arXiv subjects

Qian Wang

Publications and source records attributed to Qian Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Subsecond 3D Mesh Generation for Robot Manipulation

3D meshes are a fundamental representation widely used in computer science and engineering. In robotics, they are particularly valuable because they capture objects in a form that aligns directly with how robots interact with the physical world, enabling core capabilities such as predicting stable grasps, detecting collisions, and simulating dynamics. Although automatic 3D mesh generation methods have shown promising progress in recent years, potentially offering a path toward real-time robot perception, two critical challenges remain. First, generating high-fidelity meshes is prohibitively slow for real-time use, often requiring tens of seconds per object. Second, mesh generation by itself is insufficient. In robotics, a mesh must be contextually grounded, i.e., correctly segmented from the scene and registered with the proper scale and pose. Additionally, unless these contextual grounding steps remain efficient, they simply introduce new bottlenecks. In this work, we introduce an end-to-end system that addresses these challenges, producing a high-quality, contextually grounded 3D mesh from a single RGB-D image in under one second. Our pipeline integrates open-vocabulary object segmentation, accelerated diffusion-based mesh generation, and robust point cloud registration, each optimized for both speed and accuracy. We demonstrate its effectiveness in a real-world manipulation task, showing that it enables meshes to be used as a practical, on-demand representation for robotics perception and planning.

cs.RO↗

arXiv2025

SyncGait: Robust Long-Distance Authentication for Drone Delivery via Implicit Gait Behaviors

In recent years, drone delivery, which utilizes unmanned aerial vehicles (UAVs) for package delivery and pickup, has gradually emerged as a crucial method in logistics. Since delivery drones are expensive and may carry valuable packages, they must maintain a safe distance from individuals until user-drone mutual authentication is confirmed. Despite numerous authentication schemes being developed, existing solutions are limited in authentication distance and lack resilience against sophisticated attacks. To this end, we introduce SyncGait, an implicit gait-based mutual authentication system for drone delivery. SyncGait leverages the user's unique arm swing as he walks toward the drone to achieve mutual authentication without requiring additional hardware or specific authentication actions. We conducted extensive experiments on 14 datasets collected from 31 subjects. The results demonstrate that SyncGait achieves an average accuracy of 99.84\% at a long distance ($>18m$) and exhibits strong resilience against various spoofing attacks, making it a robust, secure, and user-friendly solution in real-world scenarios.

cs.CR↗

arXiv2025

Valence Quark Distributions in Pions: Insights from Tsallis Entropy

We investigate the valence quark distributions of pions at a low initial scale ($Q^2_0$) by employing Tsallis entropy, a non-extensive measure that effectively captures long-range correlations among internal constituents. Utilizing the maximum entropy approach, we adopt two distinct functional forms and fit experimental data through the elegant GLR-MQ-ZRS evolution equation to derive the model parameters. Our findings indicate that the resulting valence quark distributions provide an optimal fit to experimental data, with the values of the $q$ parameter deviating from unity. This deviation indicates the significant role that correlations among valence quarks play in shaping our understanding of pion internal structure. Additionally, our computations of the first three moments of pion quark distributions at $ Q^2 = 4 \, \mathrm{GeV}^2$ display consistency with other theoretical models, thereby reinforcing the importance of incorporating valence quark correlations within this analytical framework.

hep-ph↗

arXiv2025

A voltage-responsive strongly dipolar-coupled macrospin network with emergent dynamics for computing

Emergent behavior, which arises from local interactions between simple elements, is pervasive in nature. It underlies the energy-efficient computing in our brains. However, realizing such dynamics in artificial materials, particularly under low-energy stimuli, remains a fundamental challenge. While dipole-dipole interactions are typically suppressed in magnetic storage, here we harness and amplify them to construct a strongly dipolar-coupled network of SmCo5 macrospins at wafer scale, which can exhibit intrinsic interaction-driven collective dynamics in response to voltage pulses. The network combines three essential ingredients: strong dipolar coupling by large single-domain macrospin, giant voltage control of coercivity over nearly 1000-fold, and disordered network topology with frustrated Ising-like energy landscape. When stimulated by 1 V pulses, the network enters a regime where interaction-driven magnetic behaviors emerge, including spontaneous demagnetization, greatly enhanced magnetization modulation, reversible freeze and resume evolution and stochastic convergence toward low-energy magnetic configurations. All these behaviors are completely absent at the single-nanomagnet level. Furthermore, by constructing micromagnetic models of the strongly dipolar-coupled macrospin networks, we show that the resulting nonlinear, high-dimensional collective dynamics, intrinsic to strongly-interacting systems, can enable accurate chaotic Mackey-Glass prediction and multiclass drone-signal classification. Our work establishes the voltage-responsive strongly-coupled SmCo5 network as a mesoscopic platform for probing emergent magnetic dynamics previously inaccessible under ambient conditions. It also suggests a fundamental distinct route towards scalable, low-voltage computing, one rooted in native physical interaction-driven collective dynamics at the network level.

