arXiv subjects

Zeyuan Wang

Publications and source records attributed to Zeyuan Wang.

At least 19 recordsLinked to original sources

arXiv2026

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation with dynamic references that can be updated at any moment, and stronger instruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, including style rendering, clothing replacement, character replacement, and background replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.

cs.CV↗

arXiv2026

Emergent Vibronic Spectral Hierarchy in a Kagome Flat-Band Insulator

Electron-phonon coupling is usually understood in terms of electronic quasiparticles interacting with dispersive lattice vibrations. Much less is known about the complementary limit in which the relevant phonon mode is itself localized or weakly dispersive. Here we investigate this regime in the kagome compound Rb$_{2}$Ni$_{3}$S$_{4}$, which undergoes an unconventional insulating transition near $T^{*} \approx$ 260-280~K. Combining polarization-resolved Raman spectroscopy with temperature-dependent x-ray diffraction, scanning tunneling microscopy, and electrical, thermal, and magnetic measurements, we show that the transition involves electronic localization without a conventional structural or magnetic order parameter. Raman spectra reveal a giant Franck-Condon progression associated with a nearly dispersionless 333.7~cm$^{-1}$ phonon, decorated by an equally spaced comb-like fine structure with a characteristic spacing of 40.6~cm$^{-1}$. The comb spacing is insensitive to magnetic field, whereas its spectral weight is strongly field tunable. Rather than treating either hierarchy alone as pure phonon effect, we interpret their nested coexistence as evidence for a strongly coupled electron-vibrational manifold involving a localized lattice coordinate. These results identify dispersionless phonons as an active route to vibronic correlations in solids and suggest that such electron-vibrational self-trapping is closely associated with the insulating phase of Rb$_{2}$Ni$_{3}$S$_{4}$.

cond-mat.str-el↗

arXiv2026

Neutral Atom Quantum Computing: Principles, Routes, Progress, and Challenges

Neutral atom quantum computing utilizes laser-trapped neutral atoms as qubits and realizes quantum logic gate operations through Rydberg-state interactions. In recent years, it has become one of the most vibrant directions in quantum computing hardware. This paper systematically reviews the working principles of neutral-atom quantum computers, including qubit encoding, atom trapping and manipulation, Rydberg states and interactions, the Rydberg blockade quantum gate mechanism, and atom rearrangement with reconfigurable architectures. The mainstream technical routes are surveyed, represented by optical tweezer arrays combined with Rydberg interactions, optical lattice schemes, and dipole trap arrays. A panoramic review is provided of domestic and international research progress from theoretical foundations in 2000 to the latest achievements in 2026, including thousand-qubit-scale systems, logical qubits, and quantum error correction experiments. Key breakthroughs are highlighted, such as the 6100-atom qubit array, continuous operation of a 3000-qubit system, quantum simulation of the Kitaev honeycomb model, toric code error correction demonstrations, encoding rates exceeding 1/2, and fault-tolerant architectures. The core bottlenecks are analyzed in depth, including the scalability--fidelity trade-off, engineering implementation of quantum error correction, atom loss and mid-circuit replenishment, laser system industrialization, control electronics scalability, and long-distance quantum interconnection. This paper aims to provide a systematic reference for academic research and technological development in this field.

quant-ph↗

arXiv2026

HI-HCQC: A Tightly-Coupled Hardware Interface with High-Efficiency Communication for Hybrid Classical-Quantum Computing

Hybrid classical-quantum computing requires frequent data exchange between classical processors and quantum control hardware. However, existing superconducting quantum control systems are commonly connected through loosely coupled interfaces such as Ethernet, resulting in high communication latency and limited task throughput. To address this issue, we present HI-HCQC, an RFSoC-based hardware interface for tightly coupled hybrid classical-quantum computing. HI-HCQC integrates high-speed RF-DACs, RF-ADCs, programmable logic, embedded processors, clock synchronization circuits, and a PCIe Gen3 x8 interface, enabling direct microwave pulse synthesis, qubit readout, and high-throughput data transfer between host servers and quantum measurement-control units. Experimental results show that HI-HCQC supports six control channels and one multiplexed readout channel, achieves stable microwave generation and acquisition, and successfully performs qubit spectroscopy, Rabi oscillation, T1 measurement, single-shot readout, randomized benchmarking, and CZ-gate characterization. Compared with a conventional control system, HI-HCQC reduces end-to-end execution latency for representative quantum gate and circuit tasks and significantly improves task throughput. These results demonstrate that PCIe-coupled RFSoC control hardware provides a practical foundation for scalable and efficient hybrid classical-quantum computing systems.

