Searcharxiv⌕ Search

arXiv subjects

Cheng Zhang

Publications and source records attributed to Cheng Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

X2-N: A Transformable Wheel-legged Humanoid Robot with Dual-mode Locomotion and Manipulation

Wheel-legged robots combine the efficiency of wheeled locomotion with the versatility of legged systems, enabling rapid traversal over both continuous and discrete terrains. However, conventional designs typically employ fixed wheels as feet and limited degrees of freedom (DoFs) at the hips, resulting in reduced stability and mobility during legged locomotion compared to humanoids with flat feet. In addition, most existing platforms lack a full upper body with arms, which limits their ability to perform dexterous manipulation tasks. In this letter, we present X2-N, a high-DoF transformable robot with dual-mode locomotion and manipulation. X2-N can operate in both humanoid and wheel-legged forms and transform seamlessly between them through joint reconfiguration. We further propose a reinforcement learning (RL)-based whole-body control framework tailored to this morphology, enabling control across hybrid locomotion, transformation, and manipulation. We validate X2-N in a range of challenging locomotion and manipulation tasks, including dynamic skating-like motion, stair climbing, and package delivery. Results demonstrate high

cs.RO↗
arXiv2026

Lattice KP type equations arising from eigenfunctions and Dbar problem

In this paper, we construct the lattice Kadomtsev-Petviashvili (KP) type eigenfunction equations. A homogeneous nonlocal $\bar{\partial}$ problem is considered, from which we are able to define the eigenfunction of the Lax pair of the lattice KP equation. The eigenfunction together with its expansions at infinity and at a finite analytic point provide formulations of the lattice modified KP equation, the lattice Schwarzian KP equation and the Nijhoff-Quispel-Capel KP (NQC-KP) equation. We also consider an inhomogeneous nonlocal $\bar{\partial}$ problem. It defines the eigenfunction of the Lax pair of the lattice modified KP equation. This eigenfunction generates a direct formulation for the NQC-KP equation, which is different from the previous ones. Explicit solutions of these equations are obtained, from which we can see the difference of the different formulations for same equations.

nlin.SI↗
arXiv2026

Outrunning Big KATs: Efficient Decision Procedures for Variants of GKAT

This paper presents several efficient decision procedures for trace equivalence of GKAT automata, which make use of on-the-fly symbolic techniques via SAT solvers. To demonstrate applicability of our algorithms, we designed symbolic derivatives for CF-GKAT, a practical system based on GKAT designed to validate control-flow transformations. We implemented the algorithms in Rust and evaluated them on both randomly generated benchmarks and real-world control-flow transformations. Indeed, we observed order-of-magnitude performance improvements against existing implementations for both KAT and CF-GKAT. Notably, our experiments also revealed a bug in Ghidra, an industry-standard decompiler, highlighting the practical viability of these systems.

cs.PL↗
arXiv2026

Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models

Autoregressive text-to-image generation has recently achieved remarkable progress, offering high-fidelity synthesis via a unified generative framework. However, fine-grained semantic control remains challenging due to the attribute entanglement and the misalignment between textual and fine-grained visual representations. In this paper, we introduce Attribute Token Arithmetic (ATA), a method that enables disentangled and continuous attribute control in visual autoregressive modelling. Inspired by the vector arithmetic property observed in word embeddings, ATA identifies semantic directions corresponding to visual attributes (e.g., aging, fatness, emotion) directly within the pretrained autoregressive latent space. These directions are learned from a single reference image, without model retraining or large-scale supervision. During generation, attributes can be continuously adjusted and compositionally combined through simple arithmetic operations with other attribute tokens. Extensive experiments demonstrate that ATA achieves identity-preserving, fine-grained, and multi-attribute adjustment, outperforming existing autoregressive editing baselines in controllability, generality, and computational efficiency. Our code will be available at https://github.com/Madaoer/ATA.