cond-mat.mtrl-sci↗

arXiv2025

MEPIC: Memory Efficient Position Independent Caching for LLM Serving

Modern LLM applications such as deep-research assistants, coding agents, and Retrieval-Augmented Generation (RAG) systems, repeatedly process long prompt histories containing shared document or code chunks, creating significant pressure on the Key Value (KV) cache, which must operate within limited memory while sustaining high throughput and low latency. Prefix caching partially alleviates some of these costs by reusing KV cache for previously processed tokens, but limited by strict prefix matching. Position-independent caching (PIC) enables chunk-level reuse at arbitrary positions, but requires selective recomputation and positional-encoding (PE) adjustments. However, because these operations vary across queries, KV for the same chunk diverges across requests. Moreover, without page alignment, chunk KV layouts diverge in memory, preventing page sharing. These issues result in only modest HBM savings even when many requests reuse the same content. We present MEPIC, a memory-efficient PIC system that enables chunk KV reuse across positions, requests, and batches. MEPIC aligns chunk KV to paged storage, shifts recomputation from token- to block-level so only the first block is request-specific, removes positional encodings via Rotary Position Embedding (RoPE) fusion in the attention kernel, and makes remaining blocks fully shareable. These techniques eliminate most duplicate chunk KV in HBM, reducing usage by up to 2x over state-of-the-art PIC at comparable latency and accuracy, and up to 5x for long prompts, without any model changes.

cs.LG↗

arXiv2025

OptHQC: Optimize HQC for High-Performance Post-Quantum Cryptography

As post-quantum cryptography (PQC) becomes increasingly critical for securing future communication systems, the performance overhead introduced by quantum-resistant algorithms presents a major computing challenge. HQC (Hamming Quasi-Cyclic) is a newly standardized code-based PQC scheme designed to replace classical key exchange methods. In this paper, we propose OptHQC, an optimized implementation of the HQC scheme to deliver high-performance cryptographic operations. Our approach provides a comprehensive analysis of each computational blocks in HQC and introduces optimizations across all three stages: key generation, encryption, and decryption. We first exploit data-level sparsity in vector multiplication to accelerate polynomial operations during vector generation. We then leverage instruction-level acceleration (e.g., AVX2) in hash computation to further improve performance. Last, we transform multiplication into lookup table indexing and optimize memory access patterns in syndrome computation and error vector recovery, which are the most computationally intensive operations in HQC. Overall, OptHQC achieves an average 55% speedup over the reference HQC implementation on CPU.

cs.CR↗

arXiv2025

Amulet: Fast TEE-Shielded Inference for On-Device Model Protection

On-device machine learning (ML) introduces new security concerns about model privacy. Storing valuable trained ML models on user devices exposes them to potential extraction by adversaries. The current mainstream solution for on-device model protection is storing the weights and conducting inference within Trusted Execution Environments (TEEs). However, due to limited trusted memory that cannot accommodate the whole model, most existing approaches employ a partitioning strategy, dividing a model into multiple slices that are loaded into the TEE sequentially. This frequent interaction between untrusted and trusted worlds dramatically increases inference latency, sometimes by orders of magnitude. In this paper, we propose Amulet, a fast TEE-shielded on-device inference framework for ML model protection. Amulet incorporates a suite of obfuscation methods specifically designed for common neural network architectures. After obfuscation by the TEE, the entire transformed model can be securely stored in untrusted memory, allowing the inference process to execute directly in untrusted memory with GPU acceleration. For each inference request, only two rounds of minimal-overhead interaction between untrusted and trusted memory are required to process input samples and output results. We also provide theoretical proof from an information-theoretic perspective that the obfuscated model does not leak information about the original weights. We comprehensively evaluated Amulet using diverse model architectures ranging from ResNet-18 to GPT-2. Our approach incurs inference latency only 2.8-4.8x that of unprotected models with negligible accuracy loss, achieving an 8-9x speedup over baseline methods that execute inference entirely within TEEs, and performing approximately 2.2x faster than the state-of-the-art obfuscation-based method.

cs.CR↗

arXiv2025

Can VLMs Detect and Localize Fine-Grained AI-Edited Images?

