Searcharxiv⌕ Search

arXiv subjects

Jingxuan Chen

Publications and source records attributed to Jingxuan Chen.

At least 19 recordsLinked to original sources

Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length

Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, analysing the overall sentiment of a number of movie reviews requires an LLM to process the sentiment of each review individually in order to provide a final aggregated answer. While LLM performance on such individual tasks is generally high, there has been little research on how LLMs perform when dealing with multi-instance inputs. In this paper, we perform a comprehensive evaluation of the multi-instance processing (MIP) ability of LLMs for tasks in which they excel individually. The results show that all LLMs follow a pattern of slight performance degradation for small numbers of instances (approximately 20-100), followed by a performance collapse on larger instance counts. Crucially, our analysis shows that while context length is associated with this degradation, the number of instances has a stronger effect on the final results. This finding suggests that when optimising LLM performance for MIP, attention should be paid to both context length and, in particular, instance count.

cs.AI↗

Thermo-VLA: A Thermal-Aware Vision-Language-Action Model with Gated Residual Modulation for Robotic Manipulation

Recent Vision-Language-Action (VLA) models have begun incorporating thermal sensing, but existing approaches typically treat thermal images as ordinary visual inputs, providing limited support for temperature-aware relational reasoning in manipulation. To address this limitation, we propose Thermo-VLA with a ThermoRes Encoder, which decomposes thermal images into cold and hot attribute representations and injects them into the RGB token through language-conditioned residual modulation, enabling temperature-driven target selection and continuous manipulation. We further construct six real-world robotic tasks on a dual-arm Unitree G1 platform, spanning basic grounding to relational reasoning. Experiments show that Thermo-VLA achieves an average success rate of 0.86 across four thermal-dependent tasks, outperforming a pi_0.5 baseline that directly incorporates RGB-thermal observations by 18 percentage points. Under unseen-object and scene variations, Thermo-VLA maintains an average success rate of 0.78, achieving the best generalisation performance among the compared methods. Beyond thermal sensing, we transfer the same residual modulation mechanism to colour attributes and observe consistent improvements in both simulation and real-robot experiments, indicating its potential to generalise beyond thermal attributes. Project website: https://j-x-chen.github.io/Thermo-VLA-web/

cs.RO↗

Does Every Instance Count Equally? Order Effects in LLM Multi-Instance Processing

Users increasingly rely on large language models (LLMs) to analyse collections of independent inputs, such as product reviews or social media posts, and return a single aggregated answer. This setting requires multi-instance processing (MIP), where a model combines information from multiple instances into one prediction. We study a task in which the model must infer a binary label for each instance, and identify the most frequent label among the full instance set. The correct answer should be invariant to instance order. By evaluating fifteen LLMs across five datasets and seven instance order patterns, with each instance set held fixed across patterns, we find substantial order sensitivity. Accuracy can differ by about 90 percentage points between the best and worst order patterns, with models generally more accurate when majority-label instances appear at the start than when they appear in the middle or at the end. For subsets of models, available reasoning traces and gradient-based attribution reveal uneven emphasis across positions. Traces disproportionately mention early instances, while attribution scores are generally higher near the beginning and end than in the middle. These results show that instance order can systematically bias aggregated predictions, highlighting the need to evaluate MIP across different input arrangements.

cs.AI↗

PRB-WM: Physics-Regularized Beta World Models for Predictive Link Adaptation on Real Time-Varying Underwater Acoustic Channels

Adaptive modulation and coding (AMC) improves the spectral efficiency of underwater acoustic (UWA) links, but its feedback is inevitably stale: sound propagates slowly, and by the time channel state information (CSI) arrives, the fast time-varying multipath channel has moved on. Predictive link adaptation therefore needs more than a point forecast: it needs a distribution over each candidate action's consequences. We propose PRB-WM, a physics-regularized Beta world model for predictive per-subcarrier link adaptation on real time-varying UWA channels. A persistence-anchored stochastic latent-space dynamics model learns how the channel evolves; a counterfactual outcome head evaluates, for every candidate modulation and coding scheme (MCS), a Beta-binomial distribution of bit errors on shared imagined futures; and a chance-constrained receding-horizon model predictive controller maximizes expected spectral efficiency subject to a bounded probability of violating the bit error rate (BER) target. To the best of our knowledge, PRB-WM is the first world model for UWA communications. In closed-loop replay of six measured sea-trial links from the public UWA Channel Library against a 24-method pool spanning the full methodological spectrum, PRB-WM attains a mean goodput 87% above the strongest baseline, ranks first on all six time-varying links at the longest lookahead, and is the only method whose realized frame risk decreases systematically with lookahead, meeting the BER-violation contract where no baseline does. Ablations confirm that rollout sampling dispersion is essential to the chance constraint and that the physics anchor is necessary for trainability.