cs.CV↗
arXiv2026

Giant bulk photovoltaic effect driven by interfacial symmetry breaking in MoS2/Ta2NiSe5 heterostructures

Van der Waals (vdW) heterostructures offer a versatile platform for engineering unconventional bulk photovoltaic (BPV) effect through interfacial symmetry breaking. However, the coexistence of multiple photophysical mechanisms, driven by structural complexity, spontaneous charge transfer, and strong interlayer coupling, often obscures the microscopic origin of the BPV response and hinders its rational optimization. Here, we demonstrate a pronounced BPV effect localized at the overlap region of a cross-bar MoS2/Ta2NiSe5 vdW heterostructure, where symmetry breaking induced by vertical stacking lifts the inversion center of MoS2. The orthogonal device geometry enables the independent probing of intralayer and interfacial photoresponse pathways, facilitating clear separation of competing mechanisms. Spontaneous interfacial charge transfer between MoS2 and Ta2NiSe5 further establishes a strong interlayer electronic coupling. By modulating the interlayer potential landscape through gate voltage and vertical electric fields, we achieve an optimized zero-bias photocurrent density of 247 A/cm2 and a BPV coefficient of 0.99 V-1. Supported by theoretical modelling, our results illustrate how minimalist device geometry can transform complex heterostructures into experimentally tractable platforms. This strategy paves the way for analyzing and optimizing interface-driven BPV effect, with implications for self-powered optoelectronics, broadband photodetection, and energy-harvesting nanodevices.

cond-mat.mes-hall↗
arXiv2026

Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence

Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context. Existing certified robustness methods are limited to single-turn inputs; naive multi-turn composition yields bounds that degrade exponentially in the number of turns. We introduce Multi-Turn Certified Robustness (MTCR), a framework that models conversational safety via State-Adversarial MDPs and defines $k$-turn certified robustness as the worst-case safety probability across $k$ adversarial turns. MTCR comprises: (i) compositional certification via embedding-space mode decomposition, yielding tighter certified lower bounds than naive multiplication; (ii) $(α,β)$-safety persistence, improving the degradation rate from $\underline{p}^{k}$ to $β^k$ (with $β> \underline{p}$) and yielding interpretable horizon estimates; (iii) matching information-theoretic upper bounds establishing tightness; and (iv) a unified algorithm combining these results. Experiments on six LLMs under $ε$-bounded and Crescendo-style attacks confirm that empirical safety consistently exceeds the certified bounds.

cs.AI↗
arXiv2026

GLaQ: Grounding Latent Queries in Visual Evidence for Multimodal Reasoning

Chain-of-thought reasoning has substantially improved the problem-solving capabilities of multimodal large language models. Fine-grained visual evidence, however, remains difficult to preserve and reuse across text-based reasoning steps. To address this limitation, tool-augmented thinking-with-images methods maintain visual access externally by revisiting or manipulating the image, but require predefined tools and additional inference-time processing. As an internal alternative, continuous visual latent reasoning retains intermediate computation in hidden states. However, its prevailing autoregressive construction makes each latent state depend on its predecessors, so later states may repeat information already present in the latent sequence rather than capture complementary visual details. We introduce GLaQ, a grounded latent-query framework that replaces sequential latent rollout with a fixed set of context-conditioned queries grounded in the original visual tokens. The grounded queries are reinjected for answer generation, providing direct and coordinated access to source visual evidence. We train GLaQ with localized-view supervision followed by reinforcement learning under task-level rewards. Across five benchmarks for fine-grained visual understanding and perception, GLaQ-7B gains 5.99--9.66\% over its base model and leads all compared visual latent methods, suggesting that direct query-to-image grounding can recover localized evidence from the full image without external visual operations or autoregressive latent rollouts.

cs.CV↗
arXiv2026

Rank-Aware Element Grouping for Power-Efficient Multiuser ISAC With an Extremely Large-Scale IRS

