arXiv subjects

Yuhan Wang

Publications and source records attributed to Yuhan Wang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Building Audio-Visual Digital Twins with Smartphones

Digital twins today are almost entirely visual, overlooking acoustics-a core component of spatial realism and interaction. We introduce AV-Twin, the first practical system that constructs editable audio-visual digital twins using only commodity smartphones. AV-Twin combines mobile RIR capture and a visual-assisted acoustic field model to efficiently reconstruct room acoustics. It further recovers per-surface material properties through differentiable acoustic rendering, enabling users to modify materials, geometry, and layout while automatically updating both audio and visuals. Together, these capabilities establish a practical path toward fully modifiable audio-visual digital twins for real-world environments.

cs.SD↗

arXiv2025

MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing

Recent years have witnessed the success of diffusion models in image customization tasks. However, existing mask-guided human erasing methods still struggle in complex scenarios such as human-human occlusion, human-object entanglement, and human-background interference, mainly due to the lack of large-scale multi-instance datasets and effective spatial decoupling to separate foreground from background. To bridge these gaps, we curate the MILD dataset capturing diverse poses, occlusions, and complex multi-instance interactions. We then define the Cross-Domain Attention Gap (CAG), an attention-gap metric to quantify semantic leakage. On top of these, we propose Multi-Layer Diffusion (MILD), which decomposes the generation process into independent denoising pathways, enabling separate reconstruction of each foreground instance and the background. To enhance human-centric understanding, we introduce Human Morphology Guidance, a plug-and-play module that incorporates pose, parsing, and spatial relationships into the diffusion process to improve structural awareness and restoration quality. Additionally, we present Spatially-Modulated Attention, an adaptive mechanism that leverages spatial mask priors to modulate attention across semantic regions, further widening the CAG to effectively minimize boundary artifacts and mitigate semantic leakage. Experiments show that MILD significantly outperforms existing methods. Datasets and code are publicly available at: https://mild-multi-layer-diffusion.github.io/.

cs.CV↗

arXiv2025

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering -- STAR-1 aims to address the critical needs for safety alignment in LRMs. Specifically, we begin by integrating existing open-source safety datasets from diverse sources. Then, we curate safety policies to generate policy-grounded deliberative reasoning samples. Lastly, we apply a GPT-4o-based safety scoring system to select training examples aligned with best practices. Experimental results show that fine-tuning LRMs with STAR-1 leads to an average 40% improvement in safety performance across four benchmarks, while only incurring a marginal decrease (e.g., an average of 1.1%) in reasoning ability measured across five reasoning tasks. Extensive ablation studies further validate the importance of our design principles in constructing STAR-1 and analyze its efficacy across both LRMs and traditional LLMs. Our project page is https://ucsc-vlaa.github.io/STAR-1.

cs.CL↗

arXiv2025

KGBridge: Knowledge-Guided Prompt Learning for Non-overlapping Cross-Domain Recommendation

Knowledge Graphs (KGs), as structured knowledge bases that organize relational information across diverse domains, provide a unified semantic foundation for cross-domain recommendation (CDR). By integrating symbolic knowledge with user-item interactions, KGs enrich semantic representations, support reasoning, and enhance model interpretability. Despite this potential, existing KG-based methods still face major challenges in CDR, particularly under non-overlapping user scenarios. These challenges arise from: (C1) sensitivity to KG sparsity and popularity bias, (C2) dependence on overlapping users for domain alignment and (C3) lack of explicit disentanglement between transferable and domain-specific knowledge, which limit effective and stable knowledge transfer. To this end, we propose KGBridge, a knowledge-guided prompt learning framework for cross-domain sequential recommendation under non-overlapping user scenarios. KGBridge comprises two core components: a KG-enhanced Prompt Encoder, which models relation-level semantics as soft prompts to provide structured and dynamic priors for user sequence modeling (addressing C1), and a Two-stage Training Paradigm, which combines cross-domain pretraining and privacy-preserving fine-tuning to enable knowledge transfer without user overlap (addressing C2). By combining relation-aware semantic control with correspondence-driven disentanglement, KGBridge explicitly separates and balances domain-shared and domain-specific semantics, thereby maintaining complementarity and stabilizing adaptation during fine-tuning (addressing C3). Extensive experiments on benchmark datasets demonstrate that KGBridge consistently outperforms state-of-the-art baselines and remains robust under varying KG sparsity, highlighting its effectiveness in mitigating structural imbalance and semantic entanglement in KG-enhanced cross-domain recommendation.

