arXiv subjects

Yutong Jiang

Publications and source records attributed to Yutong Jiang.

15 recordsLinked to original sources

arXiv2026

PolyLayout: Hierarchical VLM-Guided Layout Generation Beyond Rectangular Rooms

Generating physically plausible 3D room layouts is essential for home furnishing retail, enabling customers to visualize products in their own homes and confidently make purchasing decisions. However, a gap exists between academic research and real-world application: existing solutions primarily focus on algorithmic strategies for furniture placement, largely neglecting the non-rectangular geometries and strict door/window constraints prevalent in real homes. To bridge the gap, we introduce a hybrid, hierarchical framework tailored for retail, specifically designed to support scalable spatial planning applications. Our system decouples generation into three stages: (1) functional furniture clustering and fine-grained intra-zone placement; (2) macro-routing guided by a vision-language model (VLM) to anchor both these clustered zones and any remaining standalone furniture within diverse polygonal boundaries; and (3) rule-based optimization for collision-free micro-arrangements that respect architectural constraints. We evaluate our system on production-scale catalogs and a representative set of irregular real-world topologies. Our results show that our approach attains the highest perceptual plausibility while maintaining good geometric compliance at relatively low latency, and extends to irregular boundaries that existing methods do not natively support.

cs.CV↗

arXiv2026

Incomplete Observations Boost Evolutionary Performance in Ocean Modeling

Data-driven methods have revolutionized ocean modeling, yet current approaches rely heavily on complete reanalysis datasets, imposing computational constraints and limiting model performance to that of the training data. Here, we present a generative state-space model and an optimization framework that enable learning directly from sparse and noisy observations. The model is essentially a hidden Markov model with a continuous state space, where oceanic physical quantities are treated as hidden states and measurements as observations, enabling a unified representation of ocean fields and observational data. Both the initial-state and state-transition modules are implemented as neural networks to capture the complexity and temporal evolution of ocean states, while the emission module is formulated as a masked Gaussian distribution. To train the model from sparse observations, we derive an optimization framework based on the expectation-maximization (EM) algorithm. The framework alternately reconstructs high-fidelity ocean fields via Langevin dynamics and optimizes deep neural networks to capture temporal evolution. Theoretical analysis shows that the framework maximizes the likelihood of observations under the generative model. For efficiency, we assume that ocean-state evolution follows a stationary, ergodic, and Markovian stochastic process and adopt only length-two state sequences during optimization. Experiments on CMIP6 simulation data and FY-3D satellite data demonstrate high-fidelity reconstruction and accurate prediction, showing that sparse observations can directly improve the model's representation of ocean-state dynamics. This work offers a scalable pathway for next-generation Earth system models to learn directly from sparse, incomplete real-world observations.

cs.LG↗

arXiv2026

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots. Recent work attempts to use learned world models as simulators for policy optimization, yet closed-loop imagined rollouts inevitably suffer from hallucination and long-horizon error accumulation. Such errors not only degrade visual fidelity, but also mislead policy optimization by providing unreliable learning signals. We propose WoVR, a reliable world-model-based RL framework for post-training VLA policies. Instead of assuming a faithful world model, WoVR explicitly regulates how RL interacts with imperfect imagined dynamics. It improves rollout stability through a controllable action-conditioned video world model, reshapes imagined interaction to reduce effective error depth via Keyframe-Initialized Rollouts, and maintains policy--simulator alignment through World Model-Policy co-evolution. Extensive experiments demonstrate that WoVR enables stable long-horizon imagined rollouts and effective policy optimization, achieving superior LIBERO performance and consistent real-world gains across multiple robotic platforms. These results show that world models can serve as practical simulators for RL when hallucination is explicitly controlled. Additional visualization results are available at https://wovr-corl.github.io.

cs.RO↗

arXiv2026

Focused on the User, Overlooking the Risks: Security and Privacy Understandings, Practices and Challenges of Independent Chinese AI Agent Developers

