arXiv subjects

Tao Zhang

Publications and source records attributed to Tao Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2026

SAMTok: Representing Any Mask with Two Words

Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and incompatible training objectives. To address these challenges, we present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens and reconstructs the mask using these tokens with high fidelity. By treating masks as new language tokens, SAMTok enables base MLLMs (such as the QwenVL series) to learn pixel-wise capabilities through standard next-token prediction and simple reinforcement learning, without architectural modifications and specialized loss design. SAMTok builds on SAM2 and is trained on 209M diverse masks using a mask encoder and residual vector quantizer to produce discrete, compact, and information-rich tokens. With 5M SAMTok-formatted mask understanding and generation data samples, QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation. We further introduce a textual answer-matching reward that enables efficient reinforcement learning for mask generation, delivering substantial improvements on GRES and GCG benchmarks. Our results demonstrate a scalable and straightforward paradigm for equipping MLLMs with strong pixel-wise capabilities. Our code and models are available.

cs.CV↗

arXiv2026

Efficient Implementation of a Single-Qutrit Gate Set via Coherent Control

Qutrits offer the potential for enhanced quantum computation by exploiting an enlarged Hilbert space. However, the synthesis of high-fidelity and fast qutrit gates, particularly for single qutrits, remains an ongoing challenge, as it involves overcoming intrinsic constraints in quantum platforms. Here, we develop a novel framework for the efficient implementation of a single-qutrit gate set via coherent control, leveraging SU(3) dynamics while obviating platform-specific constraints such as those arising from the selection rule. As a proof-of-principle demonstration, we realize 35-ns qutrit Hadamard and X gates using a superconducting transmon, achieving an average fidelity of 99.5\%, as verified by randomized benchmarking. We further demonstrate two paradigmatic quantum circuits, which can be naturally extended to scalable qudit algorithms for phase estimation and parity check. In addition, we propose an SU(3)-based decomposition strategy for an arbitrary single-qutrit gate and numerically demonstrate its substantial efficiency improvement over conventional SU(2)-based protocols. By addressing the challenge of efficiently implementing single-qutrit gates, our protocol paves the way for realizing high-performance qutrit processors in diverse quantum platforms.

quant-ph↗

arXiv2026

Experiment-compatible measurement--feedback quantum state preparation with reinforcement learning

Ground-state preparation is a critical task in quantum simulation and quantum computing, as it enables the study of correlated phases and the generation of entangled resource states. While measurement--feedback control has emerged as a promising route to state preparation, existing schemes either rely on handcrafted, task-specific policies or are designed using full quantum-state information that is unavailable in real experiments and becomes impractical for large many-body systems. Here we develop an adaptive measurement--feedback protocol based on reinforcement learning under partial observability. The controller uses only the history of experimentally accessible measurement outcomes to choose both the measurement operator and the feedback action in real time. To make training compatible with experiments, we introduce a stochastic terminal reward built from one-shot measurements of randomly sampled Hamiltonian components, avoiding unphysical full-state reconstruction while remaining an unbiased estimator of the target energy. We demonstrate the method by preparing ground states of the Bose--Hubbard model and by generating GHZ states, establishing a scalable and hardware-compatible route to quantum state preparation.

quant-ph↗

arXiv2026

Lie triple 2-algebras

We invent a new cohomology theory for Lie triple algebras. Using this cohomology, we introduce the notions of 2-term $L_\infty$-triple algebras and Lie triple 2-algebras. We prove that the category of 2-term $L_\infty$-triple algebras is equivalent to the category of Lie triple 2-algebras. Crossed modules of Lie triple algebras are studied in detail.

math.RA↗

arXiv2026

High-Quality Entity Segmentation and Grounding

In this work, we propose ESG, a pipeline for high-quality entity segmentation and grounding supported by a new dataset EntitySeg. At first, the proposed dataset naming EntitySeg contains images spanning various image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Then, the ESG mainly consists of two modules: CropFormer for high-quality entity segmentation whereas GELLA for accurate noun extraction from sentences and semantic matching between language and visual regions. Unlike existing grounding methods that jointly train a segmentation and a large language model, ESG adopts a two-stage decoupled design, preserving high-quality masks and grounding robustness without the trade-offs often introduced by joint training. CropFormer ensures high-quality entity segmentation results, which can then be encoded into the GELLA model for effective grounding. Extensive experimental results demonstrate the effectiveness of our proposed pipeline across five tasks, including entity segmentation, panoptic segmentation, open-vocabulary segmentation, referring segmentation, and panoptic localized narratives. Furthermore, GELLA module of ESG pipeline is highly flexible and capable of processing mask inputs from any segmentation framework, thanks to its lightweight colormap/vision encoder, language/mask decoder, and association module. The entity segmentation dataset and grounding code will be released at https://github.com/qqlu/Entity.

