Searcharxiv⌕ Search

arXiv subjects

Yuntian Wang

Publications and source records attributed to Yuntian Wang.

At least 19 recordsLinked to original sources

VBot Exo2Ego Policy: Lightweight Data Collection and Exocentric-to-Egocentric Video Generation

We present VBot Exo2Ego Policy, a video generation model that turns third-person videos into first-person observations of a selected actor, offering a practical way to expand first-person operation data from abundant real-world footage. To support this goal, we introduce a lightweight data collection pipeline and mobile app that support first-person recording, third-person recording, and synchronized capture of both views. This setup combines accessible single-view collection with paired RGB and camera geometry for learning cross-view correspondence. Building on a pretrained video diffusion transformer, our model incorporates geometric guidance and auxiliary supervision from semantic masks and hand keypoints to facilitate optimization and improve the fidelity of hand-object interactions. Camera geometry is injected stochastically during training and gradually removed, allowing inference without target-camera calibration. To accommodate the diversity of Internet videos, we combine source-video perception and reasoning, optional actor references, and multi-shot adaptation to identify the intended actor and follow an operation across camera cuts. The collection system and generation model provide a foundation for expanding first-person operation data across tasks, scenes, and participants.

cs.CV↗

Learned optical compression for single-pixel quantitative phase imaging

Quantitative phase imaging (QPI) reveals optical path-length variations in transparent objects but typically relies on spatially resolved intensity measurements. Here we numerically and experimentally demonstrate learned optical compression for single-pixel QPI, jointly optimizing a diffractive encoder and a digital neural decoder to concentrate reconstruction-relevant phase information into a compact measurement vector. A single reconfigurable phase-modulation plane sequentially displays the learned encoding patterns, which are independent of the input object, each yielding one scalar intensity measurement. Operating at a visible wavelength, the experimental system reconstructs quantitative phase images of unknown objects with ~40-fold dimensional compression, using only 2.55% as many intensity measurements as reconstructed pixels. Experimental blind testing on handwritten digits and grating-like phase objects achieves mean Pearson correlation coefficients of 0.945 and 0.848, respectively. Benchmarking under the same measurement budget demonstrates substantially higher reconstruction fidelity than other encoding strategies, highlighting the advantages of learned optical compression. With the optical encoder fixed, decoder-only neural adaptation enables experimental transfer to previously unseen data distributions, extending the utility of the learned measurement representation. These results establish learned optical compression as a measurement-efficient and reusable framework for QPI, integrating phase-information compression into single-pixel intensity measurements while retaining adaptability to new data. This approach paves the way for low-data-rate phase imaging and sensing, with the potential to extend QPI to spectral regions where high-quality detector arrays are costly or unavailable.

physics.optics↗

Functional Superoscillations in a Wave Processor

Physical wave processors are constrained by diffraction, but the bandwidth of the mathematical functions they implement need not be set by it. Here, we demonstrate continuous and multiplexed optical processing of superoscillatory functions, in which a scalar argument is encoded onto a wavefront and a fixed diffractive wave processor synthesizes optical responses that approximate the corresponding function outputs in parallel. Unlike conventional superoscillatory optics that generates predetermined fields, superoscillation here is expressed in the input-output dependence on the encoded argument. Its frequencies are therefore distinct from the transverse spatial frequencies of propagating light and are not subject to the same diffraction-imposed cutoff. We demonstrate complex-valued superoscillatory function synthesis and introduce a multiplexed architecture that simultaneously evaluates distinct target superoscillatory functions whose harmonic content exceeds that of the optical input encoding. Visible-light experiments further validate this beyond-encoding superoscillatory regime. Together, these results establish functional superoscillation as a design principle for wave-based computation and show how interference, diffractive depth and spatial channel allocation extend the functional reach of passive wave processors. More broadly, these analyses establish a separation between functional bandwidth and physical wave bandwidth in analog optical computation.

physics.optics↗

Predict in Chunks, Revise in Spans: History-conditioned Action Regeneration for Robotic Manipulation

Action chunking improves temporal coherence in visuomotor imitation learning by jointly predicting sequences of future actions. However, many existing policies regenerate entire action chunks even when errors are localized, potentially replacing otherwise valid predictions. We introduce Contextual Masked Action Policy (CMAP), a visuomotor policy that refines continuous action chunks through history-conditioned local regeneration. Specifically, CMAP introduces a history-conditioned action tape that combines executed commands with masked future positions to produce coarse action predictions and per-step uncertainty scores. An uncertainty-guided span regeneration mechanism then selects a high-uncertainty contiguous span and reconstructs it using the executed history and retained future predictions as context. By jointly reconstructing neighboring actions, CMAP models local temporal dependencies while preserving all predictions outside the selected span. Extensive experiments on nine simulated and four real-world manipulation tasks demonstrate that CMAP achieves superior overall performance over several competitive baselines. Ablation studies validate the complementary contributions of its key components, while held-out trajectory analysis shows that local regeneration reduces prediction errors within selected spans.

