Searcharxiv⌕ Search

arXiv subjects

Tao Xiang

Publications and source records attributed to Tao Xiang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories

Recovering camera parameters from images and rendering scenes from novel viewpoints have been treated as separate tasks in computer vision and graphics. This separation breaks down when image coverage is sparse or poses are ambiguous, since each task depends on what the other produces. We propose Rays as Pixels, a Video Diffusion Model (VDM) that learns a joint distribution over videos and camera trajectories. To our knowledge, this is the first model to predict camera poses and do camera-controlled video generation within a single framework. We represent each camera as dense ray pixels (raxels), a pixel-aligned encoding that lives in the same latent space as video frames, and denoise the two jointly through a Decoupled Self-Cross Attention mechanism. A single trained model handles three tasks: predicting camera trajectories from video, generating video from input images along a pre-defined trajectory, and jointly synthesizing video and trajectory from input images. We evaluate on pose estimation and camera-controlled video generation, and introduce a closed-loop self-consistency test showing that the model's predicted poses and its renderings conditioned on those poses agree. Ablations against Plücker embeddings confirm that representing cameras in a shared latent space with video is subtantially more effective.

cs.CV↗
arXiv2026

Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation

Understanding and generating the fine-grained structure of objects -- such as birds with species-specific beaks, wings, and tails -- is a long-standing challenge in computer vision. We propose Chirpy3D, a part-aware multi-view diffusion framework that learns a hierarchical part latent space from unposed 2D images, using only off-the-shelf 2D part segmentation masks as spatial guidance -- without requiring any 3D data, camera poses, or manual part annotations. This latent space enables intuitive part-level swapping, interpolation, and zero-shot composition. A self-supervised feature consistency loss further encourages structural alignment across views, allowing coherent generation even with hybrid or unseen part combinations. Our core contribution is the controllable part-aware latent space and multi-view diffusion model. Downstream 3D generation is supported via any differentiable renderer such as NeRF but is orthogonal to the main framework, making Chirpy3D a flexible foundation for creative object generation in the absence of structured 3D data. Code is released at https://github.com/kamwoh/chirpy3d.

cs.CV↗
arXiv2026

Tree tensor network impurity solver based on Cayley-tree mapping

We introduce a tree tensor network (TTN) impurity solver that enables highly efficient and accurate real-time simulations of quantum impurity models. By decomposing a noninteracting bath Hamiltonian into a Cayley tree, the method provides a tensor network representation that naturally captures the multiscale entanglement structure intrinsic to impurity-bath systems. This geometry differs from conventional chain-based mappings and yields a substantial reduction of entanglement, allowing accurate ground-state properties and long-time dynamics to be captured at significantly lower bond dimensions. Benchmark calculations for the single-impurity Anderson model demonstrate that the TTN solver achieves markedly enhanced resolution of real-frequency spectral functions, without invoking analytic continuation. This impurity solver provides a balanced, scale-uniform description of impurity physics and offers a versatile approach for real-time dynamical mean-field theory and related applications involving quantum impurity models.

cond-mat.str-el↗
arXiv2026

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the representation encoder. Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception. These results show that pretrained vision encoders are not necessary for multimodal modelling, and end-to-end pixel-space learning offers a scalable path toward stronger visual representations for both generation and perception.

cs.CV↗
arXiv2026

Shear-stress-constrained superconductivity in Ruddlesden-Popper nickelates

Ruddlesden-Popper nickelates exhibit superconductivity under pressure in bulk crystals and under epitaxial constraint in thin films, while remaining highly sensitive to sample quality, oxygen content, defects, and stress conditions. We propose that the metastable RP lattice becomes superconducting only when the local constrained deformation of the Ni-O framework falls within a bounded shear-strain window. This deformation controls octahedral rotations, the interlayer Ni-O-Ni bond angle, and coupling between Ni dz2 and dx2-y2 orbitals. This shear-stress-constrained superconductivity scenario unifies the understanding of the pressure threshold, reversibility, spatial inhomogeneity, pressure-medium dependence, film-substrate sensitivity, and reproducibility.

