arXiv subjects

Wang Liao

Publications and source records attributed to Wang Liao.

12 recordsLinked to original sources

arXiv2026

All-optical Synchronization of Breather Solitons in a Kerr Microresonator

Microresonator Kerr solitons are promising candidates for the realization of miniaturized on-chip optical frequency combs. For specific system parameters, these solitons are associated with oscillatory instabilities, leading to breathing dynamics characterized by periodically modulated temporal and spectral profiles. In this regime, the solitons form a frequency comb comprised of primary comb lines surrounded by sidebands separated by the breathing frequency. Here, we numerically and experimentally demonstrate that the breathing sidebands can be all-optically synchronized to a weak monochromatic laser injected into the cavity, thus providing direct control of the soliton oscillation frequency. We judiciously characterize the synchronization process, and show that it is accompanied by a strong reduction of noise in the soliton's breathing. Our results provide fundamental insights on oscillatory dissipative structures, and could enable new forms of composite optical frequency combs.

physics.optics↗

arXiv2026

Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography

Sparse-view computed tomography is a severely ill-posed inverse problem, where recent 3D Gaussian Splatting methods offer an efficient explicit representation for tomographic reconstruction. However, we find that projection-domain optimization can be misleading in this setting: the rendered projections may continue to improve while the reconstructed volume deteriorates. We identify this failure mode as Projection-Volume Fidelity Divergence (PVFD), a representation-level optimization drift caused by anisotropic Gaussian deformation and view-specific primitive co-adaptation under sparse Radon constraints. To characterize this behavior, we introduce geometry- and volume-level diagnostics that measure needle-like Gaussian degeneration and the stability of the voxelized density field. Based on these observations, we propose LADES, a ground-truth-free optimization controller for sparse-view Gaussian tomography. LADES combines Linearly Annealed Dropout, which applies strong stochastic masking in early training to disrupt premature primitive co-adaptation and gradually restores full capacity for structural consolidation, with Structure-Aware Early Stopping, which terminates densification according to the saturation of Gaussian population growth rather than validation PSNR. Experiments on sparse-view CT reconstruction show that LADES improves volumetric fidelity, suppresses structural degeneration, and substantially reduces training time while maintaining competitive projection accuracy. These results suggest that robust Gaussian-based tomography requires monitoring and controlling volumetric structure, rather than optimizing projection fit alone.

cs.CV↗

arXiv2026

Seedance 2.0: Advancing Video Generation for World Complexity

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

cs.CV↗

arXiv2026

Design automation and space-time reduction for surface-code logical operations using a SAT-based EDA kernel compatible with general encodings

Fault-tolerant quantum computers (FTQCs) based on surface codes and lattice surgery have been widely studied, and there is strong demand for a framework that can identify logical operations with low space-time cost, verify their functionality and fault tolerance, and demonstrate their optimality within a given search space, much like electronic design automation (EDA) in classical circuit design. In this paper, we propose KOVAL-Q, an EDA kernel that verifies and optimizes surface-code logical operations by formulating them as a satisfiability (SAT) problem. Compared with existing SAT-based frameworks such as LaSsynth, our method can handle logical qubits with more flexible surface-code encodings, both as target configurations and as intermediate states. This extension enables the optimization of advanced layouts, such as fast blocks, and broadens the search space for logical operations. We demonstrate that KOVAL-Q can determine the minimum execution time of fundamental logical operations in given spatial layouts, such as $d$-cycle logical CNOTs and $2d$-cycle patch rotations. Their use reduces the execution time of widely studied FTQC applications by about 10% under a simplified scheduling model. KOVAL-Q consists of three subkernels corresponding to different types of constraints, which facilitates its integration as a submodule into scalable heuristic frameworks. Thus, our proposal provides an essential framework for optimizing and validating core FTQC subroutines.

quant-ph↗

arXiv2025

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.

