arXiv subjects

Xinyang Li

Publications and source records attributed to Xinyang Li.

At least 19 recordsLinked to original sources

arXiv2026

TBDub: Production-Oriented Visual Dubbing

Visual dubbing must synchronize mouth motion with replacement speech while preserving identity, appearance, and temporal consistency. Although X-Dub provides a strong mask-free video-editing baseline, its application to livestream and generated-video content reveals limitations in production-domain robustness, temporal and motion stability, identity and oral-detail preservation, and inference efficiency. We present \textbf{TBDub}, a production-oriented extension of X-Dub that combines task-adaptive post-training with task-aware few-step distillation. Post-training adapts the video DiT using production-domain data, production-specific conditioning and filtering, and enhanced audio features to obtain a 30-step Teacher. Distillation adapts DMD/DMD2 to conditional video editing and compresses the Teacher into a two-step Student. On 38 TalkVid clips, the Teacher improves all eight reported reconstruction, perceptual, identity, and synchronization metrics over X-Dub. In the MOS evaluation, it improves lip-sync consistency, identity consistency, and visual quality over X-Dub by 0.14, 0.95, and 0.90 points, while the Student achieves the highest lip-sync and visual-quality scores and remains close to the Teacher in identity consistency. In paired end-to-end generation timing from the first VAE encode through the final VAE decode on a single NVIDIA H20 GPU at $512\times512$, the Student reaches 7.13 effective FPS and reduces total latency by $13.93\times$; the DiT stage alone is accelerated by $42.49\times$. The Student largely retains the Teacher's generation quality and audiovisual synchronization. The code is available on GitHub at \https://github.com/TaoLiveAIGC/TBDub, and the 30-step Teacher and two-step Student weights are available on Hugging Face at https://huggingface.co/TaoLiveAIGC/TBDub.

cs.CV↗

arXiv2026

Variational Probabilistic Quantization for Secret Key Generation

Secret key generation from correlated observations at Alice and Bob, in the presence of an eavesdropper Eve, underpins physical-layer security. Classical pipelines quantize by hand, amplify privacy afterwards, and optimize no objective tied to a key rate. We propose Variational Probabilistic Quantization (VPQ): neural encoders that map the correlated sources directly into a discrete key alphabet, trained by a variational adversarial objective whose entropy, mismatch, and leakage terms match the three terms of the one-way secret key rate. A linear code-offset secure sketch then reconciles the encoder outputs into an identical key without a separate privacy amplification step. We prove that the VPQ losses lower-bound the one-way secret key capacity of the induced source, and derive in closed form the optimal worst-case key rate over the source class of a given alphabet size and mismatch probability, attained by finite-field linear sketches. On Gaussian fading channels, VPQ leaks less to a correlated eavesdropper than one classical and two recent learning-based baselines, and Reed--Solomon reconciliation operates within the predicted finite-blocklength gap.

cs.IT↗

arXiv2026

Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages

Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages and replays the same downstream solver, called the integrator, with each message available or hidden. The replay comparison measures a message's trajectory value: whether making the message available helps or harms subsequent reasoning. Across five mathematics and science benchmarks and two openly available model families, gpt-oss-120b and gemma-4-31B-it, wrong-helpful messages appear in every benchmark-model combination. Among wrong-answer messages that change final correctness, more than four in ten changes are helpful in each model. Controlled repeats show that the number of repeatable message effects is unlikely to arise from replay variation alone (p=0.0002). A focused intervention on repeatable wrong-helpful messages finds that the complete message works best, while retaining its reasoning preserves more success than retaining only its answer; the source of the complete-message advantage remains open. Within the same problem, repeated trajectory-value evidence also identifies a better keep-or-remove choice than answer correctness alone. Answer correctness is therefore informative but does not determine trajectory value. DHD measures this missing property and produces reusable labels for learning when agents should listen.

cs.AI↗

arXiv2026

Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising

The quantum nature of light determines the inherent Poisson stochasticity of photon detection, which is ubiquitous in photography, microscopy, and astronomy. However, our controlled numerical studies reveal that the signal-dependency, heteroscedasticity, and statistical asymmetry of Poisson-mixed noise make it challenging for existing denoisers to learn. In contrast, i.i.d. Gaussian noise, with its statistical independence and symmetric distribution, is easier to model for networks. To address this gap, we propose Poisson2Gaussian (P2G), a noise Gaussianization method that explicitly converts complex real-world noise to i.i.d. Gaussian noise via probability density matching beyond low-order moments. We also design an unbiased denoising framework that synergizes P2G with downstream denoisers, ensuring convergence to the underlying signal without requiring paired clean data or explicit noise parameters. Extensive experiments demonstrate that P2G consistently achieves state-of-the-art performance across diverse datasets. In challenging scenarios where noise strongly deviates from Gaussian statistics, our method improves the PSNR by up to 0.75 dB. Notably, P2G is architecture-agnostic and can provide universal improvements for various denoisers. The source code will be publicly available.