cond-mat.supr-con↗
arXiv2026

Model Forensics in AI-Native Wireless Networks: Taxonomy, Applications, and Case Study

As artificial intelligence (AI) is increasingly embedded in wireless networks, models are becoming core components that influence signal processing, resource scheduling and network control. However, model anomalies, tampering and malicious functions also introduce new security risks. In this article, we focus on model forensics in AI-native wireless networks. Specifically, we first discuss key problems including model authenticity verification, malicious function identification and accountability tracing, and summarize the main categories of model forensics. We then explain the role of model forensics in AI-native wireless networks and review representative application scenarios. In the case study, we use RF fingerprinting as an example and present two concrete workflows based on watermark authentication and backdoor detection, illustrating how provenance authentication and malicious behavior identification can be implemented in practice. The results show that model forensics can provide important support for anomaly assessment, provenance tracing and trustworthy operation in AI-native wireless networks. Finally, we outline several promising directions for future research in this emerging area.

cs.CR↗
arXiv2026

Efficient simulation of low-entanglement bosonic Gaussian states in polynomial time

Bosonic Gaussian states are ubiquitous in quantum optics and condensed matter physics. While they are efficiently handled within the Gaussian formalism, sampling requires calculating amplitudes in the boson occupation basis. This step, however, is hindered by a significant bottleneck due to the hafnian. We present an efficient algorithm that converts pure bosonic Gaussian states into matrix product states (MPSs), thereby establishing a versatile tool for probing bosonic Gaussian systems in settings where direct Gaussian-formalism-based calculations become inefficient. Our method combines a Gaussian singular value decomposition with a projected-creation-operator mapping that constructs local MPS tensors without computing hafnians. Benchmarking on covariance matrices from the Jiuzhang 2.0 and Jiuzhang 4.0 Gaussian boson sampling experiments demonstrates substantial speedups over previous tensor-network approaches in the low-entanglement regime relevant to lossy devices. The method provides a scalable classical simulation framework for bosonic Gaussian states with limited entanglement. In this regime, a target accuracy can be achieved with a bond dimension that remains computationally tractable, thereby extending the applicability of MPS-based methods to a broad range of bosonic systems.

quant-ph↗
arXiv2026

Scaling Sequence-to-Sequence Generative Neural Rendering

We present Kaleido, a family of generative models designed for photorealistic, unified object- and scene-level neural rendering. Kaleido operates on the principle that 3D can be regarded as a specialised sub-domain of video, expressed purely as a sequence-to-sequence image synthesis task. Through a systemic study of scaling sequence-to-sequence generative neural rendering, we introduce key architectural innovations that enable our model to: i) perform generative view synthesis without explicit 3D representations; ii) generate any number of 6-DoF target views conditioned on any number of reference views via a masked autoregressive framework; and iii) seamlessly unify 3D and video modelling within a single decoder-only rectified flow transformer. Within this unified framework, Kaleido leverages large-scale video data for pre-training, which significantly improves spatial consistency and reduces reliance on scarce, camera-labelled 3D datasets -- all without any architectural modifications. Kaleido sets a new state-of-the-art on a range of view synthesis benchmarks. Its zero-shot performance substantially outperforms other generative methods in few-view settings, and, for the first time, matches the quality of per-scene optimisation methods in many-view settings.

cs.CV↗
arXiv2026

Pareto Frontier of Neural Quantum States: Scalable, Affordable, and Accurate Convolutional Backflow for Strongly Correlated Lattice Fermions