The proliferation of AI agents empowers independent developers, defined as individual or small groups who self-initiate projects rather than fulfill client-based contracts, to create sophisticated autonomous systems, but also introduces novel security and privacy (S&P) challenges beyond traditional corporate structures. We conducted an interview study (N=28) with Chinese developers, whose extensive use of global LLM services offer valuable insights into this population. We investigate their understandings, practices and challenges of S&P challenges in their developed AI agent products. We revealed that independent developers frequently think and act from their users' perspective. They focused on user-facing safety risks such as harmful content while exhibiting low awareness of security vulnerabilities. Consequently, developers rely almost exclusively on ad-hoc, manually crafted safeguards and informal communication, with an absence of formal tools or processes for S&P practices. We found these actions are driven by various inhibitors, primarily a lack of formal training on S&P related skills, accessible security tools and actionable guidance from platforms. Our work contributed the first exploration of independent AI agent developers' S&P understanding, outlining opportunities for tailored security tooling.

cs.HC↗

arXiv2026

UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios

Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing. However, current methods have fundamental drawbacks: mask-based approaches suffer from local color discrepancies, while mask-free methods struggle with global background texture misalignment. Furthermore, most methods struggle with diverse real-world scenarios such as stylized avatars, face occlusion, and extreme lighting conditions. In this paper, we propose UniSync, a unified framework designed for achieving high-fidelity lip synchronization in diverse scenarios. Specifically, UniSync uses a mask-free pose-anchored training strategy to keep head motion and eliminate synthesis color artifacts, while employing mask-based blending consistent inference to ensure structural precision and smooth blending. Notably, fine-tuning on compact but diverse videos empowers our model with exceptional domain adaptability, handling complex corner cases effectively. We also introduce the RealWorld-LipSync benchmark to evaluate models under real-world demands, which covers diverse application scenarios including both human faces and stylized avatars. Extensive experiments demonstrate that UniSync significantly outperforms state-of-the-art methods, advancing the field towards truly generalizable and production-ready lip synchronization.

cs.CV↗

arXiv2025

PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents

While web agents gained popularity by automating web interactions, their requirement for interface access introduces significant privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we found users frequently misunderstand agents' data practices, and desired unobtrusive, transparent data management. To achieve this, we designed and implemented PrivWeb, a trusted add-on on web agents that utilizes a localized LLM to anonymize private information on interfaces according to user preferences. It features privacy categorization schema and adaptive notifications that selectively pauses tasks for user control over information collection for highly sensitive information, while offering non-disruptive options for less sensitive information, minimizing human oversight. The user study (N=14) across travel, information retrieval, shopping, and entertainment tasks compared PrivWeb with baselines without notification and without control for private information access, where PrivWeb reduced perceived privacy risks with no associated increase in cognitive effort, and resulted in higher overall satisfaction.

cs.HC↗

arXiv2025

Quantum-inspired Beamforming Optimization for Quantized Phase-only Massive MIMO Arrays

This paper introduces an innovative quantum-inspired method for beamforming (BF) optimization in multiple-input multiple-output (MIMO) arrays. The method leverages the simulated bifurcation (SB) algorithm to address the complex combinatorial optimization problem due to the quantized phase configuration. We propose novel encoding techniques for high-bit phase quantization, which are then mapped into Ising spins. This enables efficient construction of the Hamiltonians and subsequent optimization of BF patterns. The results clearly demonstrate that the SB optimizer surpasses traditional schemes such as digital BF, holographic algorithms and genetic algorithms, offering faster convergence and higher solution quality. The impressive capability of the SB optimizer to handle complex BF scenarios, including sidelobe suppression and multiple beams with nulls, is undoubtedly demonstrated through several application cases. These findings strongly suggest that quantum-inspired methods have great potential to advance MIMO techniques in next-generation wireless communication.

physics.app-ph↗

arXiv2025

$γ$-FedHT: Stepsize-Aware Hard-Threshold Gradient Compression in Federated Learning