cs.SD↗

DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning

Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-entropy method whose imagined demand is anchored on the current observation window with mixing coefficient $ρ=0.95$. On a unified pipeline over three real datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.

cs.NI↗

Beyond Syntax: Action Semantics Learning for App Agents

The recent development of Large Language Models (LLMs) enables the rise of App agents that interpret user intent and operate smartphone Apps through actions such as clicking and scrolling. While prompt-based solutions with proprietary LLM APIs show promising ability, they incur heavy compute costs and external API dependency. Fine-tuning smaller open-source LLMs solves these limitations. However, current supervised fine-tuning methods use a syntax learning paradigm that forces agents to reproduce exactly the ground truth action strings, leading to out-of-distribution (OOD) vulnerability. To fill this gap, we propose Action Semantics Learning (ASL), a novel learning framework, where the learning objective is capturing the semantics of the ground truth actions. Specifically, inspired by the programming language theory, we define the action semantics for App agents as the state transition induced by the action in the user interface. Building on this insight, ASL employs a novel SEmantic Estimator~(SEE) to compute a semantic similarity to train the App agents in generating actions aligned with the semantics of ground truth actions, even when their syntactic forms differ. SEE is a flexible module that can be applied in both supervised and reinforcement fine-tuning paradigms. To support the effectiveness of ASL, we theoretically demonstrate the superior robustness of ASL for the OOD problem compared with the existing syntax learning paradigm. Extensive experiments across multiple offline and online benchmarks demonstrate that ASL significantly improves the accuracy and generalisation of App agents compared to existing methods.

cs.AI↗

Dual-VQE: A quantum algorithm to lower bound the ground-state energy

The variational quantum eigensolver (VQE) is a hybrid quantum-classical variational algorithm that produces an upper-bound estimate of the ground-state energy of a Hamiltonian. As quantum computers become more powerful and go beyond the reach of classical brute-force simulation, it is important to assess the quality of solutions produced by them. Here we propose a dual variational quantum eigensolver (dual-VQE) that produces a lower-bound estimate of the ground-state energy. As such, VQE and dual-VQE can serve as quality checks on their solutions; in the ideal case, the VQE upper bound and the dual-VQE lower bound form an interval containing the true optimal value of the ground-state energy. The idea behind dual-VQE is to employ semidefinite programming duality to rewrite the ground-state optimization problem as a constrained maximization problem, which itself can be bounded from below by an unconstrained optimization problem to be solved by a variational quantum algorithm. When using a convex combination ansatz in conjunction with a classical generative model, the quantum computational resources needed to evaluate the objective function of dual-VQE are no greater than those needed for that of VQE. We also show that the problem is well suited for classical pretraining using matrix product states and these methods help warm-start the optimization. We simulated the performance of dual-VQE on the transverse-field Ising model with and without pretraining and found that, for the example considered, while dual-VQE training is slower and noisier than VQE, it approaches the true value with an error of order $10^{-2}$.

quant-ph↗

Valence Quark Distributions in Pions: Insights from Tsallis Entropy

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

hep-ph↗

Orbital chiral lasing in twisted bilayer metasurfaces

Chirality is a fundamental concept in physics that underpins various phenomena in nonlinear optics, quantum physics, and topological photonics. Although the spin of a photon naturally brings chirality, orbital angular momentum can also become chirally active in the structures with a broken mirror symmetry. Here, we observe orbital chiral lasing from a twisted bilayer photonic structure leveraging its inherent structural chirality. Specifically, we design and fabricate a Moire-type optical structure by bonding and rotating two separate semiconductor membrane metasurfaces. We achieve single-mode lasing over a broad spectral range of 250 nm by optically pumping the twisted structure. The lasing emission exhibits orbital chiral characteristics, arising from helical and non-Hermitian couplings between clockwise and counter-clockwise rotating collective guided resonances, confirmed by polarization-resolved imaging and self-interference patterns. Our results provide the first observation of orbital chiral lasing in twisted photonics, and they can contribute to diverse applications of chiral light in diagnostics, optical manipulation, and communication with light.