We investigate power-efficient multiuser integrated sensing and communication (ISAC) assisted by an element-grouping extremely large-scale intelligent reflecting surface (EG-XL-IRS). The grouping pattern is designed using slowly varying statistical channel state information (S-CSI), so that both IRS-related channel acquisition and online passive beamforming operate in the group domain rather than the element domain. We reveal a fundamental gain-rank tradeoff induced by element grouping: phase-consistent grouping can coherently enhance selected deterministic propagation components, while excessive concentration on a common deterministic mode can reduce the effective spatial rank of the multiuser channel and, for extended targets, the diversity of desired-scatterer responses. Motivated by this observation, we develop a task-adaptive rank-aware grouping strategy that balances weak-user enhancement and target-scatterer illumination while preserving task-relevant spatial dimensions. For each candidate grouping pattern, the transmit covariances and group-wise reflection phases are jointly optimized under communication and sensing quality-of-service constraints, followed by physical phase recovery and feasibility verification. Numerical results show that the proposed design substantially reduces the required transmit power compared with representative grouping benchmarks under the same grouping dimension and online optimization budget.

eess.SP↗
arXiv2026

ASI-Bench: At the Dawn of Artificial Superintelligence

Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and turning new ideas into verifiable results. However, the capabilities of today's AI systems are still largely built on learning, compressing, and applying existing human knowledge. Accordingly, existing benchmarks primarily test whether AI can produce correct answers based on learned knowledge, or whether it can complete tasks under extensive human guidance. We therefore introduce ASI-Bench, the first benchmark to jointly evaluate AI systems' capabilities of innovative exploration and autonomous scientific execution across general research domains, and the first to progressively withdraw human methodological guidance within the same research project to test how far AI can proceed on its own. Built by over 40 experts with the cost of 31,000+ human hours, ASI-Bench contains 60 project-level research tasks across 11 scientific domains and progressively reduces methodological guidance to test whether AI can independently select methods, conduct research, and produce verifiable results. All tasks undergo expert review, AI-assisted auditing, sandbox execution, and scorer validation. Across 18 state-of-the-art agent--model configurations, the average score drops from 50.91 with full methodological guidance to 29.10 with only the method specified and 26.62 when agents must determine the method themselves. This sharp decline shows that current systems remain heavily dependent on human guidance and are still far from autonomously conducting end-to-end, project-level scientific research. ASI-Bench is open to the world. We invite researchers and builders everywhere to contribute new tasks, challenge the limits of today's AI, and help accelerate humanity's collective path toward artificial superintelligence at https://asibench.apexin.ai/submit.

cs.AI↗
arXiv2026

US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina

Artificial intelligence-assisted ultrasound scanning enhances diagnostic reliability and efficiency by providing real-time guidance for standardized image acquisition and reducing operator dependence. However, existing reinforcement learning and learning-assisted ultrasound scanning methods typically rely on carefully designed reward functions or extensive interaction data, which limits their generalization ability and stability across different devices, patient populations, and complex clinical scenarios. To address these challenges, we propose an ultrasound vision-language-action model (US-VLA) for automated ultrasound scanning that explicitly encodes clinical semantic goals and generates sequential probe manipulation actions under real-time ultrasound feedback. In particular, we first design an ultrasound-aware expert fusion module to jointly integrate ultrasound observations with auxiliary contextual information, enabling semantic ultrasound feedback to effectively guide the scanning process. Then, we construct US-VLA-Data, a real-world dataset covering liver and kidney examinations, which includes five clinically defined standard planes and comprises 320 expert scanning trajectories with approximately 80,000 synchronized timesteps. Extensive experiments demonstrate that US-VLA achieves competitive performance in ultrasound probe manipulation tasks, indicating its effectiveness and promising generalization within the evaluated abdominal ultrasound setting. The source code is available at https://github.com/VMVLab/US-VLA.

cs.RO↗
arXiv2026

Sensorimotor Stickies: A Reconfigurable On-Body Platform for Closed-Loop Sensorimotor Training

