Searcharxiv⌕ Search

arXiv subjects

Jianjun Wu

Publications and source records attributed to Jianjun Wu.

At least 19 recordsLinked to original sources

Science Prediction Universe

Humanity has long sought to explain natural phenomena. Reliable prediction of experimental outcomes is a central test of our understanding of the processes that produce them. If artificial general intelligence (AGI) is to surpass human scientific capabilities, it must also predict experimental outcomes more reliably than humans. Such capabilities could accelerate scientific discovery across disciplines, help address humanity's most pressing challenges, and improve human well-being. We introduce Science Prediction Universe (SPU), a benchmark of hidden experimental outcomes with 100 public verified tasks from chemistry, materials science, biology and medicine, and 16 private tasks from unpublished wet-lab experiments. Given an experimental setup and candidate conditions, an agent works with any resources it needs to rank the candidates by a measured outcome. We evaluate thirteen agent configurations spanning twelve frontier models across two harnesses (Codex and Claude Code). Current agents remain far from saturating wet-lab outcome prediction, with substantial performance disparities across models: on the public benchmark, configurations separate into two distinct tiers, with task-adjusted Spearman correlations ranging from 0.227 for the lowest-performing configuration to 0.478 for the best. Analysis of 1,155 scored public trajectories (227,103 tool calls) suggests that the bottleneck lies in scientific judgment rather than tool execution: agents rely on shared monotone priors, agreeing far more with one another than with experimental reality (0.52 vs. 0.33), and frequently compute trivial physical or chemical proxies that do not influence the final outcome.

cs.AI↗

PAPERBENCHX: Can AI Reproduce Science Across Disciplines?

Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is known, yet recovering it still requires translating an incomplete scientific description into an executable experiment and producing evidence that can be independently verified. Existing research-reproduction benchmarks largely focus on AI and machine learning, where experiments share relatively homogeneous software stacks. Extending this capability across scientific disciplines introduces a different challenge: agents must operate domain-specific scientific software, make physical and numerical choices, diagnose long-running computations, and distinguish valid evidence from merely plausible outputs. We introduce PAPERBENCHX, a benchmark of 93 expert-constructed paper-reproduction tasks spanning 12 research areas across electromagnetics, photonics, chemistry, materials science, biology, and robotics. Each task provides the source paper, a public task specification, and a domain-native scientific environment involving specialized scientific software. Agents must reconstruct a key experiment, execute and diagnose it, and deliver a runnable workflow that supports the target scientific claim. To evaluate scientific validity rather than surface-level agreement, we replay every submission from scratch and score only regenerated evidence against expert-validated criteria. Across 10 frontier agent configurations, the best configuration fully reproduces only 14% tasks under the 90% threshold. Meanwhile, mean rubric scores range from 27.53% to 59.08%, indicating that substantial partial progress rarely translates into complete scientific reproduction. These results reveal a large gap between paper understanding and reliably producing reproducible scientific evidence.

cs.AI↗

A Portable Optical Frequency Comb with Low Repetition-Rate Drift Based on "Optical Cubes"

We demonstrate a compact, fully stabilized, all-polarization-maintaining (all-PM) Er:fiber optical frequency comb (OFC) implemented on a silica optical-cube platform. The optical comb module, including the oscillator, amplifier, spectral-broadening stage, 780-nm frequency-doubling branch, and f-to-2f interferometer, occupies a volume of 0.88 L. Without active temperature control, the free-running repetition frequency exhibits a peak-to-peak excursion of 75 Hz over 10 h, corresponding to 0.375 ppm. Under the same laboratory conditions, this excursion is 6.2 times smaller than that of a mechanically mounted non-PM reference comb. The amplified pulses are compressed to 94 fs and spectrally broadened in a PM highly nonlinear fiber. A coherent-population-trapping-based chip-scale atomic clock is employed for the first time as the radio-frequency reference for comb locking, thereby reducing the footprint of the microwave-reference subsystem. The resulting in-loop, optical-frequency-normalized tracking instability reaches 6.03E-17 at 1 s and 2.57E-18 at 10,000 s. These results demonstrate a compact comb architecture with reduced sensitivity to environmental perturbations, providing a practical route toward portable optical atomic clocks.

physics.optics↗

Noise-Aware Fleet Scheduling for On-Demand Urban Air Mobility with Alternative Flight Paths and Cruise Separation