physics.optics↗

Twist Bilayer Photonic slab's Angle-DependentGuided Resonance Analysis based on Multiple Scattering

We present an analysis of the transmission spectra of the twisted bilayer photonic slabs using a modified rigorous coupled wave (RCWA) analysis, where the evanescent bases are replaced by bases with non-zero flux density. By utilizing the modified RCWA we demonstrate the calculation of eigenmodes, which has not been realized before. To counter for the transmission property, we propose a five-layer uniform slab approximation, with an accuracy around 0.04a/c, which is more straightforward and accessible for optical engineers compared to work by Lou et al. [Phys. Rev. Lett. 126, 136101]. The moiré pattern perturbation induces a split of resonance, which show great potential for engineering the band structure. Moreover, We observe two distinct transmission phases: the angle-dependent phase and Fabry-Pérot phase, which is explained by a coupled-mode theory (CMT) with expanded channels brought by the modified eigenmodes. Our work provides a theoretical framework for the design and optimization of twisted bilayer photonic devices.

physics.optics↗

SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation

Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is essential but challenging, requiring a varied task scope, the integration of agents with different implementations, and a generalisable evaluation pipeline to assess their strengths and weaknesses. In this paper, we present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents in an interactive environment that simulates real-world conditions. SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption. Our extensive experiments across tasks and agents reveal challenges like interpreting mobile user interfaces, action grounding, memory retention, and execution costs. We propose future research directions to ease these difficulties, moving closer to real-world smartphone agent applications. SPA-Bench is available at https://ai-agents-2030.github.io/SPA-Bench/.

cs.AI↗

GUI Agents with Foundation Models: A Comprehensive Survey

Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), have facilitated the development of intelligent agents capable of performing complex tasks. By leveraging the ability of (M)LLMs to process and interpret Graphical User Interfaces (GUIs), these agents can autonomously execute user instructions, simulating human-like interactions such as clicking and typing. This survey consolidates recent research on (M)LLM-based GUI agents, highlighting key innovations in data resources, frameworks, and applications. We begin by reviewing representative datasets and benchmarks, followed by an overview of a generalized, unified framework that encapsulates the essential components of prior studies, supported by a detailed taxonomy. Additionally, we explore relevant commercial applications. Drawing insights from existing work, we identify key challenges and propose future research directions. We hope this survey will inspire further advancements in the field of (M)LLM-based GUI agents.

cs.AI↗

GGAvatar: Reconstructing Garment-Separated 3D Gaussian Splatting Avatars from Monocular Video

Avatar modelling has broad applications in human animation and virtual try-ons. Recent advancements in this field have focused on high-quality and comprehensive human reconstruction but often overlook the separation of clothing from the body. To bridge this gap, this paper introduces GGAvatar (Garment-separated 3D Gaussian Splatting Avatar), which relies on monocular videos. Through advanced parameterized templates and unique phased training, this model effectively achieves decoupled, editable, and realistic reconstruction of clothed humans. Comparative evaluations with other costly models confirm GGAvatar's superior quality and efficiency in modelling both clothed humans and separable garments. The paper also showcases applications in clothing editing, as illustrated in Figure 1, highlighting the model's benefits and the advantages of effective disentanglement. The code is available at https://github.com/J-X-Chen/GGAvatar/.

cs.CV↗

Chiral emission of vortex microlasers enabled by collective modes of guided resonances

Vortex lasers have attracted substantial attention in recent years owing to their wide array of applications such as micromanipulation, optical multiplexing, and quantum cryptography. In this work, we propose and demonstrate chiral emission of vortex microlaser leveraging the collective modes from omnidirectionally hybridizing the guided mode resonances (GMRs) within photonic crystal (PhC) slabs. Specifically, we encircle a central uniform PhC with a heterogeneous PhC that features a circular lateral boundary. Consequently, the bulk GMRs hybridize into a series of collective modes due to boundary scatterings, resulting in a vortex pattern in real space with a spiral phase front in its radiation. Benefiting from the long lifetime of GMRs as quasi-bound state in the continuum and using asymmetric pumping to lift the chiral symmetry, we demonstrate stable single-mode lasing oscillation with a low optical pumping threshold of $18~\mathrm{kW/cm^2}$ at room temperature. We identify the real-space vortex through polarization-resolved imaging and self-interference patterns, showing a vivid example of applying collective modes to realize compact and energy-efficient vortex microlasers.