cs.CV↗

arXiv2026

SP-TransientBench: A Real-Captured Single Photon Perception Benchmark

Single-photon LiDAR (SPL) based on single-photon avalanche diode (SPAD) sensing enables time-resolved photon measurements with extreme sensitivity, offering unique potential for active 3D perception in photon-starved scenarios.However, real-world single photon perception remains fundamentally challenging due to unique measurement noise and complex multi-return transient phenomena, which jointly complicate geometric reconstruction and semantic scene understanding. Despite growing interest in SPAD-based sensing, existing studies are largely limited to simulated data or small-scale controlled captures. As a result, systematic evaluation of real-world single photon perception across depth estimation, multi-view reconstruction, and 3D semantic understanding remains underexplored. To bridge this gap, we introduce SP-TransientBench (STB), a real-captured multi-task benchmark for single photon perception. SP-TransientBenc comprises 10 diverse scenes and 10,297 views captured using a solid-state single-photon LiDAR at $256\times192$ resolution. Each view provides full time-of-flight histograms with multi-return behavior,standardized metadata, and calibrated camera poses for multi-view evaluation. We further provide 13-class 3D semantic annotations for selected scenes. By providing dedicated data splits and evaluation protocols for each task, STB enables consistent and reproducible benchmarking of real-world single photon perception across multiple 3D vision problems. The dataset and code will be released upon acceptance.

cs.CV↗

arXiv2026

Robust Flat Magnetoresistivity in D0$_3$-Fe$_3$Ga Driven by Chiral Anomaly

Topologically non-trivial nodes emerging from flat-band crossings not only enhance unconventional topological responses but also play a fundamental role in exploring correlation-driven topological physics. Here, we report the exceptionally robust chiral-anomaly-dominated transport in D0_3-Fe_3Ga. First, we observe a combination of positive and negative magnetoresistance, ideal planar longitudinal magnetoresistance (PLMR), and the planar Hall effect (PHE). Second, ultra-low-temperature resistivity exhibits pronounced non-Fermi-liquid (NFL) behavior, accompanied by the emergence of giant intrinsic anomalous Hall conductivity (AHC), in excellent agreement with our DFT calculations, which confirm the existence of tilted Weyl points arising from crossings of nearly three-dimensional (3D) flat bands. Most remarkably, we detect an exceptionally robust flat magnetoresistance (flat-MR) that persists without decay up to 33 T. This set of phenomena provides strong evidence that the Fermi level intersects the flattened Weyl crossings, offering confirmation of a topological flat-band semimetal. D0_3-Fe_3Ga presents a promising magnetic platform for quantum device innovations.

cond-mat.mtrl-sci↗

arXiv2026

Fragile topology for six-fold rotation symmetry indicated by the concentric Wilson loop spectrum

We investigate topological phase transitions for the Haldane and Kane-Mele model in a lattice with $p6$ symmetry, which consists of triangles and hexagons arranged in a two-dimensional geometry. For the Haldane model, which breaks time-reversal symmetry, we calculate the Chern number using a multi-band non-Abelian Wilson loop formalism. By varying the hopping parameters in the triangles and hexagons independently, a large variety of topological phases emerge. In the presence of a next-next-nearest neighbor hopping, the phase diagram becomes even richer, with regions exhibiting high Chern numbers. Then, we consider the Kane-Mele model, for which time-reversal symmetry is preserved, and calculate the number of $\pi$-crossings in the Concentric Wilson Loop Spectrum (CWLS). This method is appropriate to determine the topological invariant for systems hosting time-reversal and rotational symmetry, but lacking all other symmetries. According to a classification based on $K$-theory, the CWLS invariant reveals topological properties even when more conventional invariants fail to detect them. The formalism was previously successfully applied to systems with 3- and 4-fold symmetry. Here, we surprisingly find that for the 6-fold-symmetry model investigated, the topology identified by this invariant is fragile, therefore questioning the claim that this should be the strong invariant missing in a complete classification of topological insulators.