Multiple candidate flight paths between the same vertiports provide flexibility for managing noise exposure and cruise separation in on-demand urban air mobility (UAM). This paper introduces the fleet scheduling problem with alternative flight paths (FSP-AFP). We develop a time-expanded fleet-flow formulation for a finite aircraft fleet, in which each service or empty repositioning flight is assigned a planar path from a predefined set of alternatives connecting its origin and destination vertiports. These path choices are jointly optimized with cruise altitudes, departure times, and repositioning movements, while maintaining aircraft flow balance and enforcing geometric separation between flights cruising concurrently at the same altitude. The objective combines flight costs, service departure delays, and population-weighted noise exposure. A tailored branch-and-cut algorithm incorporates three complementary clique constructions based on a request-augmented conflict graph, exploiting physical flight conflicts, request exclusivity, and request-route relationships. Computational experiments show that, compared with a baseline implemented using Gurobi's native lazy-constraint functionality, the proposed algorithm generally obtains stronger lower bounds and finds feasible solutions for all test instances, while generating fewer cuts on average and achieving a 43.16-fold reduction in the mean number of processed search nodes. An operational case study shows that increasing the number of candidate planar routes per vertiport pair from one to four reduces the weighted objective by 6.71% and modeled noise exposure by 15.14% under the cruise-separation constraints. Further increases in the number of candidate routes yield only marginal improvement in the objective value. These findings show the value of coordinating alternative flight paths, scheduling, and fleet circulation in UAM.

math.OC↗

Accurate recovery of the two linewidths hidden in laser beatnote statistics

Photons from ultrastable lasers can remain coherent over distances approaching the Earth-Sun separation, enabling optical clocks projected to lose less than one second over the age of the Universe. Yet characterizing these photons poses an identifiability problem: a two-laser heterodyne measurement produces a single beatnote linewidth that conflates contributions from both lasers. For more than half a century, the standard solution has been the three-cornered-hat (TCH) method, which requires three independent ultrastable lasers. Here we derive the mathematical form and elucidate the physical origin of asymmetric beatnote-linewidth distributions arising from finite photon wave trains, a long-observed feature not captured by canonical Gaussian or Lorentzian statistics. This finding accurately recovers two linewidths hidden in laser beatnote statistics without a third laser. The framework consistently captures the observed coherence-length and coherence-time statistics of photons, while comparison with TCH measurements confirms the quantitative validity of the extracted individual linewidths across five independent ultrastable-laser datasets spanning nearly two orders of magnitude. Most notably, the method resolves the 7.8-mHz linewidth of a cryogenic silicon-cavity laser beating with a broader laser. This transformative function of beatnote-linewidth distributions, together with the resulting method, could fundamentally advance optical clocks and precision metrology.

physics.optics↗

DREAM Technical Report

Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment information and objectives across modules, rely on rigid rules, and have limited awareness of real-time intent, leaving session-level shifts among browsing, comparison, and purchase insufficiently addressed. We present DREAM (Developing Recommender Engine with Agentic Methods), an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them. DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%. Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with safety guardrails. A Reward Dual Loop continuously optimizes both components by combining offline simulation for strategy-space exploration with online feedback for outcome calibration, forming a cycle of generation, execution, evaluation, and experience accumulation. Large-scale A/B tests on Taobao's homepage feed show that re-ranking control alone improves IPV by 2.06%, Core IPV by 2.39%, and GMV by 0.88%. Extending control to fine ranking raises these gains to 2.71%, 3.06%, and 1.31%, respectively, while consistently improving PV by more than 1%. These gains require neither replacement of pipeline models nor compromise of serving stability, supporting agentic meta-control as a viable paradigm for industrial recommendation.

cs.IR↗

Overcoming BS Down-Tilt for Air-Ground ISAC Coverage: Antenna Design, Beamforming and User Scheduling

Integrated sensing and communication holds great promise for low-altitude economy applications. However, conventional downtilted base stations primarily provide sectorized forward lobes for ground services, failing to sense air targets due to backward blind zones. In this paper, a novel antenna structure is proposed to enable air-ground beam steering, facilitating simultaneous full-space sensing and communication (S&C). Specifically, instead of inserting a reflector behind the antenna array for backlobe mitigation, an omni-steering plate is introduced to collaborate with the active array for omnidirectional beamforming. Building on this hardware innovation, sum S&C mutual information (MI) is maximized, jointly optimizing user scheduling, passive coefficients of the omni-steering plate, and beamforming of the active array. The problem is decomposed into two subproblems: one for optimizing passive coefficients via Riemannian gradient on the manifold, and the other for optimizing user scheduling and active array beamforming. Exploiting relationships among S&C MI, data decoding MMSE, and parameter estimation MMSE, the original subproblem is equivalently transformed into a sum weighted MMSE problem, rigorously established via the Lagrangian and first-order optimality conditions. Simulations show that the proposed algorithm outperforms baselines in sum-MI and MSE, while providing 360 sensing coverage. Beampattern analysis further demonstrates effective user scheduling and accurate target alignment.