physics.optics↗

RIMformer: An End-to-End Transformer for FMCW Radar Interference Mitigation

Frequency-modulated continuous-wave (FMCW) radar plays a pivotal role in the field of remote sensing. The increasing degree of FMCW radar deployment has increased the mutual interference, which weakens the detection capabilities of radars and threatens reliability and safety of systems. In this paper, a novel FMCW radar interference mitigation (RIM) method, termed as RIMformer, is proposed by using an end-to-end Transformer-based structure. In the RIMformer, a dual multi-head self-attention mechanism is proposed to capture the correlations among the distinct distance elements of intermediate frequency (IF) signals. Additionally, an improved convolutional block is integrated to harness the power of convolution for extracting local features. The architecture is designed to process time-domain IF signals in an end-to-end manner, thereby avoiding the need for additional manual data processing steps. The improved decoder structure ensures the parallelization of the network to increase its computational efficiency. Simulation and measurement experiments are carried out to validate the accuracy and effectiveness of the proposed method. The results show that the proposed RIMformer can effectively mitigate interference and restore the target signals.

eess.SP↗

An analysis of the gluon distribution with next-to-leading order splitting function in small-$x$

An approximated solution for gluon distribution from DGLAP evolution equations with NLO splitting function in the small-$x$ limit is presented. We first obtain the simplified forms of LO and NLO splitting functions in the small-$x$ limit. With these approximated splitting functions, we obtain the analytical gluon distribution by using the Mellin transform. The free parameters in the boundary conditions are obtained by fitting the CJ15 gluon distribution data. We find that the asymptotic behavior of gluon distribution are consistent with the CJ15 data, however, the NLO results with the consideration of ``ladder'' structure of gluon emission are slightly better than those from LO. These results indicate that the corrections from NLO is significant and is necessary for a better description of the behavior of the gluon distribution in small-$x$ region. In addition, we investigate the DGLAP evolution of the proton structure function by using the analytical solution of the gluon distribution. The differential structure function shows that our results have a similar tendency with CJ15 at small-$x$.

hep-ph↗

Exploring Short-Range Correlations in Symmetric Nuclei: Insights into Contacts and Entanglement Entropy

The Short-Range Correlations between nucleons in nuclei is regarded as a complex system. We investigate the relationship between the orbital entanglement entropy of SRCs $S_{ij}$ in nuclear structures and Tan contact $c_{ij}$, and find that the orbital entanglement entropies and Tan contacts corresponding to proton-proton SRC pairs and neutron-proton SRC pairs in nuclei demonstrate a scaling relation. More specifically, the proportionality of entanglement entropy between proton-proton pairs and neutron-proton pairs is directly related to the ratio of nuclear contacts within the atomic nucleus, demonstrating an approximate ratio of 2.0. Our research suggests that this scaling relationship should hold true for all symmetric nuclei, furthermore, we offer a possible explanation for this phenomenon.

nucl-th↗

Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of generality across multiple tasks and the need for a large amount of training data. The leading cause is that it cannot effectively integrate prior information into the perception-action cycle when devising the policy. Large language models (LLMs) emerged as a fundamental way to incorporate cross-domain knowledge into AI agents but lack crucial learning and adaptation toward specific decision problems. This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies. Our methodology is motivated by the modularity found in the human brain. The framework utilises the construction of intrinsic and extrinsic functions to add previous understandings of reasoning structures. It also provides the adaptive ability to learn models inside every module or function, consistent with the modular structure of cognitive processes. We describe the framework in-depth and compare it with other AI pipelines and existing frameworks. The paper explores practical applications, covering experiments that show the effectiveness of our method. Our results indicate that AI agents perform and adapt far better when organised reasoning and prior knowledge are embedded. This opens the door to more resilient and general AI agent systems.

cs.AI↗