cs.DC↗

arXiv2026

Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions

Tool-using large language model agents frequently replan, retry failed operations, delegate tasks, and resume after crashes. These behaviors can cause one user authorization to be requested and executed multiple times under freshly issued token identifiers, even when each individual token is single-use. We call this failure semantic replay: exceeding the execution budget of a token-independent authorization instance rather than merely reusing an old token identifier. We show that identifier-local token consumption cannot prevent fresh reissuance unless the issuer retains monotonic durable state over the authorized action, confirmation event, and remaining execution budget. We introduce CapLease, an authorization-consumption layer that follows proposal- and authority-level defenses, binds an authenticated user confirmation to a canonical action, and enforces transactional Issue-Prepare-Commit transitions. Across LLM-agent replanning, retry, delegation, concurrency, confirmation-replay, and crash-recovery scenarios, identifier-local tokens permit fresh semantic reissuance, whereas CapLease and an equally stateful Server Ledger prevent duplicate admission and, with an idempotent sink, duplicate external effects. Our results identify durable authorization state, rather than token representation alone, as the systems requirement for replay-resistant agent execution.

cs.AI↗

arXiv2026

MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication

Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream. We introduce Minimum-Necessary Communication (MNC), a typed semantic-declassification protocol that selects a task-sufficient disclosure from an application-authored candidate family and binds it to explicit recipient, purpose, forwarding, lifetime, logging, and memory scopes. A reference monitor enforces these scopes across subsequent operations, while a history-aware extension accounts for inference risk accumulated over repeated disclosures. Controlled semantic-join, memory, probing, and longitudinal experiments show that conventional defenses can preserve protocol-level utility while exposing substantial additional inference signal. Under identical receipt text, MNC preserves authorized delivery while blocking unauthorized forwarding, logging, durable storage, and retrieval after expiration that a text-only semantic declassifier permits. Two-backbone MAGPIE executions further show that mediated disclosures propagate through subsequent planning, tool use, coordination, and memory retrieval. These results support scope-bound semantic declassification as a practical communication boundary for private LLM-agent systems.

cs.CR↗

arXiv2026

Motubrain: An Advanced World Action Model for Robot Control

Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present Motubrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, Motubrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling, a shared cross-embodiment action representation, and an efficient post-training and deployment recipe for long-horizon real-world control. Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution, achieving over 50x speedup over a naive baseline and up to 11 Hz inference. Experimentally, Motubrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.

cs.RO↗

arXiv2026

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios. To address these challenges, we propose an instruction-driven agentic framework comprising three components. First, LandslideBench, a multimodal fine-grained dataset with seven subtype labels, high-resolution imagery, pixel-level masks, and high-quality textual descriptions, is constructed via multi-VLM cross-validation and interactive annotation. Then, LandslideVLM, a landslide-oriented VLM, is fine-tuned via LoRA on LandslideBench to enhance geological semantic understanding. Finally, LandslideAgent, a domain rule-enhanced agent taking LandslideVLM as its cognitive backbone, employs a dual-rule controller incorporating structured report metadata constraints and cross-validation identification constraints to regulate automated tool invocation. Experiments demonstrate that LandslideBench provides effective baselines across five mainstream models on fine-grained classification and semantic segmentation. LandslideVLM achieves accuracy improvements of 10.96%, 32.87%, and 15.91% on landslide discrimination, fine-grained classification, and semantic description quality, respectively. LandslideAgent further enables autonomous multi-source spatial data inference, realizing full-process intelligence for landslide identification and analysis.

