Search arXiv⌕ Search

arXiv subjects

Yuning Zhang

Publications and source records attributed to Yuning Zhang.

At least 19 recordsLinked to original sources
arXiv2026

WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models

Vision-language-action (VLA) policies generate robot controls autoregressively, making closed-loop latency dominated by repeated target-model forward passes. Speculative decoding reduces this cost by verifying blocks of draft action tokens in parallel, and recent VLA methods further relax token-level acceptance because small differences in action-token space often map to similar continuous controls. However, this relaxation remains scene-agnostic. A fixed token-distance tolerance treats the same action-token deviation as equally safe across states, although deviations that are harmless in free space can cause collisions or grasp failures near contact. We propose WA-SpecDec, a world-aware speculative decoding framework that injects world-model-derived physical scene awareness during the VLA prefill stage, producing shared world-aware prefill states for draft proposal and target verification without changing the relaxed acceptance rule. Across three state-of-the-art relaxed acceptance schemes, WA-SpecDec preserves higher task success under looser relaxation and enables longer accepted prefixes. At comparable-success operating points, WA-SpecDec achieves a 1.5x matched-success speedup over VLA speculative decoding alone and reduces near-contact failure (NCF) by 18.6% on average relative to the corresponding speculative baselines.

cs.RO↗
arXiv2026

HorizonServe: Coordinating Request Scheduling with GPU Sharing for Omni-Model Serving

Omni models unify text, speech, image, and multimodal reasoning in a single serving backend, but this unified deployment exposes a new scheduling problem. Requests with different output modalities may share an initial multimodal backbone and then diverge into downstream generation stages, creating heterogeneous first-response metrics and service-level objective (SLO) targets on the same GPU. Existing large language model (LLM) and multimodal serving systems mainly optimize token progress or input-side processing, and they do not jointly control temporal sharing in the shared stage and spatial sharing among co-running stages. This paper presents HorizonServe, a single-GPU omni-model serving system that coordinates request admission and GPU allocation under heterogeneous SLOs. HorizonServe profiles per-class first-response latency, protects requests with limited slack, rotates shared-stage opportunities across execution paths, and throttles the shared-stage streaming multiprocessor (SM) allocation when downstream stages are active. Across three omni-model workloads and two GPU platforms, HorizonServe improves SLO attainment by up to 4.9$\times$ in arrival-rate sweeps and 7.0$\times$ under downstream-heavy traffic, and reduces per-class first-response latency by 38.4--63.7\%.

cs.DC↗
arXiv2026

TacGen: Touch Is a Necessary Dimension of Physical-World Representation -- Addressing Tactile Data Scarcity with Scalable Vision-to-Touch Alignment and Generation

Touch resolves the physical-property ambiguity left by vision: exploratory contact recovers shape, texture, compliance, and material, and visuo-haptic object representations converge in ventral visual cortex. We ask whether representation learning can reproduce this grounding. TacGen mitigates the tactile-data scarcity bottleneck by combining pre-specified V+T contrastive alignment with a latent-space residual-MLP V->T generator that synthesizes tactile latents from RGB for tactile-data scaling. With matched DINOv2 backbones, splits, and probes, V+T improves matched V-only on mass (Delta R^2=+0.570), density (Delta acc=+0.067), hardness (+0.117), and uncertainty-banded force labels (Delta R^2=+0.281); all CIs exclude zero. The same representation lifts matched-capacity TACTO manipulation 0.246->0.979 while V-only capacity scaling accounts for only 4.5% of the gap, preserving 95.5%. The generator reaches cross-seed +0.589, with real tactile +0.585 inside the seed interval; the architecture comparison shows a 13pp downstream gap between reconstruction quality and representation utility. Across five-seed SSVTP/TVL reproductions, YCB-Sight transfer, three-backbone checks, permutation/random-feature controls, hash-verified manifests, and measured-force validation checks, the evidence supports the claim that touch supplies a necessary physical evidence channel for representations of contact-dependent properties.

cs.RO↗
arXiv2026

OmniLoc: A Geometry-Aware Foundation Model for Anchor-Free UE Localization Across Diverse Indoor Environments