Fine-grained detection and localization of localized image edits is crucial for assessing content authenticity, especially as modern diffusion models and image editors can produce highly realistic manipulations. However, this problem faces three key challenges: (1) most AIGC detectors produce only a global real-or-fake label without indicating where edits occur; (2) traditional computer vision methods for edit localization typically rely on costly pixel-level annotations; and (3) there is no large-scale, modern benchmark specifically targeting edited-image detection. To address these gaps, we develop an automated data-generation pipeline and construct FragFake, a large-scale benchmark of AI-edited images spanning multiple source datasets, diverse editing models, and several common edit types. Building on FragFake, we are the first to systematically study vision language models (VLMs) for edited-image classification and edited-region localization. Our experiments show that pretrained VLMs, including GPT4o, perform poorly on this task, whereas fine-tuned models such as Qwen2.5-VL achieve high accuracy and substantially higher object precision across all settings. We further explore GRPO-based RLVR training, which yields modest metric gains while improving the interpretability of model outputs. Ablation and transfer analyses reveal how data balancing, training size, LoRA rank, and training domain affect performance, and highlight both the potential and the limitations of cross-editor and cross-dataset generalization. We anticipate that this work will establish a solid foundation to facilitate and inspire subsequent research endeavors in the domain of multimodal content authenticity.

cs.CV↗

arXiv2025

LongCat-Flash-Omni Technical Report

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

cs.MM↗

arXiv2025

Huizhou Hadron Spectrometer -- a Proposed High-rate Experimental Setup at the High Intensity Heavy-ion Accelerator Facility

The High-Intensity Heavy-Ion Accelerator Facility (HIAF), currently under construction in Huizhou, Guangdong Province, China, is projected to be completed by 2025. This facility will be capable of producing proton and heavy-ion beams with energies reaching several GeV, thereby offering a versatile platform for advanced fundamental physics research. Key scientific objectives include exploring physics beyond the Standard Model through the search for novel particles and interactions, testing fundamental symmetries, investigating exotic hadronic states such as di-baryons, pentaquark states and multi-strange hypernuclei, conducting precise measurements of hadron and hypernucleus properties, and probing the phase boundary and critical point of nuclear matter. To facilitate these investigations, we propose the development of a dedicated experimental apparatus at HIAF - the Huizhou Hadron Spectrometer (HHaS). This paper presents the conceptual design of HHaS, comprising a solenoid magnet, a five-dimensional silicon pixel tracker, a Low-Gain Avalanche Detector (LGAD) for time-of-flight measurements, and a Cherenkov-scintillation dual-readout electromagnetic calorimeter. The design anticipates an unprecedented event rate of 1-100 MHz, extensive particle acceptance, a track momentum resolution at 1% level, an electromagnetic energy resolution of ~3% @ 1 GeV and multi-particle identification capabilities. Such capabilities position HHaS as a powerful instrument for advancing experimental studies in particle and nuclear physics. The successful realization of HHaS is expected to significantly bolster the development of medium- and high-energy physics research within China.

hep-ex↗

arXiv2025

HST Confirms Sub-5 kpc Dual Quasar Pairs at Cosmic Noon

During cosmic noon ($z\sim1-3$), when both star formation and black hole growth peaked, galaxy mergers are predicted to trigger dual active galactic nuclei (AGN) that eventually coalesce as supermassive black hole (SMBH) binaries. However, observations of dual quasars with sub-5 kpc separations-the critical phase preceding final coalescence-have remained challenging due to angular resolution limitations. We present the discovery and confirmation of two sub-arcsecond dual quasars at $z>1$, selected from 59,025 SDSS quasars, which fall within the footprint of the Hyper Suprime-Cam Survey. Using high-resolution Hubble Space Telescope (HST) imaging and slitless spectroscopy, we confirmed SDSS J1625+4309 ($z=1.647$, separation 0.55"/4.7 kpc) and SDSS J0229$-$0514 ($z=3.174$, separation 0.42"/3.2 kpc), probing the sub-5 kpc separation regime. Through novel combination of WFC3/IR direct imaging (F140W) and grism spectroscopy (G141), we resolve both components morphologically and spectroscopically confirm their dual nature via detection of H$β$+[OIII] and MgII emission lines in each nucleus. Two-dimensional image decomposition reveals distinct host galaxy morphologies: J1625+4309 shows an extended, disturbed structure ($R_e$=4.7 kpc) indicative of an ongoing major merger, while J0229$-$0514 exhibits a compact host ($R_e$=1.4 kpc) suggesting an advanced coalescence stage. Black hole mass estimates based on virial relations yield M$_{\mathrm{BH}} \sim 10^{8.1}-10^{8.7} M_\odot$ with line-of-sight velocity offsets of $(0.7\pm0.1)\times10^{3}$ km s$^{-1}$ and $(1.0\pm0.2)\times10^{3}$ km s$^{-1}$, respectively. These confirmations directly constrain the frequency and properties of close dual quasars, opening new avenues for studying SMBH mergers at cosmic noon.

