arXiv subjects

Rui Bao

Publications and source records attributed to Rui Bao.

At least 19 recordsLinked to original sources

arXiv2026

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

Diffusion watermarking embeds verifiable signals into the generative process and commonly verifies them by recovering trajectory-dependent evidence, making the marks robust to conventional pixel-space distortions. Existing removal attacks either regenerate along deterministic trajectories, which often preserve the watermark-bearing latent structure, or optimize every image separately. We identify the reliance on a recoverable generative trajectory as a common attack surface among the schemes we study. Based on this observation, we propose DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling. Forward re-noising limits source information available to a fixed-depth recovery pipeline, while stochastic reversal supplies alternative noise-driven paths whose removal benefit we isolate through matched sampler comparisons. Adaptive DRIFT searches a selected ladder for each image's first verifier-rejected rung and refines fidelity while retaining only updates rejected by the same verifier. At fixed depth, we derive information-theoretic and Wasserstein source-dependence bounds; under realized-ladder monotonicity, the first rejected rung is least distorted among rejected rungs on that ladder, and verifier-gated refinement preserves rejection. Across nine watermarks spanning three paradigms, DRIFT achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.

cs.CR↗

arXiv2026

IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the generator did not produce, resulting in forgery. Binding the mark to visual semantics prevents such transplantation, yet existing bindings anchor to a proxy image rather than the image they mark. Realizing visual-semantic binding inside generation faces two challenges. The mark derives from the image itself yet enters the sampling trajectory before that image exists, and may itself shift the semantics it binds. The binding also meets opposite sensitivity demands, breaking under semantic change while holding through common processing. We present IRIS, a training-free watermarking scheme that embeds an Intrinsic Ring Identifier from Semantics. IRIS reads a content code from the non-watermarked generated image, derives a one-time ring from the code and a secret key, returns to the final low-noise steps of the same trajectory and blends the ring in, after the semantics it binds are settled. To meet the opposite sensitivity demands, the code is read through a canonicalization shared between embedding and detection, holding through common distortions and mild regeneration while flipping under semantic change. Detection recomputes the ring from the query image and the key alone, and the mark therefore fails on a foreign or spliced image, with acceptance tracking semantic displacement. On three prompt datasets IRIS detects reliably and stays close to its same-seed non-watermarked counterpart, a fidelity prior in-generation marks do not reach. While forgeries transfer fixed-pattern marks and regeneration strips post-hoc marks, IRIS alone among the compared marks withstands both.

cs.CV↗

arXiv2026

$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference

Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time, and it is non-stationary due to user-driven semantic events, background load, and device churn. Consequently, a resource manager that is tuned offline under a fixed regime can become brittle and expensive to maintain. This paper presents $E^3$-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. $E^3$-Agent separates a fast-path router that makes millisecond-level dispatch decisions from a slow-path, event-driven large language model (LLM) meta-controller that mitigates regime shifts through a small, explicit control surface exposed via a tool interface, including risk gating, router configuration, and rapid performance calibration. The agent learns online from execution feedback and continuously adapts to unknown and time-varying service-time mappings. We evaluate $E^3$-Agent in a discrete-event simulator driven by MLPerf-derived device-model measurement priors, covering cold-start warmup and three dynamic regimes: semantic dynamics, device churn, and hidden drift. Across the dynamic scenarios, $E^3$-Agent reduces average latency by 65%-73% compared to the best static baseline, stays within 7%-10% of an online full-information Oracle used for evaluation, and effectively suppresses stutter rate under semantic degradation.

cs.LG↗

arXiv2026

SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumption: verification can succeed only if the diffusion trajectory can be faithfully reconstructed. This reliance on trajectory recovery constitutes a fundamental and exploitable vulnerability. We propose $\underline{\mathbf{S}}$tochastic $\underline{\mathbf{Hi}}$dden-Trajectory De$\underline{\mathbf{f}}$lec$\underline{\mathbf{t}}$ion ($\mathbf{SHIFT}$), a training-free attack that exploits this common weakness across diverse watermarking paradigms. SHIFT leverages stochastic diffusion resampling to deflect the generative trajectory in latent space, making the reconstructed image statistically decoupled from the original watermark-embedded trajectory while preserving strong visual quality and semantic consistency. Extensive experiments on nine representative watermarking methods spanning noise-space, frequency-domain, and optimization-based paradigms show that SHIFT achieves 95%--100% attack success rates with nearly no loss in semantic quality, without requiring any watermark-specific knowledge or model retraining.