cs.CV↗

arXiv2026

Trapping 11,000 Atoms in a Tweezer Array Generated by a Single Metasurface

The scalability of physical qubit numbers is a central challenge toward a universal fault-tolerant quantum computer. The inherent scalability of atom array quantum computers stems from the identical nature of atomic qubits, so the available qubit resource is primarily limited by the number of atoms that can be trapped and controlled. Here, we robustly trap 11,000 individual atoms in a tweezer array, thereby enabling the available qubit resource to reach the tens-of-thousands scale for the first time among all quantum computation platforms. This advance is enabled by a single metasurface, approximately 2 cm in diameter, that generates the entire tweezer array without the need for microscope objectives, thereby maximizing laser-power efficiency. The large aperture ensures a working distance of about 1.5 cm, allowing the metasurface to be placed outside the vacuum cell and avoiding the technical complications of in-vacuum operation. We further characterize the randomly loaded atom array using the statistical theory of percolation phase transitions. This work takes an important first step toward a quantum computer at the 10,000-qubit scale.

quant-ph↗

arXiv2026

Unified Flux Control Architecture for Fluxonium Qubits

Control architectures that reduce hardware overhead while maintaining high-fidelity operations are essential for the continued scaling of superconducting quantum processors. Here we experimentally realize a unified control architecture for fluxonium qubits, in which both transverse ($XY$) and longitudinal ($Z$) operations are implemented through a single flux-control channel driven by a single arbitrary waveform generator channel. This architecture imposes competing requirements on the shared control channel, which must simultaneously support low-frequency flux transmission for reset operations while strongly attenuating broadband noise near the qubit transition frequency. We address this challenge through frequency-selective cryogenic filtering together with compensated waveform synthesis that corrects the pulse distortion introduced by the filtered control line. Experimentally, this approach preserves coherence times above 100 $μ$s while enabling active reset with approximately 98% fidelity and 20-ns single-qubit gates with fidelities exceeding 99.99%. We further demonstrate FPGA-native instruction-level waveform synthesis based on reusable pulse primitives for unified flux control. These results establish unified flux control as a scalable architecture for fluxonium qubits that reduces control hardware overhead while preserving high-fidelity operation.

quant-ph↗

arXiv2026

Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection

Time series anomaly detection (TSAD) has long been a hot research topic in data mining due to its various applications. Recent studies challenge the effectiveness of popular deep learning methods for TSAD, suggesting their failure in detecting subtle and prolonged anomalies. Outlier Exposure (OE) and Masked Autoencoder (MAE) emerge as two promising paradigms (classification and reconstruction) for solving the above problems. However, OE-based methods are constrained by poor generalization, while MAE-based methods are limited by masking misalignment issues. To address these limitations, this paper proposes a novel framework, CoAD, which unifies the two paradigms to leverage their complementary strengths while mitigating their respective weaknesses. In this framework, the classification module generates probability-informed soft masks for the reconstruction module, which in turn alleviates the generalization problem of the classification module. This cooperative design enables CoAD to effectively detect subtle and complex anomalies that are often overlooked by existing methods. Additionally, the classification module is carefully designed to resolve issues related to improper classification granularity and the neglect of frequency information. Extensive experiments on high-quality benchmark datasets, conducted under rigorous evaluation protocols, demonstrate that CoAD significantly outperforms both state-of-the-art deep learning and traditional data mining methods, highlighting the potential of deep learning in TSAD. Moreover, CoAD is lightweight and substantially faster than existing SOTA methods, demonstrating its practical value for large-scale, real-time applications.

cs.LG↗

arXiv2026

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets

Semantic identifiers (SIDs) have gained increasing attention in generative retrieval (GR) for recommendation due to their meaningful semantic discriminability. However, current studies in this field primarily (1) offer limited investigation into the construction strategies for better SIDs, and (2) their SID assessment typically relies on costly GR training. To address these challenges, we propose FORGE, a comprehensive benchmark for FOrming semantic identifieRs for Generative rEtrieval. Specifically, FORGE provides a taxonomy of the SID construction process from several perspectives and validates their impact on downstream GR through offline experiments across diverse settings. Notably, these empirical findings have led to a 0.35% increase in transaction count via online A/B experiments in the Guess You Like section of Taobao. The corresponding SID construction strategies have since been deployed at full scale on Taobao, demonstrating their practical effectiveness. To avoid expensive SID assessment that requires full GR training, we propose two novel SID evaluation metrics that are highly correlated with recommendation performance, enabling convenient evaluations without any GR training. Furthermore, to facilitate the community, we release AL-GR, the industrial dataset used in our experiments, comprising 14 billion interactions and 250 million items with the corresponding multimodal features collected from Taobao. All the code and data are available at https://github.com/selous123/al_sid.