cs.RO↗

Assessing the Marginal Utility of Exocentric Head Views in UMI-Style Large-FoV Wrist-Camera Manipulation

Multi-view perception is often treated as a safe design choice for robot manipulation: if one camera is useful, more cameras should be better. We revisit that assumption in tabletop bimanual manipulation by comparing policies trained with two large-field-of-view (FoV) wrist cameras against policies that additionally receive a head view, using controlled-variable experiments on a real bimanual platform. Across three tabletop tasks, adding a head view does not consistently improve task completion or execution quality: when the wrist cameras already observe the objects, grippers, and goal regions, wrist-only policies form a strong baseline. Restricting the wrist-camera FoV increases the potential value of a head view, but performance improves most reliably when the added view supplies concentrated, task-relevant information: region-of-interest (ROI) cropping yields more consistent head-view gains than the uncropped image, which is dominated by background and task-irrelevant regions. The data-scaling results further suggest an interaction between FoV and demonstration count: wide observations improve coverage but may require more data to stabilize, and they may reach a higher performance ceiling once enough demonstrations are available. These results suggest that camera design should be framed as a task-relevance and information-density problem rather than as a simple count of input views.

cs.RO↗

Scope-WM: Scoped Computation for Efficient Visual World Models

Visual world models enable robotic planning by predicting future observations, but dense latent-state propagation and sample-intensive trajectory optimization incur high inference latency and peak memory usage, limiting real-time deployment on resource-constrained platforms. Existing sparse world-model acceleration methods either rely on unguided token sparsification, which may discard planning-relevant information and restrict achievable sparsity, or introduce heavy auxiliary modules and cumbersome multi-stage training pipelines. In this work, we present Scope-WM, an efficient visual world model that scopes computation to prediction-relevant latent regions and promising action sequences. Scope-WM distills prediction relevance into a lightweight action-conditioned selector and applies full dynamics prediction only to a compact subset of selected tokens. It updates the remaining tokens using a compact summary of foreground states and their changes, allowing the background to perceive foreground dynamics without costly token-to-token interactions. During planning, Scope-WM preserves and reuses high-quality action sequences discovered during the initial MPC search, focusing subsequent search under reduced rollout budgets. The resulting pipeline requires only a one-off selector distillation followed by a single joint training stage for the sparse world model. On the challenging Push-T task, Scope-WM reduces peak GPU memory usage and planning time to $18.1\%$ and $14.3\%$ of those of dense DINO-WM, respectively, corresponding to a $6.97\times$ planning speedup, while maintaining competitive task performance. Further evaluations across five diverse visual planning tasks demonstrate the general applicability of Scope-WM. Code is available at https://github.com/ChunZheng2022/Scope-WM.

cs.CV↗

Wavelength-Multiplexed Nonlinear Computing with a Single-Layer Diffractive Optical Processor

Diffractive optical processors provide a promising platform for high-throughput, low-latency analog computing by exploiting engineered wave propagation to transform optical fields. However, implementing nonlinear mappings in optical hardware remains challenging. Here, we introduce a wavelength-multiplexed encoding-and-decoding (E+D) diffractive processor that exploits multiple illumination wavelengths to enhance the nonlinear function-approximation capability of a compact single-layer diffractive architecture, without cascading multiple diffractive layers or increasing the trainable degrees of freedom. Under sequential wavelength scanning, each wavelength-detector channel implements a distinct nonlinear function at the output of the diffractive processor. Numerical simulations using 100 wavelength channels and 10,000 spatial detector regions at the output of the diffractive processor demonstrate the implementation of one million distinct nonlinear functions through wavelength multiplexing. We also demonstrate a simultaneous multiwavelength illumination configuration in which the E+D diffractive processor performs wavelength-division multiplexing and nonlinear function approximation concurrently. This multiwavelength illumination configuration is experimentally validated by optically implementing 64 distinct nonlinear functions under simultaneous illumination at eight wavelengths from 495 to 635 nm. Through numerical simulations and visible-light experimental demonstrations, our results indicate that this wavelength-multiplexed nonlinear function approximation framework provides a scalable route toward compact, high-capacity diffractive processors for large-scale analog optical computing and optical information processing.