cond-mat.mes-hall↗

arXiv2026

Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models

As large language models (LLMs) continue to advance, there is increasing interest in their ability to infer human mental states and demonstrate a human-like Theory of Mind (ToM). Most existing ToM evaluations, however, are centered on text-based inputs, while scenarios relying solely on visual information receive far less attention. This leaves a gap, since real-world human-AI interaction typically requires multimodal understanding. In addition, many current methods regard the model as a black box and rarely probe how its internal attention behaves in multiple-choice question answering (QA). The impact of LLM hallucinations on such tasks is also underexplored from an interpretability perspective. To address these issues, we introduce VisionToM, a vision-oriented intervention framework designed to strengthen task-aware reasoning. The core idea is to compute intervention vectors that align visual representations with the correct semantic targets, thereby steering the model's attention through different layers of visual features. This guidance reduces the model's reliance on spurious linguistic priors, leading to more reliable multimodal language model (MLLM) outputs and better QA performance. Experiments on the EgoToM benchmark-an egocentric, real-world video dataset for ToM with three multiple-choice QA settings-demonstrate that our method substantially improves the ToM abilities of MLLMs. Furthermore, results on an additional open-ended generation task show that VisionToM enables MLLMs to produce free-form explanations that more accurately capture agents' mental states, pushing machine-human collaboration toward greater alignment.

cs.CV↗

arXiv2026

CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. To overcome these limitations, we introduce CustomTex, a novel framework for instance-level, high-fidelity scene texturing driven by reference images. CustomTex takes an untextured 3D scene and a set of reference images specifying the desired appearance for each object instance, and generates a unified, high-resolution texture map. The core of our method is a dual-distillation approach that separates semantic control from pixel-level enhancement. We employ semantic-level distillation, equipped with an instance cross-attention, to ensure semantic plausibility and ``reference-instance'' alignment, and pixel-level distillation to enforce high visual fidelity. Both are unified within a Variational Score Distillation (VSD) optimization framework. Experiments demonstrate that CustomTex achieves precise instance-level consistency with reference images and produces textures with superior sharpness, reduced artifacts, and minimal baked-in shading compared to state-of-the-art methods. Our work establishes a more direct and user-friendly path to high-quality, customizable 3D scene appearance editing.

cs.CV↗

arXiv2026

Indirect and Direct Multiuser Hybrid Beamforming for Far-Field and Near-Field Communications: A Deep Learning Approach

Hybrid beamforming for extremely large-scale multiple-input multiple-output (XL-MIMO) systems is challenging in the near field because the channel depends jointly on angle and distance, and the multiuser interference (MUI) is strong. Existing deep learning methods typically follow either a decoupled design that optimizes analog beamforming without explicitly accounting for MUI, or an end-to-end (E2E) joint analog-digital optimization that can be unstable under nonconvex constant-modulus (CM), pronounced analog-digital coupling, and gradient pattern of sum-rate loss. To address both issues, we develop a complex-valued E2E framework based on a variant minimum mean square error (variant-MMSE) criterion, where the digital precoder is eliminated in closed form via Karush-Kuhn-Tucker (KKT) conditions so that analog learning is trained with a stable objective. The network employs a grouped complex-convolution sensing front-end for uplink (UL) measurements, a shared complex multi-layer perceptron (MLP) for per-user feature extraction, and a merged constant-modulus head to output the analog precoder. In the indirect mode, the network designs hybrid beamformers from estimated channel state information (CSI). In the direct mode where explicit CSI is unavailable, the network learns the sensing operator and the analog mapping from short pilots, after which additional pilots estimate the equivalent channel and enable a KKT closed-form digital precoder. Simulations show that the indirect mode approaches the performance of iterative variant-MMSE optimization with a complexity reduction proportional to the antenna number. In the direct mode, the proposed method improves spectral efficiency over sparse-recovery pipelines and recent deep learning baselines under the same pilot budget.

eess.SP↗

arXiv2026

Near-Field Multiuser Beam Training for XL-MIMO: An End-to-End Interference-Aware Approach with Pilot Limitations

