arXiv subjects

Qijie Wang

Publications and source records attributed to Qijie Wang.

17 recordsLinked to original sources

arXiv2026

SIRA: Reasoning-Aware Surgical Instrument Segmentation via Query-Anchored Alignment

Surgical instrument segmentation (SIS) plays a critical role in robotic assistance and surgical workflow analysis. However, most existing SIS methods formulate segmentation as a category-driven localization problem, limiting their ability to capture procedural context and task-dependent semantics in surgical workflows. We introduce Reasoning-Aware Surgical Instrument Segmentation (RA-SIS), a task formulation that frames segmentation as query-conditioned inference under surgical context. To benchmark this setting, we construct SurgRS, a surgical reasoning segmentation dataset consisting of 41,000 image-text pairs, which aligns instance-level masks with structured query-answer supervision to enable semantic grounding at the pixel level. Based on SurgRS, we propose Surgical Instrument Reasoning and Segmentation Assistant (SIRA), a multimodal framework that disentangles target-level and query-level semantics and integrates them with visual features through query-anchored dual alignment. By aligning query semantics with spatial features and segmentation prompts, SIRA enhances semantic-visual consistency in mask prediction. Extensive experiments on SurgRS demonstrate improvements over existing reasoning-aware baselines. Code is available at https://github.com/linxir226/SIRA.

cs.CV↗

arXiv2026

Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation

RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, generating high-quality RGBA animations for games remains challenging for two reasons. First, most existing RGBA video datasets are dominated by photorealistic content, with limited coverage of game assets. Second, the traditional generate-then-matte pipelines estimate alpha only after RGB synthesis, so semi-transparent regions are often blurred by background, resulting in unstable matting outputs. More recently, many methods have begun to model RGB and alpha jointly, but existing approaches are mostly text-conditioned, and still have unresolved issues in efficiency and quality. To address these challenges, we introduce GameAlpha-2.4K, a 2.4K-clip game-style RGBA video dataset built with matte-friendly synthesis, multi-hypothesis alpha recovery, and compositing-based quality gates. Using this dataset, we train a reference-conditioned RGBA video generator that jointly produces RGB frames and alpha mattes in a single pass. To improve efficiency, we propose a visibility router that identifies transparent tokens in an early stage and bypasses their later DiT updates, while x_0-lock guides them along the original flow-matching schedule toward self-predicted endpoints. Our model obtains lower FVD than traditional two-stage pipelines, and the visibility router skips 35% of token evaluations in the final two DiT denoising steps, providing a 1.2x backbone speedup with negligible quality degradation compared to dense inference.

cs.CV↗

arXiv2026

Resolution and Robustness Bounds for Reconstructive Spectrometers

Reconstructive spectrometers are a promising emerging class of devices that combine complex light scattering with inference to enable compact, high-resolution spectrometry. Thus far, the physical determinants of these devices' performance remain under-explored. We show that under a broad range of conditions, the noise-induced error for spectral reconstruction is governed by the Fisher information. We then use random matrix theory to derive a closed-form relation linking the variance bound to a set of key physical parameters: the spectral correlation length, the mean transmittance, and the number of frequency and measurement channels. The analysis reveals certain fundamental trade-offs between these physical parameters, and establishes the conditions for a spectrometer to achieve ``super-resolution'' below the limit set by the spectral correlation length. Our theory is confirmed using numerical validations with a random matrix model as well as full-wave simulations. These results establish a physically-grounded framework for designing and analyzing performant and noise-robust reconstructive spectrometers.

physics.optics↗

arXiv2026

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.

cs.CV↗

arXiv2026

Segment-chirped periodically poled lithium niobate waveguides for broadband supercontinuum generation

Supercontinuum generation is a key technology in nonlinear optics, supporting a wide range of applications in frequency metrology and spectroscopy. Integrated photonics offers a promising route toward compact and efficient supercontinuum sources, yet extending the bandwidth while maintaining high spectral flatness remains a central challenge. Here we demonstrate an integrated broadband supercontinuum source based on segment-chirped periodically poled lithium niobate (SC-PPLN) nanophotonic waveguides. By discretizing the chirped poling profile into independently optimized segments, this approach enables high-fidelity ferroelectric domain inversion with near-ideal duty cycles and establishes broadband quasi-phase matching, overcoming the domain inhomogeneity and efficiency limitations commonly encountered in conventional chirped poling. The engineered phase-matching landscape supports efficient wavelength conversion and simultaneous activation of multiple second- and third-order nonlinear processes. Experimentally, we achieve a spectrally flat supercontinuum spanning three optical octaves, from 320 nm in the ultraviolet to 2600 nm in the mid-infrared. These results establish segment-chirped poling as a practical strategy for broadband wavelength conversion and supercontinuum generation in integrated photonics.