eess.SP↗

Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging Thromboelastography

In an ideal medical environment, real-time coagulation monitoring can enable early detection and prompt remediation of risks. However, traditional Thromboelastography (TEG), a widely employed diagnostic modality, can only provide such outputs after nearly 1 hour of measurement. The delay might lead to elevated mortality rates. These issues clearly point out one of the key challenges for medical AI development: Mak-ing reasonable predictions based on very small data sets and accounting for variation between different patient populations, a task where conventional deep learning methods typically perform poorly. We present Physiological State Reconstruc-tion (PSR), a new algorithm specifically designed to take ad-vantage of dynamic changes between individuals and to max-imize useful information produced by small amounts of clini-cal data through mapping to reliable predictions and diagnosis. We develop MDFE to facilitate integration of varied temporal signals using multi-domain learning, and jointly learn high-level temporal interactions together with attentions via HLA; furthermore, the parameterized DAM we designed maintains the stability of the computed vital signs. PSR evaluates with 4 TEG-specialized data sets and establishes remarkable perfor-mance -- predictions of R2 > 0.98 for coagulation traits and error reduction around half compared to the state-of-the-art methods, and halving the inferencing time too. Drift-aware learning suggests a new future, with potential uses well be-yond thrombophilia discovery towards medical AI applica-tions with data scarcity.

cs.LG↗

WiCo-PG: Wireless Channel Foundation Model for Pathloss Map Generation via Synesthesia of Machines

A wireless channel foundation model for pathloss map generation (WiCo-PG) via Synesthesia of Machines (SoM) is developed for the first time. Considering sixth-generation (6G) uncrewed aerial vehicle (UAV)-to-ground (U2G) scenarios, a new multi-modal sensing-communication dataset is constructed for WiCo-PG pre-training, including multiple U2G scenarios, diverse flight altitudes, and diverse frequency bands. Based on the constructed dataset, the proposed WiCo-PG enables cross-modal pathloss map generation by leveraging RGB images from different scenarios and flight altitudes. In WiCo-PG, a novel network architecture designed for cross-modal pathloss map generation based on dual vector quantized generative adversarial networks (VQGANs) and Transformer is proposed. Furthermore, a novel frequency-guided shared-routed mixture of experts (S-R MoE) architecture is designed for cross-modal pathloss map generation. Simulation results demonstrate that the proposed WiCo-PG achieves improved pathloss map generation accuracy through pre-training with a normalized mean squared error (NMSE) of 0.012, outperforming the large language model (LLM)-based scheme, i.e., LLM4PG, and the conventional deep learning-based scheme by more than 6.98 dB. The enhanced generality of the proposed WiCo-PG can further outperform the LLM4PG by at least 1.37 dB using 2.7% samples in few-shot generalization.

eess.SP↗

LLM4PG: Adapting Large Language Model for Pathloss Map Generation via Synesthesia of Machines

In this paper, a novel large language model (LLM)-based pathloss map generation model, termed LLM4PG, is proposed for sixth-generation (6G) AI-native communication systems via Synesthesia of Machines (SoM). To explore the mapping mechanism between sensing images and pathloss maps, a new synthetic intelligent multi-modal sensing-communication dataset, SynthSoM-U2G, is constructed, covering multiple scenarios, frequency bands, and flight altitudes. By adapting the LLM for cross-modal pathloss map generation for the first time, LLM4PG establishes an effective cross-domain alignment between the multi-modal sensing-communication and natural language domains. A task-specific fine-tuning strategy with a tailored layer selection and activation scheme is designed to meet the demands of massive-scale, high-quality generation. Compared with conventional deep learning artificial intelligence generated content (AIGC) models, LLM4PG achieves more accurate pathloss map generation and stronger generalization across diverse conditions. Results show that LLM4PG attains an NMSE of 0.0454, outperforming the conventional AIGC model by over 2.90 dB, while its cross-condition generalization achieves an NMSE of 0.0492, exceeding the baseline by 4.52 dB.