cs.CV↗

arXiv2025

A Time-Series Foundation Model by Universal Delay Embedding

This study introduces Universal Delay Embedding (UDE), a pretrained foundation model designed to revolutionize time-series forecasting through principled integration of delay embedding representation and Koopman operator prediction. Leveraging Takens' embedding theorem, UDE as a dynamical representation of observed data constructs two-dimensional subspace patches from Hankel matrices, theoretically preserving dynamical and topological properties of underlying dynamical systems. Such patches are viewed as images, which can be efficiently processed by exploiting advanced deep learning technologies. Computationally, these patches further serve as tokens for learning a self-attention encoder, thus enabling accurate prediction of nonlinear time-series by a finite-dimensional Koopman operator in a linear manner in a latent space. Extensive evaluations across various benchmarks and real-world climate datasets demonstrate over 20% average reduction in mean squared error versus state-of-the-art foundation models, alongside superior generalization in fine-tuning scenarios. In particular, the learned dynamical representations and Koopman operator prediction forms from the patches exhibit exceptional interpretability, with consistent identification of topologically informative subspaces and robust encoding of domain-invariant dynamics, establishing UDE as a scalable, interpretable framework for universal time-series modeling and forecasting with broad scientific and industrial applicability.

cs.LG↗

arXiv2025

CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems

While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches often ignore the cold-start latency caused by on-demand model loading. In this paper, we propose a latency-aware scheduling framework that overlaps model loading with computation and communication to minimize total inference latency. Based on device and model parameters, the framework dynamically adjusts layer partitioning and allocation to effectively hide loading time, thereby eliminating as many idle periods as possible. We formulate the problem as a Mixed-Integer Non-Linear Program and design an efficient dynamic programming algorithm to optimize model partitioning and device assignment. Experimental results show that the proposed method significantly reduces cold-start latency compared to baseline strategies.

cs.IT↗

arXiv2025

Dynamic Quality-Latency Aware Routing for LLM Inference in Wireless Edge-Device Networks

The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between inference quality and end-to-end latency. A fundamental mismatch exists between task complexity and resource allocation: offloading simple queries invites prohibitive latency, while on-device models lack the capacity for demanding computations. To address this challenge, we propose a dynamic, quality-latency aware routing framework that orchestrates inference between a lightweight model on the mobile device and a powerful model on the edge server. Our framework employs two distinct cost models: for single-turn queries, it fuses a BERT-predicted semantic score with communication and computation overheads; for multi-turn dialogues, it further quantifies context-aware costs arising from model switching and KV-cache management. While maintaining full inference quality, extensive experiments demonstrate that our framework cuts average response latency by 5-15% and reduces large model invocations by 10-20% against competitive baselines on MMLU, GSM8K, and MT-Bench-101 benchmarks.

cs.IT↗

arXiv2025

When Pipelined In-Memory Accelerators Meet Spiking Direct Feedback Alignment: A Co-Design for Neuromorphic Edge Computing

Spiking Neural Networks (SNNs) are increasingly favored for deployment on resource-constrained edge devices due to their energy-efficient and event-driven processing capabilities. However, training SNNs remains challenging because of the computational intensity of traditional backpropagation algorithms adapted for spike-based systems. In this paper, we propose a novel software-hardware co-design that introduces a hardware-friendly training algorithm, Spiking Direct Feedback Alignment (SDFA) and implement it on a Resistive Random Access Memory (RRAM)-based In-Memory Computing (IMC) architecture, referred to as PipeSDFA, to accelerate SNN training. Software-wise, the computational complexity of SNN training is reduced by the SDFA through the elimination of sequential error propagation. Hardware-wise, a three-level pipelined dataflow is designed based on IMC architecture to parallelize the training process. Experimental results demonstrate that the PipeSDFA training accelerator incurs less than 2% accuracy loss on five datasets compared to baselines, while achieving 1.1X~10.5X and 1.37X~2.1X reductions in training time and energy consumption, respectively compared to PipeLayer.

cs.AR↗

arXiv2024

What can LLM tell us about cities?