cs.IR↗

arXiv2025

LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition

The growing diversity of large language models (LLMs) means users often need to compare and combine outputs from different models to obtain higher-quality or more comprehensive responses. However, switching between separate interfaces and manually integrating outputs is inherently inefficient, leading to a high cognitive burden and fragmented workflows. To address this, we present LLMartini, a novel interactive system that supports seamless comparison, selection, and intuitive cross-model composition tools. The system decomposes responses into semantically aligned segments based on task-specific criteria, automatically merges consensus content, and highlights model differences through color coding while preserving unique contributions. In a user study (N=18), LLMartini significantly outperformed conventional manual methods across all measured metrics, including task completion time, cognitive load, and user satisfaction. Our work highlights the importance of human-centered design in enhancing the efficiency and creativity of multi-LLM interactions and offers practical implications for leveraging the complementary strengths of various language models.

cs.HC↗

arXiv2025

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations

Humans rely on multisensory integration to perceive spatial environments, where auditory cues enable sound source localization in three-dimensional space. Despite the critical role of spatial audio in immersive technologies such as VR/AR, most existing multimodal datasets provide only monaural audio, which limits the development of spatial audio generation and understanding. To address these challenges, we introduce MRSAudio, a large-scale multimodal spatial audio dataset designed to advance research in spatial audio understanding and generation. MRSAudio spans four distinct components: MRSLife, MRSSpeech, MRSMusic, and MRSSing, covering diverse real-world scenarios. The dataset includes synchronized binaural and ambisonic audio, exocentric and egocentric video, motion trajectories, and fine-grained annotations such as transcripts, phoneme boundaries, lyrics, scores, and prompts. To demonstrate the utility and versatility of MRSAudio, we establish five foundational tasks: audio spatialization, and spatial text to speech, spatial singing voice synthesis, spatial music generation and sound event localization and detection. Results show that MRSAudio enables high-quality spatial modeling and supports a broad range of spatial audio research. Demos and dataset access are available at https://mrsaudio.github.io.

cs.SD↗

arXiv2025

Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks

Early tumor detection save lives. Each year, more than 300 million computed tomography (CT) scans are performed worldwide, offering a vast opportunity for effective cancer screening. However, detecting small or early-stage tumors on these CT scans remains challenging, even for experts. Artificial intelligence (AI) models can assist by highlighting suspicious regions, but training such models typically requires extensive tumor masks--detailed, voxel-wise outlines of tumors manually drawn by radiologists. Drawing these masks is costly, requiring years of effort and millions of dollars. In contrast, nearly every CT scan in clinical practice is already accompanied by medical reports describing the tumor's size, number, appearance, and sometimes, pathology results--information that is rich, abundant, and often underutilized for AI training. We introduce R-Super, which trains AI to segment tumors that match their descriptions in medical reports. This approach scales AI training with large collections of readily available medical reports, substantially reducing the need for manually drawn tumor masks. When trained on 101,654 reports, AI models achieved performance comparable to those trained on 723 masks. Combining reports and masks further improved sensitivity by +13% and specificity by +8%, surpassing radiologists in detecting five of the seven tumor types. Notably, R-Super enabled segmentation of tumors in the spleen, gallbladder, prostate, bladder, uterus, and esophagus, for which no public masks or AI models previously existed. This study challenges the long-held belief that large-scale, labor-intensive tumor mask creation is indispensable, establishing a scalable and accessible path toward early detection across diverse tumor types. We plan to release our trained models, code, and dataset at https://github.com/MrGiovanni/R-Super