Neural Quantum States (NQS) are now among the most accurate methods for studying strongly correlated many-fermion systems, outperforming existing many-body approaches for large systems. However, NQS calculations remain extremely resource-intensive. Here, we introduce a new Pareto frontier of efficiency and accuracy for NQS in simulating strongly correlated lattice fermions, defined by two complementary backflow-related architectures: the Sparse Convolutional Ansatz for Lattice Electrons (SCALE) (state-of-the-art efficiency) and the Accurate Convolutional ansatz for lattice Electrons (ACE) (state-of-the-art accuracy), benchmarked on the iconic Hubbard and $t-J$ models for large lattices. SCALE uses a tailored convolutional design enabling efficient local updates via low-rank determinant updates, reducing computational scaling from $O(N^4)$ to $O(N^3)$ in backflow methods and yielding a >40$\times$ practical speed-up in tests while maintaining high variational accuracy. As an application, we study the previously inaccessible 1/8-doped pure Hubbard model up to $32 \times 32$, finding no significant energy difference between horizontal and vertical filled stripe states - contrasting with half-filled stripe states when next-nearest-neighbor hoppings are included. ACE employs a deep convolutional stack to maximize expressive power, achieving unprecedented accuracy on large systems. Extensive benchmarks on Hubbard and $t-J$ models show SCALE delivers variational energies competitive with leading methods at a fraction of the cost, while ACE sets a new accuracy benchmark, surpassing recent results with only 1/6 the runtime for $16 \times 4$ systems. These new NQS approaches provide scalable, affordable, and accurate tools for exploring strongly correlated fermionic physics, such as the microscopic mechanism of unconventional superconductivity.

cond-mat.str-el↗
arXiv2026

Persistent Fermi Pockets and Robust Electron Pairing in Lightly Doped CuO$_2$ Planes of Cuprate Superconductors

High temperature superconductivity in cuprate superconductors is generally considered to be generated from doping the Mott insulators. The fundamental nature of the doped parent compounds as well as the microscopic origin of electron pairing remain critical issues in understanding the emergence of superconductivity. Here, using high-resolution spatially-resolved laser angle-resolved photoemission spectroscopy, we investigate the intrinsic electronic structures of the CuO$_2$ planes in multilayer cuprates Bi$_2$Sr$_2$Ca$_{n-1}$Cu$_n$O$_{2n+4+δ}$ (n=5$\sim$8). The inner CuO$_2$ planes are well shielded from the disorders and provide a rare and ideal platform to probe the intrinsic electronic phase diagram. We observe well-defined Fermi pockets with hole doping levels as low as 0.007, demonstrating an abrupt transition from the parent Mott insulator to a metallic state upon the introduction of an infinitesimal amount of doping. The innermost CuO$_2$ planes (IP$_0$) display gapless Fermi pockets, while the second innermost planes (IP$_1$) exhibit anisotropic superconducting gaps up to $\sim$33$\,$meV, indicative of robust electron pairing coexisting with strong antiferromagnetic order. Our findings provide a revised framework for understanding the doping-driven transitions and pairing mechanisms in cuprate superconductors.

cond-mat.supr-con↗
arXiv2026

Pairing Mechanism in Bilayer Nickelate La$_3$Ni$_2$O$_7$ Superconductors

The recent discovery of superconductivity with $T_c \approx 80$~K in bilayer nickelate La$_3$Ni$_2$O$_7$ provides a new setting in which to test the organizing principles of unconventional high-temperature superconductivity. We show that the gene principle and the collaborative Fermi-surface rule which were previously proposed to unify unconventional high temperature superconductors, extend naturally to this bilayer, multi-orbital system. We identify that there are two antiferromagnetic exchange channels that can provide the dominant pairing force: an interlayer intra-orbital nearest-neighbour exchange $J_\perp$ between $d_{z^2}$ orbitals mediated by the inner apical oxygen, and an intralayer inter-orbital nearest-neighbour exchange $J_{xz}$ between $d_{z^2}$ and $d_{x^2-y^2}$ orbitals mediated by the in-plane oxygen. Owing to the bilayer bonding--antibonding splitting and the $B_{1g}$ symmetry of the $d_{x^2-y^2}$ orbital, these two channels cooperate to produce a robust $s^\pm$ superconducting state with an internal sign reversal between mirror-even and mirror-odd Fermi-surface pockets in momentum space. Both pairing channels maximize the superconducting gap on the $β$ pocket with a form factor $(cosk_x-cosk_y)^2$ in momentum space. The result places La$_3$Ni$_2$O$_7$ within a unified framework for unconventional superconductivity while revealing a distinct electronic environment for high-$T_c$ pairing.

cond-mat.supr-con↗
arXiv2026

Intelligent Forensics in Next-Generation Mobile Networks: Evidence, Methods, and Applications