This study explores the capabilities of large language models (LLMs) in providing knowledge about cities and regions on a global scale. We employ two methods: directly querying the LLM for target variable values and extracting explicit and implicit features from the LLM correlated with the target variable. Our experiments reveal that LLMs embed a broad but varying degree of knowledge across global cities, with ML models trained on LLM-derived features consistently leading to improved predictive accuracy. Additionally, we observe that LLMs demonstrate a certain level of knowledge across global cities on all continents, but it is evident when they lack knowledge, as they tend to generate generic or random outputs for unfamiliar tasks. These findings suggest that LLMs can offer new opportunities for data-driven decision-making in the study of cities.

cs.CL↗

arXiv2024

Deciphering interventional dynamical causality from non-intervention complex systems

Detecting and quantifying causality is a focal topic in the fields of science, engineering, and interdisciplinary studies. However, causal studies on non-intervention systems attract much attention but remain extremely challenging. Delay-embedding technique provides a promising approach. In this study, we propose a framework named Interventional Dynamical Causality (IntDC) in contrast to the traditional Constructive Dynamical Causality (ConDC). ConDC, including Granger causality, transfer entropy and convergence of cross-mapping, measures the causality by constructing a dynamical model without considering interventions. A computational criterion, Interventional Embedding Entropy (IEE), is proposed to measure causal strengths in an interventional manner. IEE is an intervened causal information flow but in the delay-embedding space. Further, the IEE theoretically and numerically enables the deciphering of IntDC solely from observational (non-interventional) time-series data, without requiring any knowledge of dynamical models or real interventions in the considered system. In particular, IEE can be applied to rank causal effects according to their importance and construct causal networks from data. We conducted numerical experiments to demonstrate that IEE can find causal edges accurately, eliminate effects of confounding, and quantify causal strength robustly over traditional indices. We also applied IEE to real-world tasks. IEE performed as an accurate and robust tool for causal analyses solely from the observational data. The IntDC framework and IEE algorithm provide an efficient approach to the study of causality from time series in diverse non-intervention complex systems.

cs.LG↗

arXiv2024

An erbium-doped waveguide amplifier on thin film lithium niobate with an output power exceeding 100 mW

We demonstrate high-power thin film lithium niobate (TFLN) erbium-doped waveguide amplifier (EDWA) with a maximum on-chip output power of 113 mW and a gain of 16 dB. The on-chip integrated EDWA is composed of large mode area (LMA) waveguide structures with a total length of 7 cm and a footprint of 1x1 cm2. Particularly, we connect segmented LMA waveguides with waveguide tapers to achieve on-chip mode conversion which maintains single-mode propagation all over the EDWA even at the waveguide bends. The design leads to significant increase of the amplified signal power by orders of magnitude and will open an avenue for applications such as on-chip high-power lasers and amplifiers system.

physics.optics↗

arXiv2024

Photonic Neural Network Fabricated on Thin Film Lithium Niobate for High-Fidelity and Power-Efficient Matrix Computation

Photonic neural networks (PNNs) have emerged as a promising platform to address the energy consumption issue that comes with the advancement of artificial intelligence technology, and thin film lithium niobate (TFLN) offers an attractive solution as a material platform mainly for its combined characteristics of low optical loss and large electro-optic (EO) coefficients. Here, we present the first implementation of an EO tunable PNN based on the TFLN platform. Our device features ultra-high fidelity, high computation speed, and exceptional power efficiency. We benchmark the performance of our device with several deep learning missions including in-situ training of Circle and Moons nonlinear datasets classification, Iris flower species recognition, and handwriting digits recognition. Our work paves the way for sustainable up-scaling of high-speed, energy-efficient PNNs.

physics.optics↗

arXiv2024

On-chip wavelength division multiplexing by angled multimode interferometer fabricated on erbium-doped thin film lithium niobate on insulator

Photonic integrated circuits based on erbium doped thin film lithium niobate on insulator has attracted broad interests with insofar various waveguide amplifiers and microlasers demonstrated. Wideband operation facilitated by the broadband absorption and emission of erbium ions necessitates the functional integration of wavelength filter and multiplexer on the same chip. Here a low-loss wavelength division multiplexer at the resonant pumping and emission wavelengths (~1480 nm and 1530~1560 nm) of erbium ions based on angled multimode interferometer, is realized in the erbium doped thin film lithium niobate on insulator fabricated by the photolithography assisted chemomechanical etching technique. The minimum on-chip insertion losses of the fabricated device are <0.7 dB for both wavelength ranges, and a 3-dB bandwidth of >20 nm is measured at the telecom C-band. Besides, direct visualization of the multimode interference pattern by the visible upconversion fluorescence of erbium ions compares well with the simulated light propagation in the multimode interferometer. Spectral tuning of the wavelength division multiplexer by structural design is also demonstrated and discussed.