Gradient compression can effectively alleviate communication bottlenecks in Federated Learning (FL). Contemporary state-of-the-art sparse compressors, such as Top-$k$, exhibit high computational complexity, up to $\mathcal{O}(d\log_2{k})$, where $d$ is the number of model parameters. The hard-threshold compressor, which simply transmits elements with absolute values higher than a fixed threshold, is thus proposed to reduce the complexity to $\mathcal{O}(d)$. However, the hard-threshold compression causes accuracy degradation in FL, where the datasets are non-IID and the stepsize $γ$ is decreasing for model convergence. The decaying stepsize reduces the updates and causes the compression ratio of the hard-threshold compression to drop rapidly to an aggressive ratio. At or below this ratio, the model accuracy has been observed to degrade severely. To address this, we propose $γ$-FedHT, a stepsize-aware low-cost compressor with Error-Feedback to guarantee convergence. Given that the traditional theoretical framework of FL does not consider Error-Feedback, we introduce the fundamental conversation of Error-Feedback. We prove that $γ$-FedHT has the convergence rate of $\mathcal{O}(\frac{1}{T})$ ($T$ representing total training iterations) under $μ$-strongly convex cases and $\mathcal{O}(\frac{1}{\sqrt{T}})$ under non-convex cases, \textit{same as FedAVG}. Extensive experiments demonstrate that $γ$-FedHT improves accuracy by up to $7.42\%$ over Top-$k$ under equal communication traffic on various non-IID image datasets.

cs.LG↗

arXiv2024

Data-Aware Gradient Compression for FL in Communication-Constrained Mobile Computing

Federated Learning (FL) in mobile environments faces significant communication bottlenecks. Gradient compression has proven as an effective solution to this issue, offering substantial benefits in environments with limited bandwidth and metered data. Yet, it encounters severe performance drops in non-IID environments due to a one-size-fits-all compression approach, which does not account for the varying data volumes across workers. Assigning varying compression ratios to workers with distinct data distributions and volumes is therefore a promising solution. This work derives the convergence rate of distributed SGD with non-uniform compression, which reveals the intricate relationship between model convergence and the compression ratios applied to individual workers. Accordingly, we frame the relative compression ratio assignment as an $n$-variable chi-squared nonlinear optimization problem, constrained by a limited communication budget. We propose DAGC-R, which assigns conservative compression to workers handling larger data volumes. Recognizing the computational limitations of mobile devices, we propose the DAGC-A, which is computationally less demanding and enhances the robustness of compression in non-IID scenarios. Our experiments confirm that the DAGC-R and DAGC-A can speed up the training speed by up to $25.43\%$ and $16.65\%$ compared to the uniform compression respectively, when dealing with highly imbalanced data volume distribution and restricted communication.

cs.LG↗

arXiv2024

Learn by Selling: Equipping Large Language Models with Product Knowledge for Context-Driven Recommendations

The rapid evolution of large language models (LLMs) has opened up new possibilities for applications such as context-driven product recommendations. However, the effectiveness of these models in this context is heavily reliant on their comprehensive understanding of the product inventory. This paper presents a novel approach to equipping LLMs with product knowledge by training them to respond contextually to synthetic search queries that include product IDs. We delve into an extensive analysis of this method, evaluating its effectiveness, outlining its benefits, and highlighting its constraints. The paper also discusses the potential improvements and future directions for this approach, providing a comprehensive understanding of the role of LLMs in product recommendations.

cs.IR↗

arXiv2023

Nonlocality via multiqubit orthogonal product bases

We investigate the quantum nonlocality via the discrimination on two, three and four-qubit orthogonal product bases (OPBs). We show that every two-qubit, and some three and four-qubit OPBs can be locally distinguished. It turns out that the remaining three and four-qubit OPBs cannot be locally distinguished, and thus they show the quantum nonlocality without entanglement. We also distinguish them by merging some systems using quantum teleportation with assisted Bell states.

quant-ph↗

arXiv2023

Writing your own book: A method for going from closed to open book QA to improve robustness and performance of smaller LLMs