physics.optics↗

arXiv2026

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests whether a model can reason about how an observed world should evolve over time. We introduce WorldReasonBench, which reframes video generation evaluation as world-state prediction: given an initial state and an action, can a model generate a future video whose state evolution remains physically, socially, logically, and informationally consistent? WorldReasonBench contains 436 curated test cases with structured ground-truth QA annotations spanning four reasoning dimensions and 22 subcategories. We evaluate generated videos with a human-aligned two-part methodology: Process-aware Reasoning Verification uses structured QA and reasoning-phase diagnostics to detect temporal and causal failures, while Multi-dimensional Quality Assessment scores reasoning quality, temporal consistency, and visual aesthetics for ranking and reward modeling. We further introduce WorldRewardBench, a preference benchmark with approximately 6K expert-annotated pairs over 1.4K videos, supporting pair-wise and point-wise reward-model evaluation. Across modern video generators, our results expose a persistent gap between visual plausibility and world reasoning: videos can look convincing while failing dynamics, causality, or information preservation. We will release our benchmarks and evaluation toolkit to support community research on genuinely world-aware video generation at https://github.com/UniX-AI-Lab/WorldReasonBench/.

cs.CV↗

arXiv2026

Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored. At the same time, multi-camera setups are increasingly standard in robotic platforms, as they provide complementary perspectives to mitigate occlusion and depth ambiguity. Whether VLMs can effectively leverage such multi-view inputs for robotic reasoning therefore remains an open question. To bridge this gap, we introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation. MV-RoboBench consists of 1.7k manually curated QA items across eight subtasks, divided into two primary categories: spatial understanding and robotic execution. We evaluate a diverse set of existing VLMs, including both open-source and closed-source models, along with enhanced versions incorporating CoT-inspired techniques. The results show that state-of-the-art models remain far below human performance, underscoring the substantial challenges VLMs face in multi-view robotic perception. Additionally, our analysis uncovers two key findings: (i) spatial intelligence and robotic task execution are positively correlated in multi-view robotic scenarios; and (ii) strong performance on existing general-purpose single-view spatial understanding benchmarks does not reliably translate to success in the robotic spatial tasks assessed by our benchmark. We release MV-RoboBench as an open resource to foster progress in spatially grounded VLMs and VLAs, providing not only data but also a standardized evaluation protocol for multi-view embodied reasoning.

cs.CV↗

arXiv2026

Broadband Continuous Frequency Tuning in Non-Hermitian Laser Arrays Enabled by Mode-Switching Boundary Topology

Broadband and continuous frequency tuning is central to the versatility of semiconductor lasers, yet existing approaches typically rely on external moving components, limiting scalability and integration. Here we demonstrate broadband continuous frequency tuning in a non-Hermitian laser array achieved solely by controlling the pump currents. We show that in two coupled sub-lasers with frequency detuning ($Δω$) and relative loss ($Δα$), a mode-switching boundary emerges in the ($Δω$, $Δα$) parameter space, shaping the frequency landscape of the lower-loss supermode. The topology of this boundary comprises pseudo-symmetric (PS) and pseudo-symmetry-broken (PSB) branches connected at an exceptional point (EP). When tuning trajectories cross the PS branch, frequency tuning is discontinuous, whereas trajectories crossing the PSB branch enable continuous tuning; trajectories through the EP yield the maximum continuous tuning range. Experiments using two coupled terahertz quantum cascade lasers demonstrate continuous tuning over 10 GHz, enabled by arbitrarily many combinations of pump currents. Extending this approach to a multi-element array further expands the continuous tuning range to 163 GHz. These results establish a general route to broadband continuous tuning in moving-part-free semiconductor lasers and highlight the potential for dynamic eigenvalue engineering in non-Hermitian photonics and beyond.

physics.optics↗

arXiv2025

Friction-Aware Safety Locomotion for Wheeled-legged Robots using Vision Language Models and Reinforcement Learning