astro-ph.GA↗

arXiv2025

Mesh RAG: Retrieval Augmentation for Autoregressive Mesh Generation

3D meshes are a critical building block for applications ranging from industrial design and gaming to simulation and robotics. Traditionally, meshes are crafted manually by artists, a process that is time-intensive and difficult to scale. To automate and accelerate this asset creation, autoregressive models have emerged as a powerful paradigm for artistic mesh generation. However, current methods to enhance quality typically rely on larger models or longer sequences that result in longer generation time, and their inherent sequential nature imposes a severe quality-speed trade-off. This sequential dependency also significantly complicates incremental editing. To overcome these limitations, we propose Mesh RAG, a novel, training-free, plug-and-play framework for autoregressive mesh generation models. Inspired by RAG for language models, our approach augments the generation process by leveraging point cloud segmentation, spatial transformation, and point cloud registration to retrieve, generate, and integrate mesh components. This retrieval-based approach decouples generation from its strict sequential dependency, facilitating efficient and parallelizable inference. We demonstrate the wide applicability of Mesh RAG across various foundational autoregressive mesh generation models, showing it significantly enhances mesh quality, accelerates generation speed compared to sequential part prediction, and enables incremental editing, all without model retraining.

cs.CV↗

arXiv2025

T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving

Traffic Sign Recognition (TSR) systems play a critical role in Autonomous Driving (AD) systems, enabling real-time detection of road signs, such as STOP and speed limit signs. While these systems are increasingly integrated into commercial vehicles, recent research has exposed their vulnerability to physical-world adversarial appearance attacks. In such attacks, carefully crafted visual patterns are misinterpreted by TSR models as legitimate traffic signs, while remaining inconspicuous or benign to human observers. However, existing adversarial appearance attacks suffer from notable limitations. Pixel-level perturbation-based methods often lack stealthiness and tend to overfit to specific surrogate models, resulting in poor transferability to real-world TSR systems. On the other hand, text-to-image (T2I) diffusion model-based approaches demonstrate limited effectiveness and poor generalization to out-of-distribution sign types. In this paper, we present DiffSign, a novel T2I-based appearance attack framework designed to generate physically robust, highly effective, transferable, practical, and stealthy appearance attacks against TSR systems. To overcome the limitations of prior approaches, we propose a carefully designed attack pipeline that integrates CLIP-based loss and masked prompts to improve attack focus and controllability. We also propose two novel style customization methods to guide visual appearance and improve out-of-domain traffic sign attack generalization and attack stealthiness. We conduct extensive evaluations of DiffSign under varied real-world conditions, including different distances, angles, light conditions, and sign categories. Our method achieves an average physical-world attack success rate of 83.3%, leveraging DiffSign's high effectiveness in attack transferability.

cs.CV↗

arXiv2025

Multiscale Dynamics of Roughness-Driven Flow in Soft Interfaces

Soft lubricated contacts exhibit complex interfacial behaviours governed by the coupled effects of multiscale surface roughness and non-linear fluid-solid interactions. Accurately capturing this interplay across thin-film flows is challenging due to the strong synergy between contact mechanics and hydrodynamic flow, spanning over various spatiotemporal scales. Here, we develop a rigorous computational framework to simulate the frictional behaviour of soft lubricated interfaces; its modularity and the use of optimal solvers provides solutions for realistic configurations in lubrication regimes ranging from direct solid contact to complete fluid separation. Surface roughness is described via Persson's statistical theory as well as a deterministic Conjugate Gradient with Fast Fourier Transform (CG-FFT) approach, while limitations associated with classical half-space models are addressed by developing the Reduced Stiffness Method (RSM) to rigorously model pressure-induced surface responses. The integrated framework captures the full evolution of frictional behaviour, validated against experiments on rough elastomer-glass interfaces, revealing how surface roughness and material compliance together drive the transition from solid contact to fluid-mediated sliding. The developed approach establishes a robust and versatile simulation tool for analysing a plethora of soft interfacial systems shaped by fluid-solid interactions, with potential applications including but not limited to biomechanics, soft robotics and microfluidic systems.