This survey examines intelligent forensics in next-generation mobile networks, arguing that future wireless security must move beyond real-time detection toward accountable post-incident reconstruction. Unlike traditional digital forensics, wireless investigations rely on short-lived, distributed, and heterogeneous evidence, including radio waveforms, channel measurements, device-side artifacts, and network telemetry, affected by calibration, timing uncertainty, privacy constraints, and adversarial manipulation. To address this limitation, this paper develops an evidence-centric framework that treats wireless measurements as first-class forensic artifacts and organizes the field through a unified taxonomy spanning physical-layer, device-layer, network-layer, and cross-layer forensics. We further systematize the forensic workflow into readiness and preservation-by-design, acquisition, correlation and analysis, and reporting and reproducibility, while comparing the complementary roles of traditional methods and artificial intelligence-assisted techniques. Subsequently, we review major application areas, including anomaly discovery, attribution, provenance and localization, authenticity verification, and timeline reconstruction. Finally, we identify key open challenges, including domain shift, resource-aware evidence capture, and the benefits and admissibility risks of generative evidence. Overall, this paper positions wireless forensics as a foundational capability for trustworthy, auditable, and reproducible security in next-generation wireless systems. Readers can understand and streamline wireless forensics processes for specific applications, such as low-altitude wireless networks, vehicular communications, and edge general intelligence.

eess.SP↗
arXiv2026

TransText: Alpha-as-RGB Representation for Transparent Text Animation

We introduce the first method, to the best of our knowledge, for adapting image-to-video models to layer-aware text (glyph) animation, a capability critical for practical dynamic visual design. Existing approaches predominantly handle the transparency-encoding (alpha channel) as an extra latent dimension appended to the RGB space, necessitating the reconstruction of the underlying RGB-centric variational autoencoder (VAE). However, given the scarcity of high-quality transparent glyph data, retraining the VAE is computationally expensive and may erode the robust semantic priors learned from massive RGB corpora, potentially leading to latent pattern mixing. To mitigate these limitations, we propose TransText, a framework based on a novel Alpha-as-RGB paradigm to jointly model appearance and transparency without modifying the pre-trained generative manifold. TransText embeds the alpha channel as an RGB-compatible visual signal through latent spatial concatenation, explicitly ensuring strict cross-modal (RGB-and-Alpha) consistency while preventing feature entanglement. Our experiments demonstrate that TransText significantly outperforms baselines, generating coherent, high-fidelity transparent animations with diverse, fine-grained effects.

cs.CV↗
arXiv2026

Disentangling Tensor Network States with Deep Neural Network

We introduce Neural Tensor Network States ($ν$TNS), a variational many-body wave-function ansatz that integrates deep neural networks with tensor-network architectures. In the $ν$TNS framework, a neural network serves as a disentangler of the wave-function, transforming the physical degrees of freedom into renormalized variables with much less entanglement. The renormalized state is then efficiently encoded by a back-flow tensor network. This construction yields a compact yet highly expressive representation of strongly correlated quantum states. Using convolutional neural networks combined with matrix product states as a concrete implementation, we obtain state-of-the-art variational energies for the spin-$1/2$ $J_1$-$J_2$ Heisenberg model on the square lattice at the highly frustrated point $J_2/J_1=0.5$, for systems up to $20\times 20$ with periodic boundary conditions. Finite-size scaling of spin, dimer, and plaquette correlations exhibits power-law decay without magnetic or valence-bond long-range order, consistent with a gapless quantum spin-liquid ground state at that point.This $ν$TNS framework is flexible and naturally extensible to other neural and tensor-network structures, offering a general platform for investigating strongly correlated quantum many-body systems.