Indoor localization from wireless measurements remains challenging in large-scale deployments due to substantial variation in building geometry, the set of detectable access points (APs), and the heterogeneity of received signals. Existing learning-based methods often perform well only in limited settings and degrade under environmental shifts, making robust anchor-free localization across diverse indoor environments notoriously difficult. In this paper, we present OmniLoc, an environment-interactive foundation model for anchor-free user equipment localization across diverse indoor environments. To the best of our knowledge, OmniLoc is the first foundation-model-based approach built directly on wireless measurements for this task. OmniLoc is built on three key designs. First, a unified input tokenization module converts heterogeneous wireless measurements into a common representation that is more amenable to learning. Second, a geometry-aware Transformer performs AP-aware feature extraction by emphasizing dominant APs while aggregating complementary evidence from supporting APs. Third, a geometry-aware location estimation module conditions regression on geometric embeddings to produce geometrically consistent location predictions. We evaluate OmniLoc on both a large-scale in-house dataset and a public benchmark dataset. Results show that OmniLoc significantly outperforms existing methods, consistently improves existing backbones when its design components are integrated, and demonstrates strong generalization in cross-environment evaluations.

cs.LG↗
arXiv2026

TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images

Recent AI-generated image (AIGI) detectors perform well on natural-image benchmarks, but their behavior on text-rich forgeries, such as fabricated screenshots, documents, and news pages prevalent in misinformation, remains untested. We introduce TextFake, a 20,000-image benchmark for text-rich AIGI detection spanning 28 languages, 4 topic categories, and 2 scene modalities. Fake images are synthesized via a four-stage pipeline that annotates real images along three controlled dimensions and generates counterparts through distribution-aligned structured prompting, ruling out covariate shortcuts. Zero-shot evaluation of 14 specialized detectors and 3 frontier VLM APIs reveals a large systematic gap: no method exceeds 80% accuracy, with some dropping over 60% from natural-image benchmarks. Diagnostic evaluations identify three failure modes: the Text Density Curse, where dense glyphs overwhelm low-level detectors; Cloaking via Rendering Fidelity, where stronger text rendering suppresses enerative artifacts; and Threshold Collapse, where routine perturbations drive detectors toward chance-level performance.

cs.CV↗
arXiv2026

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors

Model distillation is a primary driver behind the rapid progress of LLM agents, yet it often leads to behavioral homogenization. Many emerging agents share nearly identical reasoning steps and failure modes, suggesting they may be distilled echoes of a few dominant teachers. Existing metrics, however, fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model's autonomous preferences. We propose two complementary metrics to isolate non-mandatory behavioral patterns: \textbf{Response Pattern Similarity (RPS)} for verbal alignment and \textbf{Action Graph Similarity (AGS)} for tool-use habits modeled as directed graphs. Evaluating 18 models from 8 providers on $\tau$-Bench and $\tau^2$-Bench against Claude Sonnet 4.5 (thinking), we find that within-family model pairs score 5.9 pp higher in AGS than cross-family pairs, and that Kimi-K2 (thinking) reaches 82.6\% $S_{\text{node}}$ and 94.7\% $S_{\text{dep}}$, exceeding Anthropic's own Opus 4.1. A controlled distillation experiment further confirms that AGS distinguishes teacher-specific convergence from general improvement. RPS and AGS capture distinct behavioral dimensions (Pearson $r$ = 0.491), providing complementary diagnostic signals for behavioral convergence in the agent ecosystem. Our code is available at https://github.com/Syuchin/AgentEcho.

cs.CL↗
arXiv2026

High Performance 4H-SiC Optically Controlled MOS Transistor

This paper introduces an optically controlled 4H-SiC MOSFET designed to avoid the gate-oxide interface unreliability and electromagnetic interference (EMI) susceptibility inherent in conventional voltage-driven devices. By replacing the conventional gate electrode with a semi-transparent optical window, the device enables direct modulation of channel conductivity through ultraviolet illumination. Electrical and optical characterization demonstrates that under an optical power density above 0.1 W/cm^2, the device achieves an on/off current ratio exceeding 10^6 between illuminated and dark states. Notably, at an optical power density of 0.031 W/cm^2, the photogenerated current density exceeds that obtained under a gate bias of 15 V in magnitude. Energy band analysis confirms that the optical switching mechanism operates through direct photogenerated carrier generation and transport, fundamentally differing from conventional gate voltage control and thus circumventing interface-trap and EMI-related limitations. Dynamic measurements further reveal fast switching capability, with a rise time of 1.44 ns. These results validate the feasibility of optically driven switching in SiC-based devices and highlight their potential for high-speed logic applications.

physics.app-ph↗
arXiv2026

Cognibit: From Digital Exhaustion to Real-World Connection Through Gamified Territory Control and LLM-Powered Twin Networking