cs.IR↗

arXiv2026

Two new super integrable hierarchies and a generalized super-AKNS hierarchy

In this paper, we investigate two non-isospectral problems on the loop algebra of the Lie superalgebra osp(1,6), and construct two super-integrable systems and their super Hamiltonian structure using the supertrace identity. The resulting super-integrable system can be reduced to the super-AKNS hierarchy under certain conditions. By reconsidering a new (2 + 1)-dimensional non-isospectral problem with spectral matrices satisfying these conditions, we obtain a (2 + 1)-dimensional generalization of the super-AKNS hierarchy.

nlin.SI↗

arXiv2026

Additive structures imply more distances in $\mathbb{F}_q^d$

For a set $E \subseteq \mathbb{F}_q^d$, the distance set is defined as $Δ(E) := \{\|\mathbf{x} - \mathbf{y}\| : \mathbf{x}, \mathbf{y} \in E\}$, where $\|\cdot\|$ denotes the standard quadratic form. We investigate the Erdős--Falconer distance problem within the flexible class of $(u, s)$--Salem sets introduced by Jonathan M. Fraser, with emphasis on the even case $u = 4$. By exploiting the exact identity between $\|\widehat{E}\|_4$ and the fourth additive energy $Λ_4(E)$, we prove that quantitative gains in $Λ_4(E)$ force the existence of many distances. In particular, for a $(4, s)$--Salem set $E\subset \mathbb{F}_q^d$ with $d \geq 2$, if \[ |E|\gg q^{\min\left\{\frac{d+2}{4s+1}, \frac{d+4}{8s}\right\}}, \] then $E$ determines a positive proportion of all distances. This strictly improves Fraser's threshold of $\frac{d}{4s}$ and the Iosevich-Rudnev bound of $q^{\frac{d+1}{2}}$ in certain parameter ranges. As applications, we obtain improved thresholds for multiplicative subgroups and sets on arbitrary varieties, and establish a sharp incidence bound for Salem sets that is of independent interest in incidence geometry. Moreover, our methods give sharp lower bounds for the number of distinct distances determined by two different sets. We also propose a unified conjecture for $(4, s)$--Salem sets that reconciles known bounds and pinpoints the odd-dimensional sphere regime: in odd dimensions $d \geq 3$, the often-cited $\frac{d-1}{2}$ threshold does not follow without additional structures. This provides a clear picture of the spherical distance conjecture.

math.CO↗

arXiv2026

Super integrable hierarchies associated with color Lie algebra

In this paper, by considering two non-isospectral problems with matrices chosen on the color Lie algebra $\mathfrak{sp}_{1}(6)$, we construct (1+1)-dimensional and (2+1)-dimensional super integrable systems on $\mathfrak{sp}_{1}(6)$. Moreover, based on the supertrace identity, their super Hamiltonian structures are also constructed.

nlin.SI↗

arXiv2026

A High-Contrast Bragg Atom Interferometer for Testing Continuous Spontaneous Localization

The continuous spontaneous localization (CSL) model is one of the most promising approaches to address the wave function collapse problem in the measurement process of standard quantum mechanics. In this work, the effect of the CSL model on a Bragg atom interferometer was investigated. A Bragg interferometer achieving high fringe contrast of 99$\%$ has been demonstrated, maintaining this performance level at interrogation time up to $T=60~\mathrm{ms}$. The primary factors responsible for fringe contrast loss in the atom interferometer were systematically analyzed and corrected. This improvement established a new upper limit of $λ_{\rm CSL}=1.27\times10^{-5}~\mathrm{s}^{-1}$ at $r_C=10^{-5}~\mathrm{m}$ for the CSL collapse rate, representing approximately 4 times enhancement over previous atom-interferometric constraints.

physics.atom-ph↗

arXiv2026

AI-Enabled Decoding of Qubit Loss for Quantum Error-Correcting Codes

Qubit loss is a major source of error in quantum computation, as it invalidates the algebraic structure of the standard stabilizer formalism for quantum error-correcting codes. On the one hand, it complicates decoding; on the other hand, it introduces stochastic flicker patterns in stabilizers as a hallmark of qubit loss. Here, we develop an artificial-intelligence-enabled decoder based on a spatiotemporal Graph Neural Network (STGNN) architecture to extract spatial and temporal correlations from syndrome histories. Our decoder performs a dual-head task, simultaneously correcting standard Pauli errors and identifying the locations of qubit loss. Our decoder achieves significantly higher logical accuracy than both the traditional minimum-weight perfect matching (MWPM) algorithm and even delayed-erasure MWPM decoders that use qubit loss information from the final round as input. Our decoder can also identify more than 90% of loss locations after accumulating stabilizer measurements over the subsequent ten rounds, thereby facilitating qubit reinitialization, for instance, via the continuous loading technique on the atom array platform. For both tasks, our STGNN performs nearly identically to a modified version of AlphaQubit, but it employs a parallel input structure, giving it an advantage in inference time over modified AlphaQubit's recurrent input structure. This work provides a robust and scalable framework for correcting qubit loss errors, paving the way for more efficient fault-tolerant quantum computation.