Controlling Wheeled-legged robots is challenging especially on slippery surfaces due to their dependence on continuous ground contact. Unlike quadrupeds or bipeds, which can leverage multiple fixed contact points for recovery, wheeled-legged robots are highly susceptible to slip, where even momentary loss of traction can result in irrecoverable instability. Anticipating ground physical properties such as friction before contact would allow proactive control adjustments, reducing slip risk. In this paper, we propose a friction-aware safety locomotion framework that integrates Vision-Language Models (VLMs) with a Reinforcement Learning (RL) policy. Our method employs a Retrieval-Augmented Generation (RAG) approach to estimate the Coefficient of Friction (CoF), which is then explicitly incorporated into the RL policy. This enables the robot to adapt its speed based on predicted friction conditions before contact. The framework is validated through experiments in both simulation and on a physical customized Wheeled Inverted Pendulum (WIP). Experimental results show that our approach successfully completes trajectory tracking tasks on slippery surfaces, whereas baseline methods relying solely on proprioceptive feedback fail. These findings highlight the importance and effectiveness of explicitly predicting and utilizing ground friction information for safe locomotion. They also point to a promising research direction in exploring the use of VLMs for estimating ground conditions, which remains a significant challenge for purely vision-based methods.

cs.RO↗

arXiv2025

Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling

Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs, requiring numerous iterative steps for training and inference. Existing acceleration techniques, such as distillation and solver optimization, are generally task-agnostic and do not fully leverage the specific characteristics of low-level tasks like super-resolution (SR). In this study, we analyze the frequency- and spatial-domain properties of diffusion-based SR methods, revealing key insights into the temporal and spatial dependencies of high-frequency signal recovery. Specifically, high-frequency details benefit from concentrated optimization during early and late diffusion iterations, while spatially textured regions demand adaptive denoising strategies. Building on these observations, we propose the Time-Spatial-aware Sampling strategy (TSS) for the acceleration of Diffusion SR without any extra training cost. TSS combines Time Dynamic Sampling (TDS), which allocates more iterations to refining textures, and Spatial Dynamic Sampling (SDS), which dynamically adjusts strategies based on image content. Extensive evaluations across multiple benchmarks demonstrate that TSS achieves state-of-the-art (SOTA) performance with significantly fewer iterations, improving MUSIQ scores by 0.2 - 3.0 and outperforming the current acceleration methods with only half the number of steps.

cs.CV↗

arXiv2025

Enabling Highly Efficient Infrared Silicon Photodetectors via Disordered Metasurfaces with Upconversion Nanoparticles

Silicon photodetectors are highly desirable for their CMOS compatibility, low cost, and fast response speed. However, their application the infrared (IR) is limited by silicon's intrinsic bandgap, which restricts its detection to photons with wavelengths shorter than 1100 nm. Although several methods have been developed to extend silicon photodetectors further in the IR range, these approaches often introduce additional challenges, such as increased fabrication complexity and compatibility issues with standard CMOS processes. Here, we present an approach to overcome these limitations by integrating disordered metasurfaces with upconversion nanoparticles (UCNPs), enabling IR detection by silicon photodetectors. The disordered design consists of hybrid Mie-plasmonic cavities, which can enhance both the near-field localization and wide-band light absorption from visible to IR, improving photocurrent conversion. Compared to ordered structures, the infrared absorption and near field of the highly disordered configuration are increased by 2.6-folds and 3.9-folds, respectively. UCNPs not only convert near-infrared photons into visible light but also enhance absorption in the mid-infrared range, thereby improving hot electron generation. The measured responsivity of the disordered element for 1550 nm laser is up to 0.22 A/W at room temperature, corresponding to an external quantum efficiency of 17.6%. Our design not only enhances the photocurrent performance significantly, but also extends the working wavelength of silicon photodetectors to IR wavelength, making them suitable for broad spectrum applications.

physics.optics↗

arXiv2024

CapS-Adapter: Caption-based MultiModal Adapter in Zero-Shot Classification

Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive fine-tuning process. In response, TIP-Adapter and SuS-X have introduced training-free methods aimed at bolstering the efficacy of downstream tasks. While these approaches incorporate support sets to maintain data distribution consistency between knowledge cache and test sets, they often fall short in terms of generalization on the test set, particularly when faced with test data exhibiting substantial distributional variations. In this work, we present CapS-Adapter, an innovative method that employs a caption-based support set, effectively harnessing both image and caption features to exceed existing state-of-the-art techniques in training-free scenarios. CapS-Adapter adeptly constructs support sets that closely mirror target distributions, utilizing instance-level distribution features extracted from multimodal large models. By leveraging CLIP's single and cross-modal strengths, CapS-Adapter enhances predictive accuracy through the use of multimodal support sets. Our method achieves outstanding zero-shot classification results across 19 benchmark datasets, improving accuracy by 2.19\% over the previous leading method. Our contributions are substantiated through extensive validation on multiple benchmark datasets, demonstrating superior performance and robust generalization capabilities. Our code is made publicly available at https://github.com/WLuLi/CapS-Adapter.