We present an LLM-powered social discovery platform that uses digital twins to autonomously evaluate interpersonal compatibility through behavioral simulation. The platform unifies three key pillars: (1) digital twins that engage in autonomous multi-turn conversations on behalf of users to estimate compatibility, (2) gamified territory conquest mechanics that incentivize real-world exploration and create organic settings for in-person encounters, and (3) AI companions that preserve persistent shared memory across devices. Built upon CogniPair's cognitive architecture (Ye et al., 2026), validated on the Columbia Speed Dating dataset (551 participants), our system extends prior simulation-only matching into a fully deployed social discovery environment. Through deployment, we derive empirical cost-quality baselines and identify fundamental scaling bottlenecks that remain hidden in component-level testing alone.

cs.HC↗
arXiv2026

AI assisted optimization of integrated waveguide polarizers containing 2D reduced graphene oxide

Reduced graphene oxide (rGO) exhibits strong anisotropic light absorption and high compatibility with photonic integrated chips, making it a promising material for implementing high performance onchip polarization selective devices. The performance of rGO integrated waveguide polarizers is highly dependent on the waveguide geometry, and achieving optimal performance requires exploring a large parameter space, making conventional mode simulation methods computationally demanding. Here, we propose and demonstrate a machine learning framework based on fully connected neural networks (FCNNs) to map the dependence of the polarizer figure of merit (FOM) on the waveguide geometry. Once trained by using a small dataset of low resolution mode simulation results, the FCNN framework can rapidly and accurately predict FOM values across a large structural parameter space with high resolution. Results show that this method can reduce overall computing time by more than 4 orders of magnitude as compared to the mode simulation methods, and achieve high prediction accuracy with an average deviation (AD) below 0.05. These results highlight the FCNN based machine learning framework as an efficient tool for the design and optimization of rGO integrated waveguide polarizers.

physics.optics↗
arXiv2026

AgentServe: Algorithm-System Co-Design for Efficient Agentic AI Serving on a Consumer-Grade GPU

Large language models (LLMs) are increasingly deployed as AI agents that operate in short reasoning-action loops, interleaving model computation with external calls. Unlike traditional chat applications, these agentic workloads require inference serving systems to balance low latency, stable token emission, and throughput under multiple request arrivals from different AI agents. Recent deployments highlight a shift toward running small language models (SLMs) locally on consumer-grade GPUs, driven by privacy, compliance, and cost constraints. When heterogeneous requests overlap on a single GPU, long prefills and short decodes contend for resources, creating head-of-line blocking that destabilizes interactive performance. By analyzing agent workloads, we observe that their execution naturally separates into cold prefills, which process long system prompts, resume prefills, which append tool outputs to cached contexts, and short decodes, which are latency-critical. This mix intensifies contention compared to conventional chatbot serving. We present AgentServe, a single-GPU serving system that ensures stable multi-agent execution under such conditions by isolating prefills from decodes, applying dynamic budgeting to resume prefills, and allocating GPU resources through pre-established CUDA Green Context slots with adaptive control. Evaluation results show that AgentServe significantly improves latency stability while sustaining competitive throughput, achieving up to 2.8x TTFT improvement and 2.7x TPOT improvement over state-of-the-art baselines across different settings.

cs.DC↗
arXiv2026

AI based design of 2D material integrated optical polarizers

On-chip integration of highly anisotropic two-dimensional (2D) materials offers new opportunities for realizing high performance polarization selective devices. Obtaining optimized designs for such devices requires extensively sweeping large parameter spaces, which in conventional approaches relies on massive mode simulations that demand considerable computational resources. Here, we address this limitation by developing a machine learning (ML) model based on fully connected neural networks (FCNNs). Trained by using mode simulation results for low resolution structural parameters, the FCNN model can accurately predict polarizer figures of merits (FOMs) for high resolution parameters and rapidly map the global variation trend across the entire parameter space. We test the performance of the FCNN model using two types of polarizers with 2D graphene oxide (GO) and molybdenum disulfide (MoS2). Results show that, compared to conventional mode simulation approach, our approach can not only reduce the overall computing time by about 4 orders of magnitude, but also achieve highly accurate FOM predictions with an average deviation of less than 0.04. In addition, the measured FOM values for the fabricated devices show good agreement with the predicted ones, with discrepancies remaining below 0.2. These results validate artificial intelligence (AI) as an effective approach for designing and optimizing 2D-material based optical polarizers with high efficiency.