quant-ph↗

arXiv2026

Probing scalar-neutrino and scalar-dark-matter interactions with PandaX-4T

Scalar-mediated interactions may exist among neutrinos, dark matter particles, or between the two. Double $β$-decay experiments provide a powerful tool to probe such exotic interactions. Using $^{136}$Xe double $β$-decay data from PandaX-4T, we perform the first direct spectral search in the energy range of 20 to 2800~keV, setting the most stringent limits to date on scalar-mediated neutrino self-interactions for mediator masses below 2~MeV$/c^2$. These results place significant constraints on models invoking such interactions to alleviate the Hubble Tension. Assuming the same scalar also mediates dark matter self-interactions, constraints on the dark matter-scalar interactions can be placed in conjunction with cosmological constraints.

hep-ex↗

arXiv2026

FUSE: A Framework for Unified State Estimation in Vehicular and Robotic SLAM Systems

Tightly coupled SLAM formulations under mixed-rate sensing often bind temporal processing, local geometric association, estimator formulation, and map-update policy into method-specific designs. Such binding makes it difficult to vary one design choice without re-engineering the rest of the state-estimation process. This paper presents FUSE, a framework for unified state estimation in vehicular and robotic SLAM systems. FUSE organizes the state-estimation interface around observation ingestion, propagation, update, and state query, and uses this interface to separate temporal processing, residual-ready local geometric association, estimator formulation, and map-update policy. A LiDAR--IMU instantiation is developed to examine the framework under mixed-rate sensing and directional degeneracy, where high-rate inertial propagation, LiDAR-triggered geometric update, residual screening, and degeneracy-aware correction operate through the same interface boundaries. On a 418~m loop-corridor sequence, the instantiation reports a 1.626 m end-to-end trajectory error, corresponding to a 7.9% relative error reduction compared with Faster-LIO, the lowest-error baseline on this sequence. The results support FUSE as a framework for organizing state-estimation design choices and show how the evaluated instantiation regularizes updates along weakly observable directions.

cs.RO↗

arXiv2026

Randomized interventional effects in semicompeting risks, with application to a hematopoietic cell transplantation study

In clinical studies, the risk of the primary (terminal) event may be modified by intermediate events, resulting in semicompeting risks. To study the treatment effect on the terminal event mediated by the intermediate event, researchers wish to decompose the total effect into direct and indirect effects. In this article, we extend the randomized interventional approach to time-to-event outcomes, where both intermediate and terminal events are subject to right censoring. We envision a random draw for the intermediate event process from a reference distribution, either marginally over time-varying confounders or conditionally given the observed history. We present the identification formula for interventional effects. We also discuss some variants of the identification assumptions. We estimate the treatment effects using nonparametric maximum likelihood estimation and propose a sensitivity analysis that incorporates a latent frailty. As an illustration, we study the effect of matched unrelated donor versus haploidentical donor on death mediated by relapse in a hematopoietic cell transplantation study with graft-versus-host disease (GVHD) as the time-varying confounder. We find that matched unrelated donor transplantation is preferable in terms of survival rates under the use of post-transplant PTCy GVHD prophylaxis for lymphoma patients.

stat.ME↗

arXiv2026

Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search

Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to streamline downstream reasoning. However, existing pruning methods typically rely on sequential revisions driven by unreliable critique signals, often failing to detect the loss of answer-critical data. To address this limitation, we propose TabTrim, a novel table pruning framework which transforms table pruning from sequential revisions to gold trajectory-supervised parallel search. TabTrim derives a gold pruning trajectory using the intermediate sub-tables in the execution process of gold SQL queries, and trains a pruner and a verifier to make the step-wise pruning result align with the gold pruning trajectory. During inference, TabTrim performs parallel search to explore multiple candidate pruning trajectories and identify the optimal sub-table. Extensive experiments demonstrate that TabTrim achieves state-of-the-art performance across diverse tabular reasoning tasks: TabTrim-8B reaches 73.5% average accuracy, outperforming the strongest baseline by 3.2%, including 79.4% on WikiTQ and 61.2% on TableBench.

cs.CL↗