cs.CV↗

arXiv2021

Massively parallel ultrafast random bit generation with a chip-scale laser

Random numbers are widely used for information security, cryptography, stochastic modeling, and quantum simulations. Key technical challenges for physical random number generation are speed and scalability. We demonstrate a method for ultrafast generation of hundreds of random bit streams in parallel with a single laser diode. Spatio-temporal interference of many lasing modes in a specially designed cavity is introduced as a scheme for greatly accelerated random bit generation. Spontaneous emission, caused by quantum fluctuations, produces stochastic noise that makes the bit streams unpredictable. We achieve a total bit rate of 250 terabits per second with off-line post-processing, which is more than two orders of magnitude higher than the current post-processing record. Our approach is robust, compact, and energy efficient with potential applications in secure communication and high-performance computation.

physics.optics↗

arXiv2020

Electrically pumped semiconductor laser with low spatial coherence and directional emission

We design and fabricate an on-chip laser source that produces a directional beam with low spatial coherence. The lasing modes are based on the axial orbit in a stable cavity and have good directionality. To reduce the spatial coherence of emission, the number of transverse lasing modes is maximized by fine-tuning the cavity geometry. Decoherence is reached in a few nanoseconds. Such rapid decoherence will facilitate applications in ultrafast speckle-free full-field imaging.

physics.optics↗

arXiv2020

Strain effects on Phase-Filling Singularities in Highly Doped n-Type Ge

Recently, Chi Xu et al. predicted the phase-filling singularities (PFS) in the optical dielectric function (ODF) of the highly doped $n$-type Ge and confirmed in experiment the PFS associated $E_{1}+Δ_{1}$ transition by advanced \textit{in situ} doping technology [Phys. Rev. Lett. 118, 267402 (2017)], but the strong overlap between $E_{1}$ and $E_{1}+Δ_{1}$ optical transitions made the PFS associated $E_{1}$ transition that occurs at the high doping concentration unobservable in their measurement. In this work, we investigate the PFS of the highly doped n-type Ge in the presence of the uniaxial and biaxial tensile strain along [100], [110] and [111] crystal orientation. Compared with the relaxed bulk Ge, the tensile strain along [100] increases the energy separation between the $E_{1}$ and $E_{1}+Δ_{1}$ transition, making it possible to reveal the PFS associated $E_{1}$ transition in optical measurement. Besides, the application of tensile strain along [110] and [111] offers the possibility of lowering the required doping concentration for the PFS to be observed, resulting in new additional features associated with $E_{1}+Δ_{1}$ transition at inequivalent $L$-valleys. These theoretical predications with more distinguishable optical transition features in the presence of the uniaxial and biaxial tensile strain can be more conveniently observed in experiment, providing new insights into the excited states in heavily doped semiconductors.

cond-mat.mtrl-sci↗

arXiv2019

Band structure of Ge$_{1-x}$Sn$_{x}$alloy: a full-zone 30-band $k$$\cdot$$p$ model

A full-zone 30-band $k$$\cdot$$p$ model is developed as an efficient and reliable tool to compute electronic band structure in Ge$_{1-x}$Sn$_{x}$ alloy. The model was first used to reproduce the electronic band structures in Ge and $α$-Sn obtained with empirical tight binding and \textit{ab initio} methods. Input parameters for the 30-band $k$$\cdot$$p$ model are carefully calibrated against prior empirical predications and experimental data. Important material properties such as effective mass for electrons and holes, Luttinger parameters, and density of states are obtained for Ge$_{1-x}$Sn$_{x}$ alloy with the composition range $0<x<0.3$. The 30-band $k$$\cdot$$p$ model that requires far less computing resources is a necessary capability for optimization of sophisticated devices made from Ge$_{1-x}$Sn$_{x}$ alloy with a large parameter space to explore.

physics.app-ph↗

arXiv2018

All-dielectric active photonics driven by bound states in the continuum

Recently emerged dielectric resonators and metasurfaces offer a low-loss platform for efficient manipulation of electromagnetic waves from microwave to visible. Such flat meta-optics can focus electromagnetic waves, generate structured beams and vortices, enhance local fields for sensing as well as provide additional functionalities for advanced MRI machinery. Recent advances are associated with exotic optical modes called bound states in the continuum, which can give rise to extremely large quality factors and supercavity lasing. Here, we experimentally demonstrate subwavelength active supercavities with extremely high-Q resonances that could be reconfigured at an ultrafast time scale. We reveal that such supercavities enable all-optical switching and modulation of extremely sharp resonances, and thus could have numerous applications in lasing, mode multiplexing, and biosensing.

physics.optics↗