Near-field propagation in extremely large-scale MIMO (XL-MIMO) enlarges the beam training (BT) search space by introducing an additional range dimension, which makes conventional codebook-based beam sweeping prohibitively expensive under limited pilot resources, especially for multiuser sub-connected hybrid architectures. This letter proposes a deep-learning-based interference-aware multiuser BT framework (DL-IABT) that directly predicts analog beam indices from a small number of uplink sensing measurements. By exploiting a subarray-level approximation, a far-field codebook is adopted to represent each subarray response with negligible mismatch. To enable end-to-end (E2E) learning, we derive a variant-MSE surrogate loss by eliminating the digital precoder through a closed-form MMSE solution from KKT conditions, which implicitly accounts for multiuser interference (MUI). The proposed network integrates a complex-valued sensing front-end, a shared complex-valued encoder, a Transformer-based multiuser predictor, and a scalable Gumbel--Softmax beam selection head. Simulation results show that DL-IABT achieves near-optimal sum-rate performance while providing markedly higher effective throughput under pilot overhead constraints.

eess.SP↗

arXiv2026

Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising

The detection limit of astronomical imaging observations is limited by several noise sources. Some of that noise is correlated between neighbouring image pixels and exposures, so in principle could be learned and corrected. We present an astronomical self-supervised transformer-based denoising algorithm (ASTERIS), that integrates spatiotemporal information across multiple exposures. Benchmarking on mock data indicates that ASTERIS improves detection limits by 1.0 magnitude at 90% completeness and purity, while preserving the point spread function and photometric accuracy. Observational validation using data from the James Webb Space Telescope (JWST) and Subaru telescope identifies previously undetectable features, including low-surface-brightness galaxy structures and gravitationally-lensed arcs. Applied to deep JWST images, ASTERIS identifies three times more redshift > 9 galaxy candidates, with rest-frame ultraviolet luminosity 1.0 magnitude fainter, than previous methods.

astro-ph.IM↗

arXiv2026

VR Calm Plus: Coupling a Squeezable Tangible Interaction with Immersive VR for Stress Regulation

While Virtual Reality (VR) is increasingly employed for stress management, most applications rely heavily on audio-visual stimuli and overlook the therapeutic potential of squeezing engagement. To address this gap, we introduce VR Calm Plus, a multimodal system that integrates a pressure-sensitive plush toy into an interactive VR environment. This interface allows users to dynamically modulate the virtual atmosphere through physical squeezing actions, fostering a deeper sense of embodied relaxation. We evaluated the system with 40 participants using PANAS-X surveys, subjective questionnaires, physiological measures (heart rate, skin conductance, pulse rate variability), and semi-structured interviews. Results demonstrate that, compared to a visual-only baseline, squeeze-based interaction significantly enhances positive affect and perceived relaxation. Physiological data further revealed a state of "active relaxation", characterized by greater reductions in heart rate and preserved autonomic flexibility (PRV), alongside sustained emotional engagement (GSR). Our findings highlight the value of coupling tangible input with immersive environments to support emotional well-being and offer design insights for future VR-based mental health tools.

cs.HC↗

arXiv2025

Real-Time Multi-Target Detection and Tracking with mmWave 5G NR Waveforms on RFSoC

We demonstrate a real-time implementation of multi-target detection and tracking using 5G New Radio (NR) physical downlink shared channel (PDSCH) waveform with 400 MHz bandwidth at 28 GHz carrier frequency. The hardware platform is built on a radio frequency system-on-chip (RFSoC) 4x2 board connected with a pair of Sivers EVK02001 mmWave beamformers for transmission and reception. The entire sensing transceiver processing and fast beam control are realized purely in the programmable logic (PL) part of the RFSoC, enabling low-latency and fully hardware-accelerated operation. The continuously acquired sensing data constitute 3D range-angle (RA) tensors, which are processed on a host PC using adaptive background subtraction, cell-averaging constant false alarm rate (CA-CFAR) detection with density-based spatial clustering of applications with noise (DBSCAN) clustering, and extended Kalman filtering (EKF), to detect and track targets in the environment. Our software-defined radio (SDR) testbed integrates heterogeneous computing resources, including CPUs, GPUs, and FPGAs, thereby providing design flexibility for a wide range of tasks.

eess.SP↗

arXiv2025

Supercritical-subcritical correspondence, asymmetric effects and antisymmetric corrections near a critical point

The second-order phase transitions in the Ising model and liquid-gas systems share a universality class and critical exponents, despite the absence of $Z_2$ symmetry in the liquid-gas Hamiltonian. This discrepancy highlights a central puzzle in critical phenomena: what is the influence of asymmetry on scaling laws? For over a century, this question has been explored through examining violations of the empirical ``rectilinear diameter law'' for the subcritical coexistence curve, where asymmetry could generate singular corrections. Here, we extend this investigation to the supercritical regime. We propose a supercritical-subcritical correspondence, drawing a formal analogy between the subcritical coexistence curve and recently defined supercritical boundary lines ($L^\pm$ lines). Our theory predicts that the linear mixing of physical fields - a hallmark of asymmetric systems - produces universal scaling corrections, with antisymmetric coefficients, in these supercritical loci. We verify these predictions using liquid-gas data from the NIST database and a model liquid-liquid transition. Furthermore, we demonstrate that the same asymmetric scaling framework governs the behavior of higher-order cumulants in the order parameter distribution.

