arXiv subjects

Zheng Tan

Publications and source records attributed to Zheng Tan.

18 recordsLinked to original sources

arXiv2026

NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management

An embodied kitchen assistant must do more than recognize food in isolated frames. It must track ingredient states over time and integrate visual observations with recipe and nutritional knowledge to support constraint-aware decision-making. We formalize this capability as \emph{Embodied Nutrition Management}: perceiving nutrition-relevant events, maintaining a persistent food state, and using it for knowledge-grounded planning. Existing benchmarks evaluate static food understanding or embodied cooking actions, but do not measure whether an agent can continuously update and use nutrition-relevant states in dynamic kitchens. To fill this gap, we introduce \textbf{NutriBench-Kitchen}, a benchmark containing 1,500 manually verified question--answer pairs from 160 cooking videos. It covers five task families: Ingredient Entry, Memory Management, Recipe Query, Long-Term Planning, and Short-Term Planning, spanning food-state construction, maintenance, knowledge retrieval, and decision-making across different planning horizons. Evaluations of proprietary and open-source large vision-language models reveal a substantial gap from human performance, particularly in quantitative ingredient estimation, long-term state tracking, and reasoning under interacting constraints. We further introduce \textbf{Nutri-Vgent}, a diagnostic long-video agent with separate episodic, food-state, and recipe memories. Its consistent improvements demonstrate the value of explicit state representations and structured memory for nutrition management. Together, NutriBench-Kitchen and Nutri-Vgent provide a testbed for studying persistent state tracking and knowledge-grounded reasoning in dynamic kitchens. Code is available at https://github.com/V1ol1n/NutriBench-Kitchen.

cs.CV↗

arXiv2026

Model Merging to Evolution: Parameter Space Exploration for Expert Models

Model merging integrates the capabilities of multiple expert models to create strong models for multiple tasks without additional training, thereby reducing computational resource requirements. However, existing methods operate within the convex combination space of expert models, failing to explore high-performance regions outside this space. This paper proposes the MERGEvolve framework, which unifies model merging and evolution within an evolution strategy by treating the merged model as the initialization for evolutionary exploration of the parameter space. During the merging phase, expert models act as deterministic sources to build a strong initial point. The evolution phase then explores the parameter space using random noise. Theoretical analysis shows that MERGEvolve explores regions outside the convex combination space. Extensive experiments on single-task and multi-task benchmarks demonstrate that MERGEvolve consistently achieves performance competitive with advanced model merging baselines. Ablation studies confirm that a high-quality initial point is critical for efficient exploration of the parameter space.

cs.NE↗

arXiv2026

Surrogate Modeling with Low-Rank Function Representation for Electromagnetic Simulation

High-fidelity electromagnetic (EM) simulations are indispensable for the design of microwave and wave devices, yet repeated full-wave evaluations over high-dimensional design spaces are often computationally prohibitive. While neural surrogates can amortize this cost, learning high-dimensional EM response mappings remains difficult under limited simulation budgets due to strong and heterogeneous parameter couplings. In this work, we introduce low-rank tensor function representations as a principled surrogate modeling paradigm for EM problems and provide a systematic study of representative low-rank formats, including Tucker-style low-rank tensor function representation (LRTFR) as well as neural functional tensor-train (TT) and tensor-ring (TR) baselines. Building on these insights, we propose a pairwise low-rank tensor network (PLRNet) that uses learnable pairwise interaction factors over compact coordinate-wise embeddings. Experiments on representative EM surrogate tasks demonstrate that the proposed framework achieves a more favorable overall trade-off between accuracy, robustness, and parameter efficiency, with stable optimization in high-dimensional regimes.

cs.CE↗

arXiv2026

Irreversibility of decorrelating processes: an experimental assessment in cavity QED

Entropy production quantifies the amount of irreversibility of a physical process, leading to fundamental bounds for thermodynamic quantities. It captures the inability to run a physical system forward and then backward, bringing it to the same initial state. Considerable research has been carried out in the last decades to extend entropy production to non-equilibrium quantum processes. We experimentally investigate the entropy production of such forward-backward cycles affected by genuinely quantum irreversibility. Namely, we consider processes realized to erase different types of correlations between two interacting systems, from obliterating solely quantum coherence to completely decorrelating local states. This makes the measurement of entropy production experimentally challenging. Addressing this challenge is the purpose of this paper.

quant-ph↗

arXiv2025

Explicit Monotone Stable Super-Time-Stepping Methods for Finite Time Singularities