eess.SP↗

Recursive Inverse Design Enables Hyper-spectral Photonic Integrated Circuits

Spectrum manipulation is central to photonic systems, where advanced computing and sensing applications often demand highly complex spectral responses to achieve high throughput. Conventional methods for enhancing spectral complexity typically rely on cascading discrete photonic components, resulting in a complexity that scales only linearly with the number of components. Here, we introduce hyper-spectral photonic integrated circuits (HS-PICs), in which spectral complexity scales exponentially with the number of components. This is achieved through recursive inverse design - a system-level inverse design strategy that exploits intricate inter-component interactions as design freedoms, thereby substantially expanding the design space for spectral engineering. Using this approach, we demonstrate that even a single waveguide structure can resolve spectra with sub-picometer resolution, surpassing the performance of current state-of-the-art spectrometers. This performance bridges optical and microwave frequencies in spectral analysis, enabling simultaneous monitoring of optical and radio signals within a single device. Our work establishes a transformative framework for next-generation computing and sensing technologies.

physics.optics↗

Compact 780 nm Rb Optical Clock

We demonstrated a compact 780 nm rubidium optical clock, which includes an optical frequency standard and an optical frequency comb, with an optical volume of 11.6 liters. Unlike the 778 nm rubidium atomic clocks based on two-photon transition, here, the laser frequency is stabilized to the Rb D2 transition, using modulation transfer spectroscopy. This approach effectively eliminates Doppler background and provides a high signal to noise ratio and high sensitivity. A nearly 300 MHz microwave signal, whose phase exactly tracks that of the optical frequency standard, is generated via the optical frequency comb, yielding a frequency instability of 1.91 E-13 @1 s and 5.29 E-14 @1000 s in the electronic domain. To the best of our knowledge, this is the most precise frequency stabilization result for the first-excited-state transition of alkali metal atoms to date and represents the first optical clock based on this transition. These results offer a promising approach for the development of portable optical clocks.

physics.optics↗

Optimizing Electric Carsharing System Operations and Battery Management: Integrating V2G, B2G and Battery Swapping Strategies

Shared electric vehicles (SEVs) have emerged as a promising solution to contribute to sustainable urban mobility. However, ensuring the efficient operation and effective battery management of SEV systems remains a complex challenge. This challenge stems from factors such as slow plug-in charging, the potential role of SEVs in balancing grid load pressure, and the optimization of SEV operations to ensure their economic viability. To tackle these challenges, this paper introduces an integrated strategy for optimizing various aspects of SEV systems, encompassing strategies like Vehicle-to-Grid (V2G), Battery-to-Grid (B2G), and battery swapping. This approach is built on a space-time-energy network model that facilitates the optimization of battery charging and discharging scheduling, SEV operations like relocations and battery swapping, battery swapping station selection and the number of batteries. The objective of this approach is to maximize profits while addressing operational constraints and the complexities of energy management within SEV systems. Given the substantial complexity that arises with large-problem scales, the paper introduces a column generation-based heuristic algorithm. Extensive experimental validation is conducted, including sensitivity analysis on different charging speeds and fleet sizes. The results illuminate the impact of varying charging rates and fleet sizes on performance indicators. Notably, it is observed that battery swapping is particularly effective as an auxiliary charging method when the number of vehicles is limited. Conversely, in scenarios with a large fleet, the necessity for battery swapping diminishes. Moreover, results show the effectiveness of V2G and B2G technologies in grid load balancing.

math.OC↗

NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services

Large language models (LLMs) have triggered tremendous success to empower our daily life by generative information. The personalization of LLMs could further contribute to their applications due to better alignment with human intents. Towards personalized generative services, a collaborative cloud-edge methodology is promising, as it facilitates the effective orchestration of heterogeneous distributed communication and computing resources. In this article, we put forward NetGPT to capably synergize appropriate LLMs at the edge and the cloud based on their computing capacity. In addition, edge LLMs could efficiently leverage location-based information for personalized prompt completion, thus benefiting the interaction with the cloud LLM. In particular, we present the feasibility of NetGPT by leveraging low-rank adaptation-based fine-tuning of open-source LLMs (i.e., GPT-2-base model and LLaMA model), and conduct comprehensive numerical comparisons with alternative cloud-edge collaboration or cloud-only techniques, so as to demonstrate the superiority of NetGPT. Subsequently, we highlight the essential changes required for an artificial intelligence (AI)-native network architecture towards NetGPT, with emphasis on deeper integration of communications and computing resources and careful calibration of logical AI workflow. Furthermore, we demonstrate several benefits of NetGPT, which come as by-products, as the edge LLMs' capability to predict trends and infer intents promises a unified solution for intelligent network management & orchestration. We argue that NetGPT is a promising AI-native network architecture for provisioning beyond personalized generative services.