physics.optics↗

Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies

Learning chunk-based visuomotor policies for long-horizon robot manipulation remains challenging. Recent action-chunking methods have shown promising performance by predicting temporally extended action sequences. However, their failures are often dominated by prediction errors at a small number of critical timesteps rather than uniformly poor predictions across the entire action chunk, making uniform refinement inefficient and insufficiently targeted. To address this bottleneck, we propose Uncertainty-Guided Refinement (UGR), a sparse refinement framework for chunk-based visuomotor policies. Specifically, UGR follows a coarse-to-refine design: it first predicts a full action chunk, estimates per-step temporal uncertainty from the coarse hidden states, and applies residual correction only to the most uncertain timesteps selected by a binary mask. The uncertainty branch is decoupled from the coarse action predictor, enabling clean attribution of the refinement gains to uncertainty-guided correction rather than additional predictor capacity. Extensive experiments on five dual-arm manipulation tasks from the RoboTwin benchmark show that UGR achieves the best success rate on four tasks, improves over the ACT baseline by up to 13% absolute, and outperforms both full-chunk and position-agnostic block refinement in ablation studies.

cs.RO↗

ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation

Learning visuomotor policies for long-horizon manipulation remains a fundamental challenge. Recent skill-based imitation learning methods based on discrete quantization have shown promising results by representing complex behaviors as temporally extended skills. However, most existing approaches primarily encode action trajectories into latent skills, yielding weak visual-semantic grounding and limiting the ability to leverage visual observations for skill selection. Moreover, discrete tokenization inevitably incurs precision errors during continuous action generation. To alleviate these issues, we propose Aligned Refinement Policy (ARP), a discrete-skill framework that couples semantic grounding with execution-level refinement. Specifically, ARP introduces (i) a visual--action alignment objective that contrastively aligns visual embeddings with pre-quantized action representations in a shared latent space while preserving a state-independent skill decoder, and (ii) a lightweight Iterative Residual Head (IRH) that performs a two-step refinement to recover fine-grained control for precise execution. Extensive experiments show that ARP achieves state-of-the-art performance on the LIBERO and Meta-World benchmarks. Moreover, real-robot experiments on the Kuavo 4 Pro humanoid platform further validate its effectiveness, yielding consistent performance gains over several baselines on two challenging manipulation tasks.

cs.RO↗

UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data

Real-robot evaluation is essential for understanding whether learned manipulation policies can operate reliably outside curated demonstrations. This need is particularly pressing for Universal Manipulation Interface (UMI)-style policies, whose performance depends on the coupling between wrist-view observations, action representation, data collection, and physical deployment. Existing real-world benchmarks have made important progress, but they are not designed around this UMI data-to-deployment setting. We present UMI-Bench 1.0, a local-first real-robot benchmark for standardized evaluation of UMI-style manipulation policies. To the best of our knowledge, this is the first benchmark dedicated to real-world evaluation of UMI-based manipulation models. UMI-Bench aligns data collection, scene reset, policy execution, result logging, and task-factor analysis within a unified protocol. By making the full evaluation process reproducible and auditable, UMI-Bench provides a practical testbed for measuring how UMI-trained policies generalize to real physical manipulation.

cs.RO↗

Breaking the Cascade: Compact Nonlinear Optical Computing with Single-Layer Encoder-Decoder Co-Localization

We demonstrate that nonlinear computing can be achieved with a single linear diffractive surface under coherent illumination. We introduce a compact encoder-decoder co-localization (E+D) architecture in which an input-dependent dynamic encoder and a static optimized decoder are integrated within the same phase-only diffractive plane. Following free-space propagation, coherent interference between the encoder and decoder fields, combined with intensity detection, generates programmable nonlinear input-output mappings without requiring nonlinear optical materials or multiple diffractive layers. We prove that the proposed E+D optical processor is a universal approximator for arbitrary real-valued band-limited nonlinear functions and identify the physical factors governing its approximation fidelity, including the decoder degrees-of-freedom, detector aperture, and axial propagation distance. Crucially, we demonstrate that introducing a trained, frozen phase bias to the encoder region systematically enhances functional expressivity, providing robustness against coarse phase quantization on spatial light modulators. Using this framework, we accurately synthesize diverse nonlinear functions, including commonly used neural network activation functions and complex-valued nonlinear functions. Finally, we experimentally validate the proposed approach using a visible-light optical set-up trained through in situ learning, demonstrating the parallel approximation of 9 nonlinear functions in a single optical forward pass. By collapsing nonlinear optical computation into a single diffractive surface, the E+D architecture substantially reduces hardware and alignment complexity while preserving powerful function-approximation capabilities, providing a compact and scalable framework for analog information processing.