We explore a novel way to numerically resolve the scaling behavior of finite-time singularities in solutions of nonlinear parabolic PDEs. The Runge--Kutta--Legendre (RKL) and Runge--Kutta--Gegenbauer (RKG) super-time-stepping methods were originally developed for nonlinear complex physics problems with diffusion. These are multi-stage single step second-order, forward-in-time methods with no implicit solves. The advantage is that the timestep size for stability scales with stage number $s$ as $\mathcal{O}(s^2)$. Many interesting nonlinear PDEs have finite-time singularities, and the presence of diffusion often limits one to using implicit or semi-implicit timestep methods for stability constraints. Finite-time singularities are particularly challenging due to the large range of scales that one desires to resolve, often with adaptive spatial grids and adaptive timesteps. Here we show two examples of nonlinear PDEs for which the self-similar singularity structure has time and space scales that are resolvable using the RKL and RKG methods, without forcing even smaller timesteps. Compared to commonly-used implicit numerical methods, we achieve significantly smaller run time while maintaining comparable accuracy. We also prove numerical monotonicity for both the RKL and RKG methods under their linear stability conditions for the constant coefficient heat equation, in the case of infinite domain and periodic boundary condition, leading to a theoretical guarantee of the superiority of the RKL and RKG methods over traditional super-time-stepping methods, such as the Runge-Kutta-Chebyshev (RKC) and the orthogonal Runge-Kutta-Chebyshev (ROCK) methods. Code can be found at https://github.com/ZT220501/SRK-Singularity.

math.NA↗

arXiv2025

STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence

Diffusion models (DMs) and flow-matching models have demonstrated remarkable performance in image and video generation. However, such models require a significant number of function evaluations (NFEs) during sampling, leading to costly inference. Consequently, quality-preserving fast sampling methods that require fewer NFEs have been an active area of research. However, prior training-free sampling methods fail to simultaneously address two key challenges: the stiffness of the ODE (i.e., the non-straightness of the velocity field) and dependence on the semi-linear structure of the DM ODE (which limits their direct applicability to flow-matching models). In this work, we introduce the Stabilized Taylor Orthogonal Runge--Kutta (STORK) method, addressing both design concerns. We demonstrate that STORK consistently improves the quality of diffusion and flow-matching sampling for image and video generation. Code is available at https://github.com/ZT220501/STORK.

cs.CV↗

arXiv2025

Testing Fairness with Utility Tradeoffs: A Wasserstein Projection Approach

Ensuring fairness in data driven decision making has become a central concern across domains such as marketing, lending, and healthcare, but fairness constraints often come at the cost of utility. We propose a statistical hypothesis testing framework that jointly evaluates approximate fairness and utility, relaxing strict fairness requirements while ensuring that overall utility remains above a specified threshold. Our framework builds on the strong demographic parity (SDP) criterion and incorporates a utility measure motivated by the potential outcomes framework. The test statistic is constructed via Wasserstein projections, enabling auditors to assess whether observed fairness-utility tradeoffs are intrinsic to the algorithm or attributable to randomness in the data. We show that the test is computationally tractable, interpretable, broadly applicable across machine learning models, and extendable to more general settings. We apply our approach to multiple real-world datasets, offering new insights into the fairness-utility tradeoff through the perspective of statistical hypothesis testing.

cs.CY↗

arXiv2025

Dual-Forecaster: A Multimodal Time Series Model Integrating Descriptive and Predictive Texts

Most existing single-modal time series models rely solely on numerical series, which suffer from the limitations imposed by insufficient information. Recent studies have revealed that multimodal models can address the core issue by integrating textual information. However, these models focus on either historical or future textual information, overlooking the unique contributions each plays in time series forecasting. Besides, these models fail to grasp the intricate relationships between textual and time series data, constrained by their moderate capacity for multimodal comprehension. To tackle these challenges, we propose Dual-Forecaster, a pioneering multimodal time series model that combines both descriptively historical textual information and predictive textual insights, leveraging advanced multimodal comprehension capability empowered by three well-designed cross-modality alignment techniques. Our comprehensive evaluations on fifteen multimodal time series datasets demonstrate that Dual-Forecaster is a distinctly effective multimodal time series model that outperforms or is comparable to other state-of-the-art models, highlighting the superiority of integrating textual information for time series forecasting. This work opens new avenues in the integration of textual information with numerical time series data for multimodal time series analysis.