cs.CV↗

arXiv2025

Quantum Circuit Synthesis and Compilation Optimization: Overview and Prospects

Quantum computing is a promising paradigm that may overcome the current computational power bottlenecks. The increasing maturity of quantum processors provides more possibilities for the development and implementation of quantum algorithms. As the crucial stages for quantum algorithm implementation, the logic circuit design and quantum compiling have also received significant attention, which covers key technologies, e.g., quantum logic circuit synthesis (also widely known as quantum architecture search) and optimization, as well as qubit mapping and routing. Recent studies suggest that the scale and precision of related algorithms are steadily increasing, especially with the integration of artificial intelligence methods. In this survey, we systematically review and summarize a vast body of literature, exploring the feasibility of an integrated design and optimization scheme that spans from the algorithmic level to quantum hardware, combining the steps of logic circuit design and compilation optimization. Leveraging the exceptional cognitive and learning capabilities of AI algorithms, it becomes more possible to reduce manual design costs, enhance the precision and efficiency of execution, and facilitate the implementation and validation of the superiority of quantum algorithms on hardware.

quant-ph↗

arXiv2025

Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation

Recent advances in generative medical models are constrained by modality-specific scenarios that hinder the integration of complementary evidence from imaging, pathology, and clinical notes. This fragmentation limits their evolution into foundation models that can learn and reason across the full spectrum of biomedical data. We propose MeDiM, the first medical discrete diffusion model that learns shared distributions across modalities without modality-specific components. MeDiM unifies multiple generative tasks: translating between images and text, and jointly producing image-report pairs across domains in response to prompts. Built on a discrete diffusion framework, MeDiM bridges vision and language representations through a shared probabilistic space. To enable unified and flexible medical generation, we employ a multimodal large language model (MLLM) as the diffusion backbone, leveraging its prior knowledge and cross-modal reasoning. Two key designs are introduced: (1) removing the causal attention mask for bidirectional context, and (2) injecting continuous timestep embeddings for diffusion awareness. Experiments demonstrate high-fidelity medical generation (FID 16.60 on MIMIC-CXR and FID 24.19 on PathGen) and accurate report generation (METEOR 0.2650 and 0.2580). Jointly generated image-report pairs further enhance downstream performance (plus6.43 percent BLEU-1, plus18.57 percent BLEU-2, plus31.58 percent BLEU-3, plus4.80 percent METEOR), showing that MeDiM supports coherent and clinically grounded multimodal outputs.

cs.CV↗

arXiv2025

The Simons Observatory: Characterization of All DC/RF Routing Wafers for Detector Modules

The Simons Observatory (SO) is a cosmic microwave background experiment with over 67,000 polarization-sensitive transition-edge sensor (TES) detectors currently installed for use in observations and plans to increase the total detector count to ${\sim}$98,000 detectors with the Advanced SO upgrade. The TES arrays are packaged into Universal Focal-Plane Modules (UFMs), which also contain the multiplexing readout circuit. Within a readout module, a DC/RF routing wafer provides a cold interface between the detectors and the readout multiplexing chips. Each routing wafer hosts twelve bias lines, which contain the ${\sim}$400 $μΩ$ shunt resistors that are part of the TES bias circuitry. More than 70 routing wafers have been fabricated and tested both at room temperature and 100 mK before integration into UFMs. The lab measurements for all screened wafers have been compiled to show the distribution of measured average shunt resistance Rsh for each bias line, both across bias lines on a single routing wafer and across all routing wafers. The mean average shunt resistance for all wafers was found to be 396 $μΩ$ with a standard deviation of 16 $μΩ$, or ${\sim}$4%. For each wafer, we note good uniformity of average Rsh between bias lines, with a slight downward trend with increasing distance from the center of the wafer. The fabrication data collected at room temperature shows agreement with the cryogenic measurements of Rsh distribution.

astro-ph.IM↗

arXiv2025

The Simons Observatory: Studies of Phase Drift in RF Transmission Lines from the First Large-Scale Deployment of Microwave Frequency Multiplexing for Cosmology