We introduce two novel methods, Tree-Search and Self-contextualizing QA, designed to enhance the performance of large language models (LLMs) in question-answering tasks. Tree-Search is a sampling technique specifically created to extract diverse information from an LLM for a given prompt. Self-contextualizing QA leverages Tree-Search to enable the model to create its own context using a wide range of information relevant to the prompt, evaluate it explicitly and return a open book answer to the initial prompt . We demonstrate that the quality of generated answers improves according to various metrics, including accuracy, informativeness, coherence, and consistency, as evaluated by GPT3.5(text-davinci-003). Furthermore, we show that our methods result in increased robustness and that performance is positively correlated with tree size, benefiting both answer quality and robustness. Finally, we discuss other promising applications of Tree-Search, highlighting its potential to enhance a broad range of tasks beyond question-answering. \noindent We also discuss several areas for future work, including refining the Tree-Search and Self-Contextualizing QA methods, improving the coherence of the generated context, and investigating the impact of bootstrapping on model robustness

cs.CL↗

arXiv2020

A Kaczmarz Method with Simple Random Sampling for Solving Large Linear Systems

The Kaczmarz method is a popular iterative scheme for solving large-scale linear systems. The randomized Kaczmarz method (RK) greatly improves the convergence rate of the Kaczmarz method, by using the rows of the coefficient matrix in random order rather than in their given order. An obvious disadvantage of the randomized Kaczmarz method is its probability criterion for selecting the active or working rows in the coefficient matrix. In [{\sc Z.Z. Bai, W. Wu}, {\em On greedy randomized Kaczmarz method for solving large sparse linear systems}, SIAM Journal on Scientific Computing, 2018, 40: A592--A606], the authors proposed a greedy randomized Kaczmarz method (GRK). However, this method may suffer from heavily computational cost when the size of the matrix is large, and the overhead will be prohibitively large for big data problems. The contribution of this work is as follows. First, from the probability significance point of view, we present a partially randomized Kaczmarz method, which can reduce the computational overhead needed in greedy randomized Kaczmarz method. Second, based on Chebyshev's law of large numbers and Z-test, we apply a simple sampling approach to the partially randomized Kaczmarz method. The convergence of the proposed method is established. Third, we apply the new strategy to the ridge regression problem, and propose a partially randomized Kaczmarz method with simple random sampling for ridge regression. Numerical experiments demonstrate the superiority of the new algorithms over many state-of-the-art randomized Kaczmarz methods for large linear systems problems and ridge regression problems.

math.NA↗

arXiv2017

Rapid focus map surveying for whole slide imaging with continues sample motion

Whole slide imaging (WSI) has recently been cleared for primary diagnosis in the US. A critical challenge of WSI is to perform accurate focusing in high speed. Traditional systems create a focus map prior to scanning. For each focus point on the map, sample needs to be static in the x-y plane and axial scanning is needed to maximize the contrast. Here we report a novel focus map surveying method for WSI. The reported method requires no axial scanning, no additional camera and lens, works for stained and transparent samples, and allows continuous sample motion in the surveying process. It can be used for both brightfield and fluorescence WSI. By using a 20X, 0.75 NA objective lens, we demonstrate a mean focusing error of ~0.08 microns in the static mode and ~0.17 microns in the continuous motion mode. The reported method may provide a turnkey solution for most existing WSI systems for its simplicity, robustness, accuracy, and high-speed. It may also standardize the imaging performance of WSI systems for digital pathology and find other applications in high-content microscopy such as DNA sequencing and time-lapse live-cell imaging.

cs.CV↗

arXiv2017

Dual-LED-based multichannel microscopy for whole-slide multiplane, multispectral, and phase imaging

We report the development of a multichannel microscopy for whole-slide multiplane, multispectral, and phase imaging. We use trinocular heads to split the beam path into 6 independent channels and employ a camera array for parallel data acquisition, achieving a maximum data throughput of ~1 gigapixel per second. To perform single-frame rapid autofocusing, we place two near-infrared LEDs at the back focal plane of the condenser lens to illuminate the sample from two different incident angles. A hot mirror is used to direct the near-infrared light to an autofocusing camera. For multiplane whole slide imaging (WSI), we acquire 6 different focal planes of a thick specimen simultaneously. For multispectral WSI, we relay the 6 independent image planes to the same focal position and simultaneously acquire information at 6 spectral bands. For whole-slide phase imaging, we acquire images at 3 focal positions simultaneously and use the transport-of-intensity equation to recover the phase information. We also provide an open-source design to further increase the number of channels from 6 to 15. The reported platform provides a simple solution for multiplexed fluorescence imaging and multimodal WSI. Acquiring an instant focal stack without z-scanning may also enable fast 3D dynamic tracking of various biological samples.

physics.ins-det↗