cs.LG↗

arXiv2025

Contextual Preference Collaborative Measure Framework Based on Belief System

To reduce the human intervention in the preference measure process,this article proposes a preference collaborative measure framework based on an updated belief system,which is also capable of improving the accuracy and efficiency of preferen-ce measure algorithms.Firstly,the distance of rules and the average internal distance of rulesets are proposed for specifying the relationship between the rules.For discovering the most representative preferences that are common in all users,namely common preference,a algorithm based on average internal distance of ruleset,PRA algorithm,is proposed,which aims to finish the discoveryprocess with minimum information loss rate.Furthermore,the concept of Common belief is proposed to update the belief system,and the common preferences are the evidences of updated belief system.Then,under the belief system,the proposed belief degree and deviation degree are used to determine whether a rule confirms the belief system or not and classify the preference rules into two kinds(generalized or personalized),and eventually filters out Top-K interesting rules relying on belief degree and deviation degree.Based on above,a scalable interestingness calculation framework that can apply various formulas is proposed for accurately calculating interestingness in different conditions.At last,IMCos algorithm and IMCov algorithm are proposed as exemplars to verify the accuracy and efficiency of the framework by using weighted cosine similarity and correlation coefficients as belief degree.In experiments,the proposed algorithms are compared to two state-of-the-art algorithms and the results show that IMCos and IMCov outperform than the other two in most aspects.

cs.AI↗

arXiv2025

LeForecast: Enterprise Hybrid Forecast by Time Series Intelligence

Demand is spiking in industrial fields for multidisciplinary forecasting, where a broad spectrum of sectors needs planning and forecasts to streamline intelligent business management, such as demand forecasting, product planning, inventory optimization, etc. Specifically, these tasks expecting intelligent approaches to learn from sequentially collected historical data and then foresee most possible trend, i.e. time series forecasting. Challenge of it lies in interpreting complex business contexts and the efficiency and generalisation of modelling. With aspirations of pre-trained foundational models for such purpose, given their remarkable success of large foundation model across legions of tasks, we disseminate \leforecast{}, an enterprise intelligence platform tailored for time series tasks. It integrates advanced interpretations of time series data and multi-source information, and a three-pillar modelling engine combining a large foundation model (Le-TSFM), multimodal model and hybrid model to derive insights, predict or infer futures, and then drive optimisation across multiple sectors in enterprise operations. The framework is composed by a model pool, model profiling module, and two different fusion approaches regarding original model architectures. Experimental results verify the efficiency of our trail fusion concepts: router-based fusion network and coordination of large and small models, resulting in high costs for redundant development and maintenance of models. This work reviews deployment of LeForecast and its performance in three industrial use cases. Our comprehensive experiments indicate that LeForecast is a profound and practical platform for efficient and competitive performance. And we do hope that this work can enlighten the research and grounding of time series techniques in accelerating enterprise.

cs.LG↗

arXiv2023

Infrared Small Target Detection Using Double-Weighted Multi-Granularity Patch Tensor Model With Tensor-Train Decomposition

Infrared small target detection plays an important role in the remote sensing fields. Therefore, many detection algorithms have been proposed, in which the infrared patch-tensor (IPT) model has become a mainstream tool due to its excellent performance. However, most IPT-based methods face great challenges, such as inaccurate measure of the tensor low-rankness and poor robustness to complex scenes, which will leadto poor detection performance. In order to solve these problems, this paper proposes a novel double-weighted multi-granularity infrared patch tensor (DWMGIPT) model. First, to capture different granularity information of tensor from multiple modes, a multi-granularity infrared patch tensor (MGIPT) model is constructed by collecting nonoverlapping patches and tensor augmentation based on the tensor train (TT) decomposition. Second, to explore the latent structure of tensor more efficiently, we utilize the auto-weighted mechanism to balance the importance of information at different granularity. Then, the steering kernel (SK) is employed to extract local structure prior, which suppresses background interference such as strong edges and noise. Finally, an efficient optimization algorithm based on the alternating direction method of multipliers (ADMM) is presented to solve the model. Extensive experiments in various challenging scenes show that the proposed algorithm is robust to noise and different scenes. Compared with the other eight state-of-the-art methods, different evaluation metrics demonstrate that our method achieves better detection performance in various complex scenes.

cs.CV↗

arXiv2023

Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets

Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximally improving the underlying classifier's performance. Recent gains have been made using sequential active learning for synthetic aperture radar (SAR) data arXiv:2204.00005. In each iteration, sequential active learning selects a query set of size one while batch active learning selects a query set of multiple datapoints. While batch active learning methods exhibit greater efficiency, the challenge lies in maintaining model accuracy relative to sequential active learning methods. We developed a novel, two-part approach for batch active learning: Dijkstra's Annulus Core-Set (DAC) for core-set generation and LocalMax for batch sampling. The batch active learning process that combines DAC and LocalMax achieves nearly identical accuracy as sequential active learning but is more efficient, proportional to the batch size. As an application, a pipeline is built based on transfer learning feature embedding, graph learning, DAC, and LocalMax to classify the FUSAR-Ship and OpenSARShip datasets. Our pipeline outperforms the state-of-the-art CNN-based methods.