cs.CV↗

arXiv2025

AI summaries in online search influence users' attitudes

This study examined how AI-generated summaries, which have become visually prominent in online search results, affect how users think about different issues. In a preregistered randomized controlled experiment, participants (N = 2,004) viewed mock search result pages varying in the presence (vs. absence), placement (top vs. middle), and stance (benefit-framed vs. harm-framed) of AI-generated summaries across four publicly debated topics. Compared to a no-summary control group, participants exposed to AI-generated summaries reported issue attitudes, behavioral intentions, and policy support that aligned more closely with the AI summary stance. The summaries placed at the top of the page produced stronger shifts in users' issue attitudes (but not behavioral intentions or policy support) than those placed at the middle of the page. We also observed moderating effects from issue familiarity and general trust toward AI. In addition, users perceived the AI summaries more useful when it emphasized health harms versus benefits. These findings suggest that AI-generated search summaries can significantly shape public perceptions, raising important implications for the design and regulation of AI-integrated information ecosystems.

cs.HC↗

arXiv2025

OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

Existing video avatar models can produce fluid human animations, yet they struggle to move beyond mere physical likeness to capture a character's authentic essence. Their motions typically synchronize with low-level cues like audio rhythm, lacking a deeper semantic understanding of emotion, intent, or context. To bridge this gap, \textbf{we propose a framework designed to generate character animations that are not only physically plausible but also semantically coherent and expressive.} Our model, \textbf{OmniHuman-1.5}, is built upon two key technical contributions. First, we leverage Multimodal Large Language Models to synthesize a structured textual representation of conditions that provides high-level semantic guidance. This guidance steers our motion generator beyond simplistic rhythmic synchronization, enabling the production of actions that are contextually and emotionally resonant. Second, to ensure the effective fusion of these multimodal inputs and mitigate inter-modality conflicts, we introduce a specialized Multimodal DiT architecture with a novel Pseudo Last Frame design. The synergy of these components allows our model to accurately interpret the joint semantics of audio, images, and text, thereby generating motions that are deeply coherent with the character, scene, and linguistic content. Extensive experiments demonstrate that our model achieves leading performance across a comprehensive set of metrics, including lip-sync accuracy, video quality, motion naturalness and semantic consistency with textual prompts. Furthermore, our approach shows remarkable extensibility to complex scenarios, such as those involving multi-person and non-human subjects. Homepage: \href{https://omnihuman-lab.github.io/v1_5/}

cs.CV↗

arXiv2025

GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction

3D Gaussian Splatting (3DGS) has emerged as a promising approach for CT reconstruction. However, existing methods rely on the average gradient magnitude of points within the view, often leading to severe needle-like artifacts under sparse-view conditions. To address this challenge, we propose GR-Gaussian, a graph-based 3D Gaussian Splatting framework that suppresses needle-like artifacts and improves reconstruction accuracy under sparse-view conditions. Our framework introduces two key innovations: (1) a Denoised Point Cloud Initialization Strategy that reduces initialization errors and accelerates convergence; and (2) a Pixel-Graph-Aware Gradient Strategy that refines gradient computation using graph-based density differences, improving splitting accuracy and density representation. Experiments on X-3D and real-world datasets validate the effectiveness of GR-Gaussian, achieving PSNR improvements of 0.67 dB and 0.92 dB, and SSIM gains of 0.011 and 0.021. These results highlight the applicability of GR-Gaussian for accurate CT reconstruction under challenging sparse-view conditions.

eess.IV↗

arXiv2025

AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation

Recent advancements in human video generation and animation tasks, driven by diffusion models, have achieved significant progress. However, expressive and realistic human animation remains challenging due to the trade-off between motion naturalness and visual fidelity. To address this, we propose \textbf{AlignHuman}, a framework that combines Preference Optimization as a post-training technique with a divide-and-conquer training strategy to jointly optimize these competing objectives. Our key insight stems from an analysis of the denoising process across timesteps: (1) early denoising timesteps primarily control motion dynamics, while (2) fidelity and human structure can be effectively managed by later timesteps, even if early steps are skipped. Building on this observation, we propose timestep-segment preference optimization (TPO) and introduce two specialized LoRAs as expert alignment modules, each targeting a specific dimension in its corresponding timestep interval. The LoRAs are trained using their respective preference data and activated in the corresponding intervals during inference to enhance motion naturalness and fidelity. Extensive experiments demonstrate that AlignHuman improves strong baselines and reduces NFEs during inference, achieving a 3.3$\times$ speedup (from 100 NFEs to 30 NFEs) with minimal impact on generation quality. Homepage: \href{https://alignhuman.github.io/}{https://alignhuman.github.io/}

cs.CV↗

arXiv2024

Q3DE: A fault-tolerant quantum computer architecture for multi-bit burst errors by cosmic rays