cs.CV↗

arXiv2026

Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schrödinger Bridge

Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically instantiated with simple Gaussian policies whose expressiveness can be limited in complex continuous-control tasks. Generative policies based on diffusion and flow models provide more expressive action distributions, but they naturally define distributions over multi-step denoising paths whose terminal action density is often intractable, creating a mismatch with likelihood-based on-policy proximal updates. To address this mismatch, we introduce \textbf{GSB-MDPO} (\emph{Generalized Schrödinger Bridge Mirror Descent Policy Optimization}), which formulates on-policy generative policy optimization as a Generalized Schrödinger Bridge problem over state-conditioned generation paths and instantiates the resulting path-measure update through mirror descent policy optimization. The key insight is that the GSB path-space KL plays the role of the proximal term in MDPO while upper-bounding the terminal action KL, enabling direct control of the executed action distribution without explicit terminal action likelihood evaluation. Experiments on 14 continuous-control tasks across Playground and Gym-MuJoCo demonstrate the empirical effectiveness of GSB-MDPO and support path-space regularization as a principled proximal update for multi-step generative policies.

cs.LG↗

arXiv2026

Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative sampling or lack tractable entropy estimates. On the optimisation side, SAC-style soft policy improvement and mirror descent (MD) can be viewed as minimising different KL divergences: the former moves the policy towards a value-induced Boltzmann distribution, while the latter regularises each update against the previous policy. Combining entropy regularisation with an MD constraint is therefore attractive, as it supports exploration while stabilising policy improvement; however, the resulting target can be multimodal and is poorly matched by unimodal Gaussian policies. We propose Stochastic MeanFlow Policies (SMFP), a one-step generative policy class that maps Gaussian noise to actions through a MeanFlow transformation. This stochastic reparameterisation yields a tractable entropy surrogate and allows MeanFlow policies to be trained within off-policy mirror descent under a unified objective for exploratory yet stable improvement. Across seven MuJoCo benchmarks, SMFP improves over Gaussian and generative baselines while retaining single-step inference efficiency.

cs.LG↗

arXiv2026

iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models

Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning isolated modules per task leads to parameter explosion. Conversely, recent similarity-driven sharing mechanisms falsely equate superficial visual similarity with underlying alignment consistency. This fundamental mismatch triggers severe negative transfer between visually similar but logically distinct tasks and fails to exploit alignment reuse across visually diverse ones. We argue thatalignment sharing is fundamentally a geometric problem of overlapping optimization trajectories within shared low-rank subspaces. Grounded in this insight, we propose iGSP, a novel framework that achieves efficient adaptation via implicit gradient subspace projection. Leveraging the early convergence of MoE routers to establish the subspace basis, iGSP bifurcates the adaptation process into two phases. First, the Subspace Identification phase introduces candidate experts via basis pre-expansion, applies a novel subspace-constrained regularization to implicitly project new task gradients onto the historical subspace, and precisely prunes redundant dimensions by treating routing probabilities as gradient flow indicators, ultimately to maximize knowledge reuse. Second, the Orthogonal Subspace Fine-Tuning phase fixes this structural basis and removes the regularization to rapidly fit the task-specific residual loss. Extensive experiments on the MTIL benchmark demonstrate that iGSP achieves state-of-the-art accuracy while significantly improving training efficiency, reducing the average trainable parameters by 42.7\% compared to current SOTA methods, and decreasing the final total parameters by 86.9\% relative to counterparts. The source code is available at https://github.com/GeoX-Lab/iGSP.

cs.CV↗

arXiv2026

RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents

The rise of multi-modal large language models (MLLMs) is shifting remote sensing (RS) intelligence from "see" to "action", as OpenClaw-style frameworks enable agents to autonomously operate massive RS image-processing tools for complex tasks. Existing RS agents adopt a passive selection paradigm for tool invocation, relying on either full tool registration (Flat) or retrieval-augmented generation (RAG). However, in the massive and multi-source heterogeneous RS tool ecosystem, such passive mechanisms struggle to dynamically balance "context load" and "toolset completeness" throughout task reasoning, thus exhibiting inherent limitations: full tool registration triggers context space deficits during long-horizon tasks, whereas RAG retrieval may omit critical tools in essential steps. To overcome these bottlenecks, this paper redefines tool selection by arguing that the agent should act as an active explorer within the tool space. Based on this perspective, we propose RS-Claw, a novel RS agent architecture. By leveraging Skill encapsulation technology at the tool end, this architecture hierarchically structures tool descriptions, enabling the agent to execute on-demand sequential decision-making: initially selecting relevant skill branches by reading only tool summaries, then dynamically loading detailed descriptions, and ultimately achieving precise invocation. This active paradigm not only significantly liberates the agent's context space but also effectively ensures the accurate hit rate of critical tools during long-horizon reasoning. Systematic experiments on the Earth-Bench benchmark demonstrate that RS-Claw's active exploration mechanism effectively filters semantic noise and substantially frees up reasoning space, achieving an input token compression ratio of up to 86%, and comprehensively outperforming existing Flat and RAG baselines across complex reasoning evaluations.