cs.LG↗

arXiv2023

Non-convex approaches for low-rank tensor completion under tubal sampling

Tensor completion is an important problem in modern data analysis. In this work, we investigate a specific sampling strategy, referred to as tubal sampling. We propose two novel non-convex tensor completion frameworks that are easy to implement, named tensor $L_1$-$L_2$ (TL12) and tensor completion via CUR (TCCUR). We test the efficiency of both methods on synthetic data and a color image inpainting problem. Empirical results reveal a trade-off between the accuracy and time efficiency of these two methods in a low sampling ratio. Each of them outperforms some classical completion methods in at least one aspect.

cs.LG↗

arXiv2021

Alternative experimental ways to access entropy production

We theoretically derive and experimentally compare several different ways to access entropy production in a quantum process under feedback control. We focus on a bipartite quantum system realizing an autonomous Maxwell's demon scheme reported by Najera-Santos et al. [Phys.~Rev.~Research 2, 032025(R) (2020)], where information encoded in a demon is consumed to transfer heat from a cold qubit to a hot cavity. By measuring individual quantum trajectories of the joint demon-cavity-qubit system, we compute the entropy production with six distinct expressions derived from different approaches to the system description and its evolution. Each method uses a specific set of trajectories and data processing. Our results provide a unified view on the various meanings of irreversibility in quantum systems and pave the way to the measurement of entropy production beyond thermal frameworks.

quant-ph↗

arXiv2019

ZAIGA: Zhaoshan Long-baseline Atom Interferometer Gravitation Antenna

The Zhaoshan long-baseline Atom Interferometer Gravitation Antenna (ZAIGA) is a new type of underground laser-linked interferometer facility, and is currently under construction. It is in the 200-meter-on-average underground of a mountain named Zhaoshan which is about 80 km southeast to Wuhan. ZAIGA will be equipped with long-baseline atom interferometers, high-precision atom clocks, and large-scale gyros. ZAIGA facility will take an equilateral triangle configuration with two 1-km-apart atom interferometers in each arm, a 300-meter vertical tunnel with atom fountain and atom clocks mounted, and a tracking-and-ranging 1-km-arm-length prototype with lattice optical clocks linked by locked lasers. The ZAIGA facility will be used for experimental research on gravitation and related problems including gravitational wave detection, high-precision test of the equivalence principle of micro-particles, clock based gravitational red-shift measurement, rotation measurement and gravito-magnetic effect.

physics.atom-ph↗

arXiv2019

Normal-mode splitting of four-level atom-cavity system under collective strong coupling

We investigate the transmission spectrum of an optical cavity coupled with four-level atoms. Multiple normal-mode splitting peaks of the strongly coupled atom-cavity system are obtained as single cavity mode couples three separated atomic transitions simultaneously. We employ a confocal optical cavity and an ensemble of cold Rb-85 atoms for cavity quantum electrodynamics. We observe four normal-mode splitting peaks of the cavity transmission in the strong coupling regime due to collective enhancement of the atom-cavity coupling strength by ensemble of cold atoms. The experimental observations are consistent with the theoretical analysis. The multiple normal-mode excitation in the strongly coupled multi-level atom-cavity system may lead to practical application for realizing multi-channel all-optical devices.

quant-ph↗

arXiv2014

Interference control of nonlinear excitation in a multiatom cavity QED system

We show that by manipulating quantum interference in a multi-atom cavity QED system, the nonlinear excitation of the cavity-atom polariton can be resonantly enhanced while the linear excitation is suppressed. Under appropriate conditions, it is possible to selectively enhance or suppress the polariton excitation with two free-pace laser fields. We report an experiment with cold Rb atoms in an optical cavity and present experimental results that demonstrate such interference control of the cavity QED excitation and its direct applications for studies of all-optical switching and cross-phase modulation of the cavity transmitted light.

physics.optics↗

arXiv2013

Interaction-free all-optical switching at low light Intensities in a multi-atom cavity QED system

We propose a scheme of the interaction-free all-optical switching in a multi-atom cavity QED system consisting of three-level atoms confined in a cavity and coupled by a free-space control laser. A signal laser field is coupled into the cavity and its transmission through and reflection from the cavity form two output channels. We show that the free-space control laser induces destructive quantum interference in the excitation of the intra-cavity normal mode, which can be used to switch on or off of the output signal light of the reflection and the transmission channels. When the control light is coupled to the atoms, the input signal light is nearly totally reflected and this means that there is no direct coupling of the control light and the signal light through the cavity-confined atoms. We present analytical and numerical calculations that show this type of the interaction-free all-optical switching in the coupled cavity-atom system can be realized with high switching efficiencies and at low light intensities.

physics.optics↗