Closed-loop sensorimotor training systems can improve learning by sensing movement and delivering real-time feedback, yet most are built as fixed implementations tied to a single task, even though the core technology (inertial and tactile sensing, vibrotactile cueing, rule-based logic) remains the same. We present Sensorimotor Stickies, a reconfigurable on-body platform that treats sensing and vibrotactile feedback as modular stickies that can be patched onto the body as needed. The platform includes miniaturized adhesive modules for IMU sensing, optional tactile sensing, and vibrotactile actuation; low-power firmware and BLE infrastructure for raw streaming and motor control without task-specific rewrites; and a companion mobile app that provides a shared body-centered model for placement, calibration, and feedback authoring. Together, these components enable reconfiguration across training scenarios, user needs, and feedback setups. We evaluate the platform through technical characterization, configured application demonstration, practitioner-mediated configuration sessions, and an end-user study, demonstrating technical feasibility, reconfiguration breadth, and end-user configurability for first-time setup, calibration, and within-task feedback reconfiguration.

cs.HC↗
arXiv2026

ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning

Embodied intelligent ultrasound scanning enables the automation and standardization of the ultrasound examination process by integrating perception, decision-making, and execution capabilities. However, existing methods suffer from loosely coupled modeling between force and ultrasound modalities and lack awareness of scanning stages, which limits their ability to capture dynamic probe-tissue interactions. To address these issues, we propose ForceU-VLA, a force-aware Vision-Language-Action model for autonomous embodied ultrasound scanning, which leverages force signals and ultrasound image feedback throughout the scanning process to enable accurate and high-quality ultrasound acquisition. Firstly, we propose a Force-Ultrasound Synergistic Fusion Module (FUSFM) that synergistically fuses ultrasound visual and force-feedback information to provide stable, reliable guidance for probe motion. Secondly, a Stage-Adaptive Modulation Mechanism (SAMM) is proposed to accommodate the task requirements across different scanning stages by adaptively modulating multimodal features to enhance their representation quality. Additionally, we introduce ForceU-VLA-Data, a real-world, force-aware embodied ultrasound dataset that integrates visual, force, and action signals, including data from two organs across five representative clinical scanning views, and comprising 450 expert-collected trajectories with approximately 100,000 synchronized multimodal frames. Extensive experimental results demonstrate that ForceU-VLA significantly improves contact stability and probe pressure regulation in embodied ultrasound scanning, thereby effectively enhancing task execution quality and overall system reliability. The source code is available at https://github.com/VMVLab/ForceU-VLA.

cs.RO↗
arXiv2026

CalibAnyView: Beyond Single-View Camera Calibration in the Wild

Camera calibration is fundamental to reliable geometric perception, yet classical approaches rely on dedicated targets, successful reconstruction, or dense view coverage, which casually captured imagery rarely satisfies. Recent learning-based single-image methods lift these requirements by exploiting visual cues, and extend calibration beyond intrinsics to gravity estimation. Yet in the common multi-view case, they predict each view independently and combine the estimates only afterwards, lacking full use of cross-view consistency. We bridge this gap with CalibAnyView, a framework that unifies single- and sparse multi-view calibration by enforcing that consistency inside the network: a transformer with cross-view attention predicts camera-model-agnostic perspective fields, followed by a multi-view optimization that fuses them into shared intrinsics and per-view gravity directions, covering camera models from pinhole to severely distorted lenses. To support this, we construct a large-scale in-the-wild multi-view video dataset spanning diverse camera models, dynamic scenes, realistic motion trajectories, and heterogeneous lens distortions. Extensive experiments show that CalibAnyView outperforms state-of-the-art methods in both sparse multi-view and single-view settings spanning pinhole to distorted optics.

