arXiv subjects

Huan Deng

Publications and source records attributed to Huan Deng.

5 recordsLinked to original sources

arXiv2026

From Generation to Simulation: How Far Are World Models from Being True Simulators?

With the rapid progress of diffusion models and large-scale video generation, generative world models are increasingly expected to replace traditional simulators, including physics engines, game engines, and reinforcement-learning environments. Yet the remaining distance from generation to simulation lacks a systematic assessment. We present a capability-based study using an external yardstick: eight capabilities of a traditional simulator, namely asset construction, physics engine, interaction, controllability, stability, state feedback, diversity, and evaluation metrics. We trace three main technical routes--latent dynamics, video generation, and joint-embedding prediction--and map exactly 200 representative works published from 2018 to June 2026 onto these capabilities. Our analysis shows that world models have achieved functional substitution in interaction and controllability for specific scenarios, but remain short of traditional simulators in formal guarantees of physical laws, structured state feedback, and reproducible long-horizon evolution. State feedback is the most neglected cross-route shortcoming: only 6 of 163 implementation papers expose a runtime interface for querying entity states or physical parameters. We identify six research directions: formalized physics, a unified action interface, first-class state feedback, long-horizon stability, downstream-utility evaluation, and cross-route hybridization. Project page: https://github.com/AtongWang/world-model-simulators

cs.AI↗

arXiv2026

DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering

Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling capabilities, hallucination issues that compromise answer reliability, and single-agent architectures that struggle with complex reasoning scenarios involving semantic relationships and multi-hop logic. This paper introduces DataFactory, a multi-agent framework that addresses these limitations through specialized team coordination and automated knowledge transformation. The framework comprises a Data Leader employing the ReAct paradigm for reasoning orchestration, together with dedicated Database and Knowledge Graph teams, enabling the systematic decomposition of complex queries into structured and relational reasoning tasks. We formalize automated data-to-knowledge graph transformation via the mapping function T:D x S x R -> G, and implement natural language-based consultation that - unlike fixed workflow multi-agent systems - enables flexible inter-agent deliberation and adaptive planning to improve coordination robustness. We also apply context engineering strategies that integrate historical patterns and domain knowledge to reduce hallucinations and improve query accuracy. Across TabFact, WikiTableQuestions, and FeTaQA, using eight LLMs from five providers, results show consistent gains. Our approach improves accuracy by 20.2% (TabFact) and 23.9% (WikiTQ) over baselines, with significant effects (Cohen's d > 1). Team coordination also outperforms single-team variants (+5.5% TabFact, +14.4% WikiTQ, +17.1% FeTaQA ROUGE-2). The framework offers design guidelines for multi-agent collaboration and a practical platform for enterprise data analysis through integrated structured querying and graph-based knowledge representation.

cs.AI↗

arXiv2026

Polarized Radiative Transfer of Kerr-Newman Black Hole

In this analysis, we investigate the polarization radiation imaging of Kerr-Newman black holes, with a particular focus on the impact of black hole charge on photon propagation and polarization characteristics. By extending the traditional Walker-Penrose method, which is limited by its reliance on specific symmetric structures and Killing tensors, we overcome these limitations by constructing an ordinary differential equations (ODEs) numerical framework that combines the photon orbit equation with the polarization parallel transport equation. This allows for the self-consistent evolution of photon trajectories and polarization states in any spacetime backgrounds without relying on specific symmetries. Using this framework, we analyze the effects of black hole spin and charge on the polarization characteristics of radiation from both prograde and retrograde accretion disks. Our results show that black hole charge can significantly modify photon trajectories and polarization patterns: increasing charge compresses and distorts the EVPA structure on photon-ring scales, inducing localized rotations and asymmetries that may provide a potential diagnostic of a nonzero black hole charge.

gr-qc↗

arXiv2024

Dance of the ADS: Orchestrating Failures through Historically-Informed Scenario Fuzzing

As autonomous driving systems (ADS) advance towards higher levels of autonomy, orchestrating their safety verification becomes increasingly intricate. This paper unveils ScenarioFuzz, a pioneering scenario-based fuzz testing methodology. Designed like a choreographer who understands the past performances, it uncovers vulnerabilities in ADS without the crutch of predefined scenarios. Leveraging map road networks, such as OPENDRIVE, we extract essential data to form a foundational scenario seed corpus. This corpus, enriched with pertinent information, provides the necessary boundaries for fuzz testing in the absence of starting scenarios. Our approach integrates specialized mutators and mutation techniques, combined with a graph neural network model, to predict and filter out high-risk scenario seeds, optimizing the fuzzing process using historical test data. Compared to other methods, our approach reduces the time cost by an average of 60.3%, while the number of error scenarios discovered per unit of time increases by 103%. Furthermore, we propose a self-supervised collision trajectory clustering method, which aids in identifying and summarizing 54 high-risk scenario categories prone to inducing ADS faults. Our experiments have successfully uncovered 58 bugs across six tested systems, emphasizing the critical safety concerns of ADS.

cs.AI↗

arXiv2022

The omnidirectional receiver for UWOC systems based on the diffractive deep neural network

The link alignment requirement in underwater wireless optical communication (UWOC) systems is a knotty problem. The diffractive deep neural network (D2NN) has shown great potential in accomplishing tasks all optically these years. In this paper, an omnidirectional receiver based on 7-layer D2NN is first proposed to alleviate the link alignment difficulties in UWOC systems. In addition, the vectorial diffraction theory is introduced into the training of the D2NN to obtain more accurate diffraction calculations compared with the prevalently adopted scalar diffraction theory. Simulation results verify the validity of the vectorial diffraction theory and demonstrate that the presented method can focus incident light waves with tilt angles from 0 to 89 degrees in a 6.25% area of the detection plane with an average focusing efficiency of 90.96%, proving the feasibility of omnidirectional focusing at the receiver end. Extra simulations further reveal that more layers do not lead to a sustained performance improvement but rather reach a bottleneck, and the D2NN can achieve omnidirectional focusing with a certain range of focusing region size. With more effort, the proposed receiver design, which can be highly integrated with detectors, holds promise to realize both omnidirectional and reliable link establishment in UWOC systems in the future.

physics.optics↗