physics.optics↗
arXiv2026

WiLoc: Massive Measured Dataset of Wi-Fi Channel State Information with Application to Machine-Learning Based Localization

Localization is a key component of the wireless ecosystem. Machine learning (ML)-based localization using channel state information (CSI) is one of the most popular methods for achieving high-accuracy localization with low cost. However, to be accurate and robust, ML-based algorithms need to be trained and tested with large amounts of data, covering not only many user equipment (UE)/target locations, but also many different access points (APs) locations to which the UEs connect, in a variety of different environment types. This paper presents a massive-sized CSI dataset, WiLoc (Wi-Fi Localization), and makes it publicly available. WiLoc is obtained by a series of precision measurement campaigns that span three months, and it is massive in all the above-mentioned three dimensions: > 12 million UE locations, > 3,000 APs, covering 16 buildings for indoor localization, and > 30 streets for outdoor use. The paper describes the dataset structure, measurement environments, measurement protocols, and the dataset validations. Comprehensive case studies validate the advantages of large datasets in ML-driven localization strategies for both "standard" and transfer learning. We envision this dataset, which is by far the largest of its kind, to become a standard resource for researchers in the field of ML-based localization.

eess.SP↗
arXiv2026

Enhanced selfphase modulation in silicon nitride waveguides with integrated 2D MoS2 films

On-chip integration of 2D materials provides a promising route towards next-generation integrated optical devices with performance beyond existing limits. Here, significantly enhanced spectral broadening induced by self-phase modulation (SPM) is experimentally demonstrated in silicon nitride (Si3N4) waveguides integrated with 2D monolayer molybdenum disulfide (MoS2) films. Monolayer MoS2 films with ultrahigh optical nonlinearity are synthesized via low-pressure chemical vapor deposition (LPCVD) and subsequently transferred onto Si3N4 waveguides, with precise control of the film coating length and placement achieved by selectively opening windows on the chip silica upper cladding. Detailed SPM measurements at telecom wavelengths are performed using fabricated waveguides with various MoS2 film coating lengths. Compared to devices without MoS2, increased spectral broadening of sub-picosecond optical pulses is observed for the hybrid devices, achieving a broadening factor of up to ~ 2.4 for a device with a 1.4-mm-long MoS2 film. Theoretical fitting of the experimental results further reveals an increase of up to ~27 fold in the nonlinear parameter ({\gamma}) for the hybrid MoS2 / Si3N4 waveguides and an equivalent Kerr coefficient (n2) of MoS2 nearly 5 orders of magnitude higher than Si3N4. These results confirm the effectiveness of on-chip integration of 2D MoS2 films to enhance the nonlinear optical performance of integrated photonic devices.

physics.optics↗
arXiv2025

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fragmented, heavy, or constrained by legacy pipelines, resulting in high deployment friction and limited support for dynamic content and generative models. In this work, we present Visionary, an open, web-native platform for real-time various Gaussian Splatting and meshes rendering. Built on an efficient WebGPU renderer with per-frame ONNX inference, Visionary enables dynamic neural processing while maintaining a lightweight, "click-to-run" browser experience. It introduces a standardized Gaussian Generator contract, which not only supports standard 3DGS rendering but also allows plug-and-play algorithms to generate or update Gaussians each frame. Such inference also enables us to apply feedforward generative post-processing. The platform further offers a plug in three.js library with a concise TypeScript API for seamless integration into existing web applications. Experiments show that, under identical 3DGS assets, Visionary achieves superior rendering efficiency compared to current Web viewers due to GPU-based primitive sorting. It already supports multiple variants, including MLP-based 3DGS, 4DGS, neural avatars, and style transformation or enhancement networks. By unifying inference and rendering directly in the browser, Visionary significantly lowers the barrier to reproduction, comparison, and deployment of 3DGS-family methods, serving as a unified World Model Carrier for both reconstructive and generative paradigms.