Demonstrating small error rates by integrating quantum error correction (QEC) into an architecture of quantum computing is the next milestone towards scalable fault-tolerant quantum computing (FTQC). Encoding logical qubits with superconducting qubits and surface codes is considered a promising candidate for FTQC architectures. In this paper, we propose an FTQC architecture, which we call Q3DE, that enhances the tolerance to multi-bit burst errors (MBBEs) by cosmic rays with moderate changes and overhead. There are three core components in Q3DE: in-situ anomaly DEtection, dynamic code DEformation, and optimized error DEcoding. In this architecture, MBBEs are detected only from syndrome values for error correction. The effect of MBBEs is immediately mitigated by dynamically increasing the encoding level of logical qubits and re-estimating probable recovery operation with the rollback of the decoding process. We investigate the performance and overhead of the Q3DE architecture with quantum-error simulators and demonstrate that Q3DE effectively reduces the period of MBBEs by 1000 times and halves the size of their region. Therefore, Q3DE significantly relaxes the requirement of qubit density and qubit chip size to realize FTQC. Our scheme is versatile for mitigating MBBEs, i.e., temporal variations of error properties, on a wide range of physical devices and FTQC architectures since it relies only on the standard features of topological stabilizer codes.

quant-ph↗

arXiv2020

Using Reports of Own and Others' Symptoms and Diagnosis on Social Media to Predict COVID-19 Case Counts: Observational Infoveillance Study in Mainland China

Can public social media data be harnessed to predict COVID-19 case counts? We analyzed approximately 15 million COVID-19 related posts on Weibo, a popular Twitter-like social media platform in China, from November 1, 2019 to March 31, 2020. We developed a machine learning classifier to identify "sick posts," which are reports of one's own and other people's symptoms and diagnosis related to COVID-19. We then modeled the predictive power of sick posts and other COVID-19 posts on daily case counts. We found that reports of symptoms and diagnosis of COVID-19 significantly predicted daily case counts, up to 14 days ahead of official statistics. But other COVID-19 posts did not have similar predictive power. For a subset of geotagged posts (3.10% of all retrieved posts), we found that the predictive pattern held true for both Hubei province and the rest of mainland China, regardless of unequal distribution of healthcare resources and outbreak timeline. Researchers and disease control agencies should pay close attention to the social media infosphere regarding COVID-19. On top of monitoring overall search and posting activities, it is crucial to sift through the contents and efficiently identify true signals from noise.

cs.SI↗

arXiv2019

When Single Event Upset Meets Deep Neural Networks: Observations, Explorations, and Remedies

Deep Neural Network has proved its potential in various perception tasks and hence become an appealing option for interpretation and data processing in security sensitive systems. However, security-sensitive systems demand not only high perception performance, but also design robustness under various circumstances. Unlike prior works that study network robustness from software level, we investigate from hardware perspective about the impact of Single Event Upset (SEU) induced parameter perturbation (SIPP) on neural networks. We systematically define the fault models of SEU and then provide the definition of sensitivity to SIPP as the robustness measure for the network. We are then able to analytically explore the weakness of a network and summarize the key findings for the impact of SIPP on different types of bits in a floating point parameter, layer-wise robustness within the same network and impact of network depth. Based on those findings, we propose two remedy solutions to protect DNNs from SIPPs, which can mitigate accuracy degradation from 28% to 0.27% for ResNet with merely 0.24-bit SRAM area overhead per parameter.

cs.LG↗