physics.optics↗

arXiv2023

Enhancing the machine vision performance with multi-spectral light sources

This study mainly focuses on the performance of different multi-spectral light sources on different object colors in machine vision and tries to enhance machine vision with multi-spectral light sources. Using different color pencils as samples, by recognizing the collected images with two classical neural networks, AlexNet and VGG19, the performance was investigated under 35 different multi-spectral light sources. The results show that for both models there are always some non-pure white light sources, whose accuracy is better than pure white light, which suggests the potential of multi-spectral light sources to further enhance the effectiveness of machine vision. The comparison of both models is also performed, and surprised to find that the overall performance of VGG19 is lower than that of AlexNet, which shows that the importance of the choice of multi-spectral light sources and models.

eess.IV↗

arXiv2023

On-chip coherent beam combination of waveguide amplifiers on Er$^{3+}$-doped thin film lithium niobate

We demonstrate on-chip coherent beam combination of two waveguide amplifiers on Er$^{3+}$-doped thin film lithium niobate (Er: TFLN) platform. Our device is built based on an electro-optic modulator fabricated on Er: TFLN. The output power of the coherently combined amplifiers is measured as high as 12.9 mW, surpassing that of previous single waveguide amplifiers based on Er$^{3+}$-doped thin film lithium niobate platform.

physics.optics↗

arXiv2022

On-chip integrated Yb3+-doped waveguide amplifiers on thin film lithium niobate

We report the fabrication and optical characterization of Yb3+-doped waveguide amplifiers (YDWA) on the thin film lithium niobate fabricated by photolithography assisted chemo-mechanical etching. The fabricated Yb3+-doped lithium niobate waveguides demonstrates low propagation loss of 0.13 dB/cm at 1030 nm and 0.1 dB/cm at 1060 nm. The internal net gain of 5 dB at 1030 nm and 8 dB at 1060 nm are measured on a 4.0 cm long waveguide pumped by 976nm laser diodes, indicating the gain per unit length of 1.25 dB/cm at 1030 nm and 2 dB/cm at 1060 nm, respectively. The integrated Yb3+-doped lithium niobate waveguide amplifiers will benefit the development of a powerful gain platform and are expected to contribute to the high-density integration of thin film lithium niobate based photonic chip.

physics.optics↗

arXiv2021

On-chip multi-color microdisk laser on Yb3+-doped thin-film lithium niobate

We demonstrate an on-chip Yb3+-doped lithium niobate (LN) microdisk laser. The intrinsic quality factors of the fabricated Yb3+-doped LN microdisk resonator are measured up to 3.79x10^5 at 976 nm wavelength and 1.1x10^6 at 1514 nm wavelength. The multi-mode laser emissions are obtained in a band from 1020 nm to 1070 nm pumped by 984 nm laser and with the low threshold of 103 μW, resulting in a slope efficiency of 0.53% at room temperature. Furthermore, the second-harmonic frequency of pump light and the sum-frequency of the pump light and laser emissions are both generated in the on-chip Yb3+-doped LN microdisk benefited from the strong \c{hi}(2) nonlinearity of LN. These microdisk lasers are expected to contribute to the high-density integration of LNOI-based photonic chip.

physics.optics↗

arXiv2021

An Ultrahigh-Q Microresonator on 4H-silicon-carbide-on-insulator Platform for Multiple Harmonics, Cascaded Raman Lasing and Kerr Comb Generations

The realization of ultrahigh quality (Q) resonators regardless of the underpinning material platforms has been a ceaseless pursuit, because the high Q resonators provide an extreme environment of storage of light to enable observations of many unconventional nonlinear optical phenomenon with high efficiencies. Here, we demonstrate an ultra-high Q factor (7.1*10^6) microresonator on the 4H-silicon-carbide-on-insulator (4H-SiCOI) platform in which both \c{hi}^(2) and \c{hi}^(3) nonlinear processes of high efficiencies have been generated. Broadband frequency conversions, including second-, third-, fourth-harmonic generation were observed. Cascaded Raman lasing was demonstrated in the SiC microresonator for the first time to the best of our knowledge. Broadband Kerr frequency combs covering from 1300 to 1700 nm were achieved using a dispersion-engineered SiC microresonator. Our demonstration is a significant milestone in the development of SiC photonic integrated devices.

physics.optics↗