cs.AI↗

arXiv2026

Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents

Large language model (LLM)-based agents provide a novel paradigm for the automated processing of remote sensing(RS) data. Their success in complex RS tasks rely on extensive specialized tool libraries. However, tool documentation often exceeds the context window limits of LLMs, making precise tool retrieval essential for agentic workflows. Existing tool retrieval methods face "semantic asymmetry" bottleneck: natural language queries typically express macro-level intentions lacking tool-specific semantics, while tool documentation provides fine-grained technical descriptions lacking operational context for workflows. To bridge this semantic gap, this paper proposes a bidirectional semantic complementary tool retrieval method. First, on the query side, we introduce a planning-based query enhancement mechanism that leverages the reasoning capabilities of agents to decompose abstract intentions into logical subtasks, thereby actively supplementing the query with missing functional semantics. Second, on the tool side, addressing the strong coupling characteristics of RS tool chains, we construct a dynamic tool dependency graph with continual learning capabilities. By employing a neighborhood information aggregation mechanism, contextual information from precursor tools is explicitly injected into the current node representation, enriching tool descriptions with contextual semantics. Experimental results on the RS dataset GeoPlan-bench and the general-purpose dataset API- Bank demonstrate that the proposed method not only significantly improves tool retrieval accuracy for complex RS tasks but also exhibits robust extensibility for transfer to general-domain tasks. The source code and dataset are available at https://github.com/geox-lab/BSCTR.

cs.IR↗

arXiv2026

SciEval: A Benchmark for Automatic Evaluation of K-12 Science Instructional Materials

The need to evaluate instructional materials for K-12 science education has become increasingly important, as more educators use generative AI to create instructional materials. However, the review of instructional materials is time-consuming, expertise-intensive, and difficult to scale, motivating interest in automated evaluation approaches. While large language models (LLMs) have shown strong performance on general evaluation tasks, their performance and reliability on instructional materials remain unclear. To address this gap, we formulate Automatic Instructional Materials Evaluation (AIME) as a generative AI task that predicts scores and evidence using the rubric designed by the educator. We create a benchmark dataset and develop baseline models for AIME. First, we curate the first AIME dataset, SciEval, consisting of instructional materials annotated with pedagogy-aligned evaluation scores and evidence-based rationales. Expert annotations achieve high inter-rater reliability, resulting in a dataset of 273 lesson-level instructional materials evaluated across 13 criteria (N=3549) using the EQuIP rubric. Second, we test mainstream LLMs (GPT, Gemini, Llama, and Qwen) on SciEval and find that none achieve strong performance. Then we fine-tune Qwen3 on SciEval. Results on a held-out test set show that domain-aligned fine-tuning can achieve up to 11 percent performance gains, highlighting the importance of domain-specific fine-tuning for AIME and facilitating the use of LLMs in other educational tasks.

cs.AI↗

arXiv2026

RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding

Reinforcement learning (RL) post-training substantially improves remote sensing vision-language models (RS-VLMs). However, when handling complex remote sensing imagery (RSI) requiring exhaustive visual scanning, models tend to rely on localized salient cues for rapid inference. We term this RL-induced bias "perceptual inertia". Driven by reward maximization, models favor quick outcome fitting, leading to two limitations: cognitively, overreliance on specific features impedes complete evidence construction; operationally, models struggle to flexibly shift visual focus across tasks. To address this bias and encourage comprehensive visual evidence mining, we propose RS-HyRe-R1, a hybrid reward framework for RSI understanding. It introduces: (1) a spatial reasoning activation reward that enforces structured visual reasoning; (2) a perception correctness reward that provides adaptive quality anchors across RS tasks, ensuring accurate geometric and semantic alignment; and (3) a visual-semantic path evolution reward that penalizes repetitive reasoning and promotes exploration of complementary cues to build richer evidence chains. Experiments show RS-HyRe-R1 effectively mitigates "perceptual inertia", encouraging deeper, more diverse reasoning. With only 3B parameters, it achieves state-of-the-art performance on REC, OVD, and VQA tasks, outperforming models up to 7B parameters. It also demonstrates strong zero-shot generalization, surpassing the second-best model by 3.16%, 3.97%, and 2.72% on VQA, OVD, and REC, respectively. Code and datasets are available at https://github.com/geox-lab/RS-HyRe-R1.