physics.optics↗

Large-scale nonlinear optical computing with incoherent light via linear diffractive systems

Nonlinear computation is essential for various information processing tasks. Optical implementations are attractive because passive light propagation can manipulate high-dimensional signals with extreme throughput and parallelism; yet realizing nonlinear mappings in optical hardware remains challenging due to the weak nonlinearity of optical materials and the large intensities required to induce nonlinear interactions. This challenge is further amplified in many systems that operate with incoherent illumination, motivating a coherence-aware framework for scalable optical nonlinear processing. Here, we show that linear optical systems, in particular, optimized diffractive processors comprising passive surfaces, can perform large-scale nonlinear function approximation under spatially incoherent or partially coherent illumination, when preceded by intensity-only input encoding. We quantify how the accuracy of the nonlinear function approximation varies with the degree of parallelism, the number of diffractive layers, and the number of trainable diffractive features. Numerical results demonstrate snapshot computation of up to one million distinct nonlinear functions in a single forward pass through a diffractive processor, with the function outputs spatially multiplexed and read out using densely packed detectors at the output. We further provide a proof-of-concept experimental demonstration under incoherent illumination from a liquid crystal display (LCD), enabled by a model-free in situ learning strategy that jointly optimizes the diffractive profile and detector readout geometry in the presence of hardware imperfections and misalignments. Our findings establish diffractive processors as a massively parallel universal function approximator for both spatially incoherent and partially coherent illumination.

physics.optics↗

Compressive single-pixel imaging via a wavelength-multiplexed spatially incoherent diffractive optical processor

Despite offering high sensitivity, a high signal-to-noise ratio, and a broad spectral range, single-pixel imaging (SPI) is limited by low measurement efficiency and long data-acquisition times. To address this, we propose a wavelength-multiplexed, spatially incoherent diffractive optical processor combined with a compact/shallow digital artificial neural network (ANN) to implement compressive SPI. Specifically, we model the bucket detection process in conventional SPI as a linear intensity transformation with spatially and spectrally varying point-spread functions. This transformation matrix is treated as a learnable parameter and jointly optimized with a shallow digital ANN composed of 2 hidden nonlinear layers. The wavelength-multiplexed diffractive processor is then configured via data-free optimization to approximate this pre-trained transformation matrix; after this optimization, the diffractive processor remains static/fixed. Upon multi-wavelength illumination and diffractive modulation, the target spatial information of the input object is spectrally encoded. A single-pixel detector captures the output spectral power at each illumination band, which is then rapidly decoded by the jointly trained digital ANN to reconstruct the input image. In addition to our numerical analyses demonstrating the feasibility of this approach, we experimentally validated its proof-of-concept using an array of light-emitting diodes (LEDs). Overall, this work demonstrates a computational imaging framework for compressive SPI that can be useful in applications such as biomedical imaging, autonomous devices, and remote sensing.

physics.optics↗

Structured Light at the Extreme: Harnessing Spatiotemporal Control for High-Field Laser-Matter Interactions

This review charts the emerging paradigm of intelligent structured light for high-field laser-matter interactions, where the precise spatiotemporal and vectorial control of light is a critical degree of freedom. We outline a transformative framework built upon three synergistic pillars. First, we survey the advanced electromagnetic toolkit, moving beyond conventional spatial light modulators to include robust static optics and the promising frontier of plasma light modulators. Second, we detail the optimization engine for this high-dimensional design space, focusing on physics-informed digital twins and AI-driven inverse design to automate the discovery of optimal light structures. Finally, we explore the groundbreaking applications enabled by this integrated approach, including programmable electron beams, orbital-angular-momentum-carrying γ-rays, compact THz accelerators, and robust communications. The path forward necessitates overcoming grand challenges in material science, real-time adaptive control at MHz rates, and the extension of these principles to the quantum realm. This review serves as a call to action for a coordinated, interdisciplinary effort to command, rather than merely observe, light-matter interactions at the extreme.