Fulfilling the science goals of the Simons Observatory, a state-of-the-art cosmic microwave background (CMB) experiment, has required deploying tens of thousands of superconducting bolometers. Reading out data from the observatory's more than 67,000 transition-edge sensor (TES) detectors while maintaining cryogenic conditions requires an effective multiplexing scheme. The SLAC microresonator radio frequency (SMuRF) electronics have been developed to provide the warm electronics for a high-density microwave frequency multiplexing readout system, and this system has been shown to achieve multiplexing factors on the order of 1,000. SMuRF has recently been deployed to the Simons Observatory, which is located at 5,200 m on Cerro Toco in Chile's Atacama Desert. As the SMuRF system is exposed to the desert's diurnal temperature swings, resulting phase drift in RF transmission lines may introduce a systematic signal contamination. We present studies of phase drift in the room-temperature RF lines of the Simons Observatory's 6 m large-aperture telescope, which hosts the largest deployment to date of TES microwave frequency multiplexing to a single telescope. We show that these phase drifts occur on time scales which are significantly longer than sky scanning, and that their contribution to on-sky in-transition detector noise is within the readout noise budget.

astro-ph.IM↗

arXiv2025

CCAT: Mod-Cam Cryogenic Performance and its Impact on 280 GHz KID Array Noise

The CCAT Observatory's Fred Young Submillimeter Telescope (FYST) is designed to observe submillimeter astronomical signals with high precision, using receivers fielding state-of-the-art kinetic inductance detector (KID) arrays. Mod-Cam, a first-light instrument for FYST, serves as a testbed for instrument module characterization, including detailed evaluation of thermal behavior under operating conditions prior to deploying modules in the larger Prime-Cam instrument. Prime-Cam is a first generation multi-band, wide-field camera for FYST, designed to field up to seven instrument modules and provide unprecedented sensitivity across a broad frequency range. We present results from two key laboratory characterizations: an "optically open" cooldown to validate the overall thermal performance of the cryostat, and a "cold load" cooldown to measure the effect of focal plane temperature stability on detector noise. During the optically open test, we achieved stable base temperatures of 1.5 K on the 1 K stage and 85 mK at the detector stage. In the cold load configuration, we measured a detector focal plane RMS temperature stability of 3.2e-5 K. From this stability measurement, we demonstrate that the equivalent power from focal plane thermal fluctuations is only 0.0040% of a 5pW incident photon power for aluminum detectors and 0.0023% for titanium-nitride detectors, a negligible level for CCAT science goals. This highlights the success of the cryogenic system design and thermal management.

astro-ph.IM↗

arXiv2025

Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scenarios by compressing high-resolution meshes into compact, editable representations. Towards this end, effective shape abstraction must therefore be structure-aware, characterized by low overlap between primitives, part-aware alignment, and primitive compactness. We present Light-SQ, a novel superquadric-based optimization framework that explicitly emphasizes structure-awareness from three aspects. (a) We introduce SDF carving to iteratively udpate the target signed distance field, discouraging overlap between primitives. (b) We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition, enabling structural partitioning to drive primitive placement. (c) We implement adaptive residual pruning based on SDF update history to surpress over-segmentation and ensure compact results. In addition, Light-SQ supports multiscale fitting, enabling localized refinement to preserve fine geometric details. To evaluate our method, we introduce 3DGen-Prim, a benchmark extending 3DGen-Bench with new metrics for both reconstruction quality and primitive-level editability. Extensive experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics for complex generated geometry, advancing the feasibility of 3D UGC creation.

cs.GR↗

arXiv2025

Live-E2T: Real-time Threat Monitoring in Video via Deduplicated Event Reasoning and Chain-of-Thought

Real-time threat monitoring identifies threatening behaviors in video streams and provides reasoning and assessment of threat events through explanatory text. However, prevailing methodologies, whether based on supervised learning or generative models, struggle to concurrently satisfy the demanding requirements of real-time performance and decision explainability. To bridge this gap, we introduce Live-E2T, a novel framework that unifies these two objectives through three synergistic mechanisms. First, we deconstruct video frames into structured Human-Object-Interaction-Place semantic tuples. This approach creates a compact, semantically focused representation, circumventing the information degradation common in conventional feature compression. Second, an efficient online event deduplication and updating mechanism is proposed to filter spatio-temporal redundancies, ensuring the system's real time responsiveness. Finally, we fine-tune a Large Language Model using a Chain-of-Thought strategy, endow it with the capability for transparent and logical reasoning over event sequences to produce coherent threat assessment reports. Extensive experiments on benchmark datasets, including XD-Violence and UCF-Crime, demonstrate that Live-E2T significantly outperforms state-of-the-art methods in terms of threat detection accuracy, real-time efficiency, and the crucial dimension of explainability.