cs.CV↗

arXiv2026

MPI-Q: A Message Communication Library for Large-Scale Classical-Quantum Heterogeneous Hybrid Distributed Computing

The classical-quantum system heterogeneity (different data characteristics, execution paradigms and synchronization mechanism etc.) renders existing distributed communication mechanisms (e.g. MPI, NCCL etc.) inadequate. This bottleneck severely impairs operational synergy and programming efficiency. Thus, the performance of hybrid applications on classical-quantum heterogeneous infrastructures is directly limited. To address these challenges, this paper proposes a message-passing library tailored for large-scale classical-quantum heterogeneous distributed computing, referred to as MPI-Q. The design centers on three mechanisms. First, it defines a heterogeneous hybrid communication domain that achieves unified management of classical and quantum processes in heterogeneous hybrid systems. Second, it uses a lightweight communication path that allows classical control nodes to send device-ready waveform data directly to quantum MonitorProcesses, avoiding unnecessary relay stages. Third, it establishes a heterogeneous hybrid synchronization mechanism to tackle the problem of timing control for multi-node quantum operations. While retaining the traditional MPI programming model, MPI-Q achieves extension toward quantum subsystems. Experiments on distributed GHZ state preparation demonstrate that this model exhibits near-linear scalability, achieving a maximum speedup of 18.76 times on 24 quantum nodes. This proves that the library can effectively support large-scale heterogeneous hybrid distributed computing applications, filling the technical gap in this field.

cs.DC↗

arXiv2026

Biomedical active matter: Emergence and breakdown of collective functionalities

Living systems are made of active materials with microscopic components that work together to perform macroscopic biological tasks. The breakdown of these collective functionalities leads to diseases, which, conversely, could be treated by exploiting self-organization in healthcare technologies. Here, we review recent advances in this rapidly growing field of biomedical active matter. The main themes are (1) collective self-assembly and spatiotemporal coordination; (2) collective motion, transport, and navigation; (3) collective sensing, signaling, and communication; and (4) collective adaptation, evolution, and learning. We discuss these emerging processes in a wide range of systems, including protein folding, biomolecular condensates, cytoskeleton dynamics, intracellular flows, bacterial biofilms, quorum sensing, cilia synchronization, wound healing, biolocomotion, neurons, endocrine signalling, and cardiovascular flow networks. For each, we highlight medical conditions associated with reduced collective functionality and how they may be treated using microrobotic swarms, bioinspired metamaterials, diagnostics, lab-on-chip devices, organoids, and other active and adaptive matter innovations.

physics.bio-ph↗

arXiv2026

Virtual Community: An Open World for Humans, Robots, and Society

The rapid progress in AI and Robotics may lead to a profound societal transformation, as humans and robots begin to coexist within shared communities, introducing both opportunities and challenges. To explore this future, we present Virtual Community-an open-world platform for humans, robots, and society-built on a universal physics engine and grounded in real-world 3D scenes. With Virtual Community, we aim to enable the study of embodied social intelligence at scale. To support these, Virtual Community features: 1) An open-source multi-agent physics simulator that supports robots, humans, and their interactions within a society; 2) A large-scale, real-world aligned community generation pipeline, including vast outdoor space, diverse indoor scenes, and a community of grounded agents with rich characters and appearances. Leveraging Virtual Community, we propose two novel challenges. The Community Planning Challenge evaluates multi-agent reasoning and planning ability in open-world settings, such as cooperating to help agents with daily activities and efficiently connecting other agents. The Community Robot Challenge requires multiple heterogeneous robots to collaborate in solving complex open-world tasks. We evaluate various baselines on these tasks and demonstrate the challenges in both high-level open-world task planning and low-level cooperation controls. We hope that Virtual Community will unlock further study of human-robot coexistence within open-world environments.

cs.CV↗