physics.optics↗

Universal and Transferable Attacks on Pathology Foundation Models

We introduce Universal and Transferable Adversarial Perturbations (UTAP) for pathology foundation models that reveal critical vulnerabilities in their capabilities. Optimized using deep learning, UTAP comprises a fixed and weak noise pattern that, when added to a pathology image, systematically disrupts the feature representation capabilities of multiple pathology foundation models. Therefore, UTAP induces performance drops in downstream tasks that utilize foundation models, including misclassification across a wide range of unseen data distributions. In addition to compromising the model performance, we demonstrate two key features of UTAP: (1) universality: its perturbation can be applied across diverse field-of-views independent of the dataset that UTAP was developed on, and (2) transferability: its perturbation can successfully degrade the performance of various external, black-box pathology foundation models - never seen before. These two features indicate that UTAP is not a dedicated attack associated with a specific foundation model or image dataset, but rather constitutes a broad threat to various emerging pathology foundation models and their applications. We systematically evaluated UTAP across various state-of-the-art pathology foundation models on multiple datasets, causing a significant drop in their performance with visually imperceptible modifications to the input images using a fixed noise pattern. The development of these potent attacks establishes a critical, high-standard benchmark for model robustness evaluation, highlighting a need for advancing defense mechanisms and potentially providing the necessary assets for adversarial training to ensure the safe and reliable deployment of AI in pathology.

cs.CV↗

The high order spectral radius of graphs without long cycles or paths

In 1959, Erdős and Gallai established two classic theorems, which determine the maximum number of edges in an $n$-vertex graph with no cycles of length at least $k$, and in an $n$-vertex graph with no paths on $k$ vertices, respectively. Subsequently, generalized and spectral versions of the Erdős-Gallai theorems have been investigated. A concept of a high order spectral radius for graphs was introduced in 2023, defined as the spectral radius of a tensor and termed the $t$-clique spectral radius $ρ_t(G)$. In this paper, we establish a high order spectral version of Erdős-Gallai theorems by employing the $t$-clique spectral radius, i.e., we determine the extremal graphs that attain the maximum $t$-clique spectral radius in the $n$-vertex graphs with no cycles of length at least $k$ and in the $n$-vertex graphs with no paths on $k$ vertices, respectively.

math.CO↗

Structural Vibration Monitoring with Diffractive Optical Processors

Structural Health Monitoring (SHM) is vital for maintaining the safety and longevity of civil infrastructure, yet current solutions remain constrained by cost, power consumption, scalability, and the complexity of data processing. Here, we present a diffractive vibration monitoring system, integrating a jointly optimized diffractive layer with a shallow neural network-based backend to remotely extract 3D structural vibration spectra, offering a low-power, cost-effective and scalable solution. This architecture eliminates the need for dense sensor arrays or extensive data acquisition; instead, it uses a spatially-optimized passive diffractive layer that encodes 3D structural displacements into modulated light, captured by a minimal number of detectors and decoded in real-time by shallow and low-power neural networks to reconstruct the 3D displacement spectra of structures. The diffractive system's efficacy was demonstrated both numerically and experimentally using millimeter-wave illumination on a laboratory-scale building model with a programmable shake table. Our system achieves more than an order-of-magnitude improvement in accuracy over conventional optics or separately trained modules, establishing a foundation for high-throughput 3D monitoring of structures. Beyond SHM, the 3D vibration monitoring capabilities of this cost-effective and data-efficient framework establish a new computational sensing modality with potential applications in disaster resilience, aerospace diagnostics, and autonomous navigation, where energy efficiency, low latency, and high-throughput are critical.

physics.optics↗

Optimizing Structured Surfaces for Diffractive Waveguides

Waveguide design is crucial in developing efficient light delivery systems, requiring meticulous material selection, precise manufacturing, and rigorous performance optimization, including dispersion engineering. Here, we introduce universal diffractive waveguide designs that can match the performance of any conventional dielectric waveguide and achieve various functionalities. Optimized using deep learning, our diffractive waveguide designs can be cascaded to each other to form any desired length and are comprised of transmissive diffractive surfaces that permit the propagation of desired guided modes with low loss and high mode purity. In addition to guiding the targeted modes along the propagation direction through cascaded diffractive units, we also developed various waveguide components and introduced bent diffractive waveguides, rotating the direction of mode propagation, as well as spatial and spectral mode filtering and mode splitting diffractive waveguide designs, and mode-specific polarization-maintaining diffractive waveguides, showcasing the versatility of this platform. This diffractive waveguide framework was experimentally validated in the terahertz (THz) spectrum using 3D-printed diffractive layers to selectively pass certain spatial modes while rejecting others. Diffractive waveguides can be scaled to operate at different wavelengths, including visible and infrared parts of the spectrum, without the need for material dispersion engineering, providing an alternative to traditional waveguide components. This advancement will have potential applications in telecommunications, imaging, sensing and spectroscopy, among others.

physics.optics↗