cs.LG↗

6G Network AI Architecture for Everyone-Centric Customized Services

Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

cs.NI↗

RHFedMTL: Resource-Aware Hierarchical Federated Multi-Task Learning

The rapid development of artificial intelligence (AI) over massive applications including Internet-of-things on cellular network raises the concern of technical challenges such as privacy, heterogeneity and resource efficiency. Federated learning is an effective way to enable AI over massive distributed nodes with security. However, conventional works mostly focus on learning a single global model for a unique task across the network, and are generally less competent to handle multi-task learning (MTL) scenarios with stragglers at the expense of acceptable computation and communication cost. Meanwhile, it is challenging to ensure the privacy while maintain a coupled multi-task learning across multiple base stations (BSs) and terminals. In this paper, inspired by the natural cloud-BS-terminal hierarchy of cellular works, we provide a viable resource-aware hierarchical federated MTL (RHFedMTL) solution to meet the heterogeneity of tasks, by solving different tasks within the BSs and aggregating the multi-task result in the cloud without compromising the privacy. Specifically, a primal-dual method has been leveraged to effectively transform the coupled MTL into some local optimization sub-problems within BSs. Furthermore, compared with existing methods to reduce resource cost by simply changing the aggregation frequency, we dive into the intricate relationship between resource consumption and learning accuracy, and develop a resource-aware learning strategy for local terminals and BSs to meet the resource budget. Extensive simulation results demonstrate the effectiveness and superiority of RHFedMTL in terms of improving the learning accuracy and boosting the convergence rate.

cs.NI↗

Stochastic Graph Neural Network-based Value Decomposition for MARL in Internet of Vehicles

Autonomous driving has witnessed incredible advances in the past several decades, while Multi-Agent Reinforcement Learning (MARL) promises to satisfy the essential need of autonomous vehicle control in a wireless connected vehicle networks. In MARL, how to effectively decompose a global feedback into the relative contributions of individual agents belongs to one of the most fundamental problems. However, the environment volatility due to vehicle movement and wireless disturbance could significantly shape time-varying topological relationships among agents, thus making the Value Decomposition (VD) challenging. Therefore, in order to cope with this annoying volatility, it becomes imperative to design a dynamic VD framework. Hence, in this paper, we propose a novel Stochastic VMIX (SVMIX) methodology by taking account of dynamic topological features during the VD and incorporating the corresponding components into a multi-agent actor-critic architecture. In particular, Stochastic Graph Neural Network (SGNN) is leveraged to effectively capture underlying dynamics in topological features and improve the flexibility of VD against the environment volatility. Finally, the superiority of SVMIX is verified through extensive simulations.

cs.MA↗

Semantics-enhanced Temporal Graph Networks for Content Popularity Prediction

The surging demand for high-definition video streaming services and large neural network models (e.g., Generative Pre-trained Transformer, GPT) implies a tremendous explosion of Internet traffic. To mitigate the traffic pressure, architectures with in-network storage have been proposed to cache popular contents at devices in closer proximity to users. Correspondingly, in order to maximize caching utilization, it becomes essential to devise an effective popularity prediction method. In that regard, predicting popularity with dynamic graph neural network (DGNN) models achieve remarkable performance. However, DGNN models still suffer from tackling sparse datasets where most users are inactive. Therefore, we propose a reformative temporal graph network, named semantics-enhanced temporal graph network (STGN), which attaches extra semantic information into the user-content bipartite graph and could better leverage implicit relationships behind the superficial topology structure. On top of that, we customize its temporal and structural learning modules to further boost the prediction performance. Specifically, in order to efficiently aggregate the diversified semantics that a content might possess, we design a user-specific attention (UsAttn) mechanism for temporal learning module. Unlike the attention mechanism that only analyzes the influence of genres on content, UsAttn also considers the attraction of semantic information to a specific user. Meanwhile, as for the structural learning, we introduce the concept of positional encoding into our attention-based graph learning and adopt a semantic positional encoding (SPE) function to facilitate the analysis of content-oriented user-association analysis. Finally, extensive simulations verify the superiority of our STGN models and demonstrate the effectiveness in content caching.

cs.AI↗