cond-mat.str-el↗
arXiv2026

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

We introduce MoS (Mixture of States), a novel fusion paradigm for multimodal diffusion models that merges modalities using flexible, state-based interactions. The core of MoS is a learnable, token-wise router that creates denoising timestep- and input-dependent interactions between modalities' hidden states, precisely aligning token-level features with the diffusion trajectory. This router sparsely selects the top-$k$ hidden states and is trained with an $ε$-greedy strategy, efficiently selecting contextual features with minimal learnable parameters and negligible computational overhead. We validate our design with text-to-image generation (MoS-Image) and editing (MoS-Editing), which achieve state-of-the-art results. With only 3B to 5B parameters, our models match or surpass counterparts up to $4\times$ larger. These findings establish MoS as a flexible and compute-efficient paradigm for scaling multimodal diffusion models.

cs.CV↗
arXiv2026

VecGlypher: Unified Vector Glyph Generation with Language Models

Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, which limits accessibility and editability. We introduce VecGlypher, a single multimodal language model that generates high-fidelity vector glyphs directly from text descriptions or image exemplars. Given a style prompt, optional reference glyph images, and a target character, VecGlypher autoregressively emits SVG path tokens, avoiding raster intermediates and producing editable, watertight outlines in one pass. A typography-aware data and training recipe makes this possible: (i) a large-scale continuation stage on 39K noisy Envato fonts to master SVG syntax and long-horizon geometry, followed by (ii) post-training on 2.5K expert-annotated Google Fonts with descriptive tags and exemplars to align language and imagery with geometry; preprocessing normalizes coordinate frames, canonicalizes paths, de-duplicates families, and quantizes coordinates for stable long-sequence decoding. On cross-family OOD evaluation, VecGlypher substantially outperforms both general-purpose LLMs and specialized vector-font baselines for text-only generation, while image-referenced generation reaches a state-of-the-art performance, with marked gains over DeepVecFont-v2 and DualVector. Ablations show that model scale and the two-stage recipe are critical and that absolute-coordinate serialization yields the best geometry. VecGlypher lowers the barrier to font creation by letting users design with words or exemplars, and provides a scalable foundation for future multimodal design tools.

cs.CL↗
arXiv2026

Giant bubbles of Fisher zeros in the quantum XY chain

We demonstrate an alternative approach based on complex-valued inverse temperature and partition function to probe quantum phases of matter with nontrivial spectra and dynamics. It leverages thermofield dynamics (TFD) to quantitatively characterize quantum and thermal fluctuations, and exploit the correspondence between low-energy excitations and Fisher zeros. Using the quantum XY chain in an external field as a testbed, we show that the oscillatory gap behavior manifests as oscillations in the long-time dynamics of the TFD spectral form factor. We also identify giant bubbles, i.e. large-scale closed lines, of Fisher-zeros near the gapless XX limit. They provide a characteristic energy scale that seems to contradict the predictions of the low energy theory of a featureless Luttinger liquid. We identify this energy scale and relate the motion of these giant bubbles with varying external field to the transfer of spectral weight from high to low energies. The deep connection between Fisher zeros, dynamics, and excitations opens up promising avenues for understanding the unconventional gap behaviors in strongly correlated many-body systems.

cond-mat.str-el↗
arXiv2026

TensorCircuit-NG: A Universal, Composable, and Scalable Platform for Quantum Computing and Quantum Simulation

We present TensorCircuit-NG, a next-generation quantum software platform designed to bridge the gap between quantum physics, artificial intelligence, and high-performance computing. Moving beyond the scope of traditional circuit simulators, TensorCircuit-NG establishes a unified, tensor-native programming paradigm where quantum circuits, tensor networks, and neural networks fuse into a single, end-to-end differentiable computational graph. Built upon industry-standard machine learning backends (JAX, TensorFlow, PyTorch), the framework introduces comprehensive capabilities for approximate circuit simulation, analog dynamics, fermion Gaussian states, qudit systems, and scalable noise modeling. To tackle the exponential complexity of deep quantum circuits, TensorCircuit-NG implements advanced distributed computing strategies, including automated data parallelism and model-parallel tensor network slicing. We validate these capabilities on GPU clusters, demonstrating a near-linear speedup in distributed variational quantum algorithms. TensorCircuit-NG enables flagship applications, including end-to-end QML for CIFAR-100 computer vision, efficient pipelines from quantum states to neural networks via classical shadows, and differentiable optimization of tensor network states for many-body physics.

quant-ph↗