cs.CV↗

arXiv2025

Towards deployment-centric multimodal AI beyond vision and language

Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact.

cs.AI↗

arXiv2025

MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration

With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on feature recognition struggle to capture high-level behavioral semantics from historical information, while generative approaches based on Large Language Models (LLMs) often fail to meet real-time requirements. To address these challenges, we propose MA-CBP, a criminal behavior prediction framework based on multi-agent asynchronous collaboration. This framework transforms real-time video streams into frame-level semantic descriptions, constructs causally consistent historical summaries, and fuses adjacent image frames to perform joint reasoning over long- and short-term contexts. The resulting behavioral decisions include key elements such as event subjects, locations, and causes, enabling early warning of potential criminal activity. In addition, we construct a high-quality criminal behavior dataset that provides multi-scale language supervision, including frame-level, summary-level, and event-level semantic annotations. Experimental results demonstrate that our method achieves superior performance on multiple datasets and offers a promising solution for risk warning in urban public safety scenarios.

cs.CV↗

arXiv2025

XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs

The rapid spread of multimodal misinformation on social media calls for more effective and robust detection methods. Recent advances leveraging multimodal large language models (MLLMs) have shown the potential in addressing this challenge. However, it remains unclear exactly where the bottleneck of existing approaches lies (evidence retrieval v.s. reasoning), hindering the further advances in this field. On the dataset side, existing benchmarks either contain outdated events, leading to evaluation bias due to discrepancies with contemporary social media scenarios as MLLMs can simply memorize these events, or artificially synthetic, failing to reflect real-world misinformation patterns. Additionally, it lacks comprehensive analyses of MLLM-based model design strategies. To address these issues, we introduce XFacta, a contemporary, real-world dataset that is better suited for evaluating MLLM-based detectors. We systematically evaluate various MLLM-based misinformation detection strategies, assessing models across different architectures and scales, as well as benchmarking against existing detection methods. Building on these analyses, we further enable a semi-automatic detection-in-the-loop framework that continuously updates XFacta with new content to maintain its contemporary relevance. Our analysis provides valuable insights and practices for advancing the field of multimodal misinformation detection. The code and data have been released.

cs.CL↗

arXiv2025

Hoi2Threat: An Interpretable Threat Detection Method for Human Violence Scenarios Guided by Human-Object Interaction

In light of the mounting imperative for public security, the necessity for automated threat detection in high-risk scenarios is becoming increasingly pressing. However, existing methods generally suffer from the problems of uninterpretable inference and biased semantic understanding, which severely limits their reliability in practical deployment. In order to address the aforementioned challenges, this article proposes a threat detection method based on human-object interaction pairs (HOI-pairs), Hoi2Threat. This method is based on the fine-grained multimodal TD-Hoi dataset, enhancing the model's semantic modeling ability for key entities and their behavioral interactions by using structured HOI tags to guide language generation. Furthermore, a set of metrics is designed for the evaluation of text response quality, with the objective of systematically measuring the model's representation accuracy and comprehensibility during threat interpretation. The experimental results have demonstrated that Hoi2Threat attains substantial enhancement in several threat detection tasks, particularly in the core metrics of Correctness of Information (CoI), Behavioral Mapping Accuracy (BMA), and Threat Detailed Orientation (TDO), which are 5.08, 5.04, and 4.76, and 7.10%, 6.80%, and 2.63%, respectively, in comparison with the Gemma3 (4B). The aforementioned results provide comprehensive validation of the merits of this approach in the domains of semantic understanding, entity behavior mapping, and interpretability.

cs.CV↗