cs.RO↗

arXiv2024

"Golden Ratio Yoshimura" for Meta-Stable and Massively Reconfigurable Deployment

Yoshimura origami is a classical folding pattern that has inspired many deployable structure designs. Its applications span from space exploration, kinetic architectures, and soft robots to even everyday household items. However, despite its wide usage, Yoshimura has been fixated on a set of design constraints to ensure its flat-foldability. Through extensive kinematic analysis and prototype tests, this study presents a new Yoshimura that intentionally defies these constraints. Remarkably, one can impart a unique meta-stability by using the Golden Ratio angle to define the triangular facets of a generalized Yoshimura. As a result, when its facets are strategically popped out, a ``Golden Ratio Yoshimura'' boom with $m$ modules can be theoretically reconfigured into $8^m$ geometrically unique and load-bearing shapes. This result not only challenges the existing design norms but also opens up a new avenue to create deployable and versatile structural systems.

cs.RO↗

arXiv2024

UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement

Underwater image enhancement (UIE) plays a crucial role in various marine applications, but it remains challenging due to the complex underwater environment. Current learning-based approaches frequently lack explicit incorporation of prior knowledge about the physical processes involved in underwater image formation, resulting in limited optimization despite their impressive enhancement results. This paper proposes a novel deep unfolding network (DUN) for UIE that integrates color priors and inter-stage feature transformation to improve enhancement performance. The proposed DUN model combines the iterative optimization and reliability of model-based methods with the flexibility and representational power of deep learning, offering a more explainable and stable solution compared to existing learning-based UIE approaches. The proposed model consists of three key components: a Color Prior Guidance Block (CPGB) that establishes a mapping between color channels of degraded and original images, a Nonlinear Activation Gradient Descent Module (NAGDM) that simulates the underwater image degradation process, and an Inter Stage Feature Transformer (ISF-Former) that facilitates feature exchange between different network stages. By explicitly incorporating color priors and modeling the physical characteristics of underwater image formation, the proposed DUN model achieves more accurate and reliable enhancement results. Extensive experiments on multiple underwater image datasets demonstrate the superiority of the proposed model over state-of-the-art methods in both quantitative and qualitative evaluations. The proposed DUN-based approach offers a promising solution for UIE, enabling more accurate and reliable scientific analysis in marine research. The code is available at https://github.com/CXH-Research/UIE-UnFold.

cs.CV↗

arXiv2024

Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition

Learning to recognize novel concepts from just a few image samples is very challenging as the learned model is easily overfitted on the few data and results in poor generalizability. One promising but underexplored solution is to compensate the novel classes by generating plausible samples. However, most existing works of this line exploit visual information only, rendering the generated data easy to be distracted by some challenging factors contained in the few available samples. Being aware of the semantic information in the textual modality that reflects human concepts, this work proposes a novel framework that exploits semantic relations to guide dual-view data hallucination for few-shot image recognition. The proposed framework enables generating more diverse and reasonable data samples for novel classes through effective information transfer from base classes. Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes. Meanwhile, a prototype-view data hallucination module exploits semantic-aware measure to estimate the prototype of a novel class and the associated distribution from the few samples, which thereby harvests the prototype as a more stable sample and enables resampling a large number of samples. We conduct extensive experiments and comparisons with state-of-the-art methods on several popular few-shot benchmarks to verify the effectiveness of the proposed framework.

cs.CV↗

arXiv2024

DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal

Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability. Current shadow removal techniques, including traditional methods and deep learning approaches, face limitations in handling varying shadow intensities and preserving document details. To address these issues, we propose DocDeshadower, a novel multi-frequency Transformer-based model built upon the Laplacian Pyramid. By decomposing the shadow image into multiple frequency bands and employing two critical modules: the Attention-Aggregation Network for low-frequency shadow removal and the Gated Multi-scale Fusion Transformer for global refinement. DocDeshadower effectively removes shadows at different scales while preserving document content. Extensive experiments demonstrate DocDeshadower's superior performance compared to state-of-the-art methods, highlighting its potential to significantly improve document shadow removal techniques. The code is available at https://github.com/leiyingtie/DocDeshadower.

cs.CV↗