cond-mat.stat-mech↗

arXiv2025

FlashWorld: High-quality 3D Scene Generation within Seconds

We propose FlashWorld, a generative model that produces 3D scenes from a single image or text prompt in seconds, 10~100$\times$ faster than previous works while possessing superior rendering quality. Our approach shifts from the conventional multi-view-oriented (MV-oriented) paradigm, which generates multi-view images for subsequent 3D reconstruction, to a 3D-oriented approach where the model directly produces 3D Gaussian representations during multi-view generation. While ensuring 3D consistency, 3D-oriented method typically suffers poor visual quality. FlashWorld includes a dual-mode pre-training phase followed by a cross-mode post-training phase, effectively integrating the strengths of both paradigms. Specifically, leveraging the prior from a video diffusion model, we first pre-train a dual-mode multi-view diffusion model, which jointly supports MV-oriented and 3D-oriented generation modes. To bridge the quality gap in 3D-oriented generation, we further propose a cross-mode post-training distillation by matching distribution from consistent 3D-oriented mode to high-quality MV-oriented mode. This not only enhances visual quality while maintaining 3D consistency, but also reduces the required denoising steps for inference. Also, we propose a strategy to leverage massive single-view images and text prompts during this process to enhance the model's generalization to out-of-distribution inputs. Extensive experiments demonstrate the superiority and efficiency of our method.

cs.CV↗

arXiv2025

Variational Secret Common Randomness Extraction

This paper studies the problem of extracting common randomness (CR) or secret keys from correlated random sources observed by two legitimate parties, Alice and Bob, through public discussion in the presence of an eavesdropper, Eve. We propose a practical two-stage CR extraction framework. In the first stage, the variational probabilistic quantization (VPQ) step is introduced, where Alice and Bob employ probabilistic neural network (NN) encoders to map their observations into discrete, nearly uniform random variables (RVs) with high agreement probability while minimizing information leakage to Eve. This is realized through a variational learning objective combined with adversarial training. In the second stage, a secure sketch using code-offset construction reconciles the encoder outputs into identical secret keys, whose secrecy is guaranteed by the VPQ objective. As a representative application, we study physical layer key (PLK) generation. Beyond the traditional methods, which rely on the channel reciprocity principle and require two-way channel probing, thus suffering from large protocol overhead and being unsuitable in high mobility scenarios, we propose a sensing-based PLK generation method for integrated sensing and communications (ISAC) systems, where paired range-angle (RA) maps measured at Alice and Bob serve as correlated sources. The idea is verified through both end-to-end simulations and real-world software-defined radio (SDR) measurements, including scenarios where Eve has partial knowledge about Bob's position. The results demonstrate the feasibility and convincing performance of both the proposed CR extraction framework and sensing-based PLK generation method.

cs.IT↗

arXiv2025

JCo-MVTON: Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-on

Virtual try-on systems have long been hindered by heavy reliance on human body masks, limited fine-grained control over garment attributes, and poor generalization to real-world, in-the-wild scenarios. In this paper, we propose JCo-MVTON (Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-On), a novel framework that overcomes these limitations by integrating diffusion-based image generation with multi-modal conditional fusion. Built upon a Multi-Modal Diffusion Transformer (MM-DiT) backbone, our approach directly incorporates diverse control signals -- such as the reference person image and the target garment image -- into the denoising process through dedicated conditional pathways that fuse features within the self-attention layers. This fusion is further enhanced with refined positional encodings and attention masks, enabling precise spatial alignment and improved garment-person integration. To address data scarcity and quality, we introduce a bidirectional generation strategy for dataset construction: one pipeline uses a mask-based model to generate realistic reference images, while a symmetric ``Try-Off'' model, trained in a self-supervised manner, recovers the corresponding garment images. The synthesized dataset undergoes rigorous manual curation, allowing iterative improvement in visual fidelity and diversity. Experiments demonstrate that JCo-MVTON achieves state-of-the-art performance on public benchmarks including DressCode, significantly outperforming existing methods in both quantitative metrics and human evaluations. Moreover, it shows strong generalization in real-world applications, surpassing commercial systems.

cs.CV↗