cs.CV↗
arXiv2025

CUNEC: A Path Loss Model for Urban Cell-Free Massive MIMO Networks

Accurate path loss (PL) modeling is essential for evaluating and optimizing cell-free massive MIMO systems, especially in dense urban environments where traditional models fail to capture the complexity of real-world propagation. This paper introduces CUNEC (Cell-free massive MIMO for Urban Non-stationary Environments with Correlations, a novel PL model that accounts for spatial non-stationarity, inter-access point (AP)/user equipment (UE) correlations, and urban-specific propagation phenomena such as corner diffraction and street canyon waveguiding.bCUNEC segments AP-UE paths by street order, models PL as a stochastic function of urban geometry, and integrates spatially correlated shadowing. The parameters are derived from large-scale ray tracing and validated against both additional ray tracing in New York, NY and real-world channel measurements in Los Angeles, CA. Compared to the conventional alpha-beta model, CUNEC significantly improves accuracy in the considered urban propagation scenarios. An open-source dataset comprising over 30,000 AP locations and 128 UE positions is also released to support reproducible research and future system development.

eess.SP↗
arXiv2025

In-memory phononic learning toward cognitive mechanical intelligence

Modern autonomous systems are driving the critical need for next-generation adaptive materials and structures with embodied intelligence, i.e., the embodiment of memory, perception, learning, and decision-making within the mechanical domain. A fundamental challenge is the seamless and efficient integration of memory with information processing in a physically interpretable way that enables cognitive learning and decision-making under uncertainty. Prevailing paradigms, from intricate logic cascades to black-box morphological computing or physical neural networks, are seriously limited by trade-offs among efficiency, scalability, interpretability, transparency, and reliance on additional electronics. Here, we introduce in-memory phononic learning, a paradigm-shifting framework that unifies nonvolatile mechanical memory with wave-based perception within a phononic metastructure. Our system encodes spatial information into stable structural states as mechanical memory that directly programs its elastic wave-propagation landscape. This memory/wave-dynamics coupling enables effective sensory perception, decomposing complex patterns into informative geometric features through frequency-selective wave localization. Learning is created by optimizing input waveforms to selectively probe these features for memory-pattern classification, with decisions inferred directly from the output wave energy, thereby completing the entire information loop mechanically through an efficient and physically transparent mechanism without hidden architectures or electronics. This work transcends the paradigm of 'materials that compute' to cognitive matter capable of interpreting dynamic environments, paving the way for future intelligent structural-material systems with low power consumption, more direct interaction with surroundings, and enhanced cybersecurity and resilience in harsh conditions.

physics.app-ph↗
arXiv2025

GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks

Federated learning (FL) enables privacy-preserving collaborative model training but remains vulnerable to adversarial behaviors that compromise model utility or fairness across sensitive groups. While extensive studies have examined attacks targeting either objective, strategies that simultaneously degrade both utility and fairness remain largely unexplored. To bridge this gap, we introduce the Dual-Facet Attack (DFA), a novel threat model that concurrently undermines predictive accuracy and group fairness. Two variants, Synchronous DFA (S-DFA) and Split DFA (Sp-DFA), are further proposed to capture distinct real-world collusion scenarios. Experimental results show that existing robust FL defenses, including hybrid aggregation schemes, fail to resist DFAs effectively. To counter these threats, we propose GuardFed, a self-adaptive defense framework that maintains a fairness-aware reference model using a small amount of clean server data augmented with synthetic samples. In each training round, GuardFed computes a dual-perspective trust score for every client by jointly evaluating its utility deviation and fairness degradation, thereby enabling selective aggregation of trustworthy updates. Extensive experiments on real-world datasets demonstrate that GuardFed consistently preserves both accuracy and fairness under diverse non-IID and adversarial conditions, achieving state-of-the-art performance compared with existing robust FL methods.

cs.LG↗
arXiv2025

Dynamical control of quantum photon-photon interaction with phase change material

Quantum interference can produce a pivotal effective photon-photon interaction, enabling the exploration of various quantum information technologies that beyond the possibilities of classical physics. While such an effective interaction is fundamentally limited to the bosonic nature of photons and the restricted phase responses from commonly used unitary optical elements, loss-induced nonunitary operation provides an alternative degree of freedom to control the quantum interference. Here, we propose and experimentally demonstrate a concise yet powerful tool to unravel fundamental features of quantum interference based on the phase change material vanadium dioxide. Since the insulator-metal transition in an elaborate vanadium dioxide thin film can create any desired particle exchange phase response, we show its tunability over the effective photon-photon interaction between paired photons that are entangled in the symmetric and anti-symmetric forms, which may introduce sophisticated nonunitary operations and functionalities into programmable optical platforms. These results provide an alternative approach to investigate the quantum light-matter interaction, and facilitate the use of quantum interference for various quantum information processing tasks such as quantum simulation and quantum computation.

quant-ph↗