cs.CV↗
arXiv2026

PinpointQA: A Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos

Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations. Yet this fundamental capability remains challenging for multimodal large language models (MLLMs), particularly when spatial understanding must be performed from indoor videos. Existing benchmarks study video spatial intelligence and embodied reasoning, but do not directly evaluate whether a model can localize a small target object and express its position with sufficient precision. We introduce PinpointQA, a benchmark built from ScanNet++ and ScanNet200. It contains 1,024 scenes and 10,094 QA pairs across four progressively challenging tasks: Target Presence Verification, Nearest Reference Identification, Fine-Grained Spatial Description, and Structured Spatial Prediction. Ground-truth annotations are constructed from intermediate spatial representations derived from aligned 3D geometry and instance-level annotations, while evaluated models receive only sampled RGB video frames. Evaluations of representative MLLMs reveal a consistent performance decline across the task progression, with structured spatial prediction remaining particularly challenging, while supervised fine-tuning substantially improves performance. By isolating the spatial grounding capabilities that precede downstream embodied interaction, PinpointQA serves as both a diagnostic benchmark and an effective training resource. The project page is available at https://rainchowz.github.io/PinpointQA/.

cs.CV↗
arXiv2026

Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models

Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources. To evaluate this missing capability, we introduce ST-OmniQA, a spatio-temporal audio-visual question-answering benchmark built from panoramic videos paired with synchronized first-order Ambisonics (FOA) audio of moving sound sources. It contains 40K videos and 400K question-answer pairs organized into four capability levels covering sound-event recognition, direction of arrival, source distance, motion trajectories, and temporally grounded audio-visual reasoning. Building on this benchmark, we propose ST-Omni-R1, which integrates FOA-derived semantic and trajectory representations with panoramic visual context and is trained through progressive curriculum learning and reasoning-tree reinforcement learning. ST-Omni-R1 achieves 77.83\% average semantic accuracy across the four levels, compared with 37.28\% for the best evaluated baseline. Results on three public spatial-audio benchmarks further indicate that its learned spatial and motion representations transfer beyond ST-OmniQA.

cs.AI↗
arXiv2026

Sharp Endpoint Eigenfunction Estimates for the Two-Dimensional Hermite Operator

Let $\mathcal H=-Δ+|x|^2$ be the Hermite operator on $\mathbb R^2$, and let $Π_λ$ denote the spectral projection corresponding to $λ=2N+2$. We prove the sharp log-free endpoint estimate $||Π_λ||_{L^2(\mathbb R^2)\to L^{10/3}(\mathbb R^2)}\lesssimλ^{-1/10}$. The proof uses a spectral decomposition in polar coordinates and combines Koch-Tataru localized spectral projection bounds with a Liouville-Green representation, van der Corput estimates for exponential sums, and a weighted $TT^*$ argument across radial scales.

math.AP↗
arXiv2026

Giant-exchange-driven Vectorial Control of a Minimal Topological Magnet in Eu3In2As4

The interplay between magnetism and band topology provides a route to controlling quantum states of matter, yet its realization in materials is often constrained by weak exchange coupling and complex electronic structures. Here, a giant exchange coupling is identified in the newly predicted topological magnet Eu3In2As4, giving rise to magnetization-dependent band shifts of up to 300 meV. Together with its intrinsically soft magnetic response, this strong cou-pling enables systematic tuning of topological phases by both the magnitude and orientation of applied magnetic fields. The magneto-topological phase diagram is mapped out in which an antiferromagnetic topological insulator ground state evolves, under modest fields, into a pro-posed intermediate 2/3-ferrimagnetic phase, and further into fully polarized ferromagnetic states predicted to host either Weyl or nodal-ring semimetals. Notably, the Weyl phase corresponds to a minimal model hosting a single pair of Weyl nodes. Quantum oscillations, anomalous Hall transport and magneto-infrared spectroscopy consistently reveal exchange-driven band recon-struction across these transitions. Rotation of the magnetization theoretically provides an effi-cient means to tune the momentum-space positions and separations of the Weyl nodes. These results establish Eu3In2As4 as a model system for exploring how strong exchange coupling can be used to control topological band structures with minimal complexity.

cond-mat.mtrl-sci↗