cond-mat.soft↗

arXiv2025

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present FreeControl, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs one-step attention extraction from a single, optimally chosen key timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce Latent-Condition Decoupling (LCD): a principled separation of the key timestep and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources - enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control, enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at approximately 5 percent additional cost.

cs.CV↗

arXiv2025

JudgeLRM: Large Reasoning Models as a Judge

Large Language Models (LLMs) are increasingly adopted as evaluators, offering a scalable alternative to human annotation. However, existing supervised fine-tuning (SFT) approaches often fall short in domains that demand complex reasoning. Judgment is inherently reasoning-intensive: beyond surface-level scoring, it requires verifying evidence, identifying errors, and justifying decisions. Through the analysis of evaluation tasks, we find a negative correlation between SFT performance gains and the proportion of reasoning-demanding samples, revealing the limits of SFT in such scenarios. To address this, we introduce JudgeLRM, a family of judgment-oriented LLMs, trained using reinforcement learning (RL) with judge-wise, outcome-driven rewards to activate reasoning capabilities. JudgeLRM consistently outperform SFT-tuned baselines in the same size, as well as other RL and SFT variants, and even surpass state-of-the-art reasoning models: notably, JudgeLRM-3B/4B exceeds GPT-4, while JudgeLRM-7B/8B/14B outperforms DeepSeek-R1 by over 2% in F1 score, with particularly strong gains on reasoning-heavy tasks. Our findings underscore the value of RL in unlocking reasoning-aligned LLM judges.

cs.CL↗

arXiv2025

VisionCAD: An Integration-Free Radiology Copilot Framework

Widespread clinical deployment of computer-aided diagnosis (CAD) systems is hindered by the challenge of integrating with existing hospital IT infrastructure. Here, we introduce VisionCAD, a vision-based radiological assistance framework that circumvents this barrier by capturing medical images directly from displays using a camera system. The framework operates through an automated pipeline that detects, restores, and analyzes on-screen medical images, transforming camera-captured visual data into diagnostic-quality images suitable for automated analysis and report generation. We validated VisionCAD across diverse medical imaging datasets, demonstrating that our modular architecture can flexibly utilize state-of-the-art diagnostic models for specific tasks. The system achieves diagnostic performance comparable to conventional CAD systems operating on original digital images, with an F1-score degradation typically less than 2\% across classification tasks, while natural language generation metrics for automated reports remain within 1\% of those derived from original images. By requiring only a camera device and standard computing resources, VisionCAD offers an accessible approach for AI-assisted diagnosis, enabling the deployment of diagnostic capabilities in diverse clinical settings without modifications to existing infrastructure.

cs.CV↗

arXiv2025

BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning

We present the B-spline Encoded Action Sequence Tokenizer (BEAST), a novel action tokenizer that encodes action sequences into compact discrete or continuous tokens using B-splines. In contrast to existing action tokenizers based on vector quantization or byte pair encoding, BEAST requires no separate tokenizer training and consistently produces tokens of uniform length, enabling fast action sequence generation via parallel decoding. Leveraging our B-spline formulation, BEAST inherently ensures generating smooth trajectories without discontinuities between adjacent segments. We extensively evaluate BEAST by integrating it with three distinct model architectures: a Variational Autoencoder (VAE) with continuous tokens, a decoder-only Transformer with discrete tokens, and Florence-2, a pretrained Vision-Language Model with an encoder-decoder architecture, demonstrating BEAST's compatibility and scalability with large pretrained models. We evaluate BEAST across three established benchmarks consisting of 166 simulated tasks and on three distinct robot settings with a total of 8 real-world tasks. Experimental results demonstrate that BEAST (i) significantly reduces both training and inference computational costs, and (ii) consistently generates smooth, high-frequency control signals suitable for continuous control tasks while (iii) reliably achieves competitive task success rates compared to state-of-the-art methods.

cs.RO↗