arXiv subjects

Siyuan Chen

Publications and source records attributed to Siyuan Chen.

At least 55 records · Page 3Linked to original sources

arXiv2026

Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems

Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction systems to deliver efficient, personalized, and 24/7 support. In practice, intelligent interaction systems encounter several challenges: (1) Constructing high-quality data for cold-start training is difficult, hindering self-evolution and raising labor costs. (2) Multi-turn dialogue performance remains suboptimal due to inadequate intent understanding, rule compliance, and solution extraction. (3) Frequent evolution of business rules affects system operability and transferability, constraining low-cost expansion and adaptability. (4) Reliance on a single LLM is insufficient in complex scenarios, where the absence of multi-agent frameworks and effective collaboration undermines process completeness and service quality. (5) The open-domain nature of multi-turn dialogues, lacking unified golden answers, hampers quantitative evaluation and continuous optimization. To address these challenges, we introduce WOWService, an intelligent interaction system tailored for industrial applications. With the integration of LLMs and multi-agent architectures, WOWService enables autonomous task management and collaborative problem-solving. Specifically, WOWService focuses on core modules including data construction, general capability enhancement, business scenario adaptation, multi-agent coordination, and automated evaluation. Currently, WOWService is deployed on the Meituan App, achieving significant gains in key metrics, e.g., User Satisfaction Metric 1 (USM 1) -27.53% and User Satisfaction Metric 2 (USM 2) +25.51%, demonstrating its effectiveness in capturing user needs and advancing personalized service.

cs.CL↗

arXiv2026

From Conflicts to Collisions: A Two-Stage Collision Scenario-Testing Approach for Autonomous Driving Systems

Autonomous driving systems (ADS) are safety-critical and require rigorous testing before public deployment. Simulation-based scenario testing provides a safe and cost-effective alternative to extensive on-road trials, enabling efficient evaluation of ADS under diverse and high-risk conditions. However, existing approaches mainly evaluates the scenarios based on their proximity to collisions and focus on scenarios already close to collision, leaving many other hazardous situations unexplored. To bridge this, we introduce a collision-related concept of conflict as an intermediate search target and propose a two-stage scenario testing framework that first searches for conflicts and then mutates these conflict scenarios to induce actual collisions. Evaluated on Baidu Apollo, our approach reveals up to 12 distinct collision types in a single run, doubling the diversity discovered by state-of-the-art baselines while requiring fewer simulations thanks to conflict-targeted mutations. These results show that using conflicts as intermediate objectives broadens the search horizon and significantly improves the efficiency and effectiveness of ADS safety evaluation.

cs.RO↗

arXiv2026

Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning

Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a partition-based multi-stage fine-tuning framework designed to exploit inter-domain synergies while minimizing negative transfer. Our approach strategically partitions domains into subsets (stages) by balancing domain discrepancy, synergy, and model capacity constraints. We theoretically analyze the proposed framework and derive novel generalization bounds that justify our partitioning strategy. Extensive empirical evaluations on various language understanding tasks show that our method consistently outperforms state-of-the-art baselines.

cs.LG↗

arXiv2026

Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment

Most multimodal models treat every negative pair alike, ignoring the ambiguous negatives that differ from the positive by only a small detail. We propose Boundary-Aware Curriculum with Local Attention (BACL), a lightweight add-on that turns these borderline cases into a curriculum signal. A Boundary-aware Negative Sampler gradually raises difficulty, while a Contrastive Local Attention loss highlights where the mismatch occurs. The two modules are fully differentiable and work with any off-the-shelf dual encoder. Theory predicts a fast O(1/n) error rate; practice shows up to +32% R@1 over CLIP and new SOTA on four large-scale benchmarks, all without extra labels.

cs.LG↗

arXiv2026

Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation

Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in practice they often hallucinate, over-trust noisy snippets, or ignore vital context. We introduce TCR (Transparent Conflict Resolution), a plug-and-play framework that makes this decision process observable and controllable. TCR (i) disentangles semantic match and factual consistency via dual contrastive encoders, (ii) estimates self-answerability to gauge confidence in internal memory, and (iii) feeds the three scalar signals to the generator through a lightweight soft-prompt with SNR-based weighting. Across seven benchmarks TCR improves conflict detection (+5-18 F1), raises knowledge-gap recovery by +21.4 pp and cuts misleading-context overrides by -29.3 pp, while adding only 0.3% parameters. The signals align with human judgements and expose temporal decision patterns.

cs.AI↗

arXiv2025

The SKAO Pulsar Timing Array

Pulsar timing arrays (PTAs) are ensembles of millisecond pulsars observed for years to decades. The primary goal of PTAs is to study gravitational-wave astronomy at nanohertz frequencies, with secondary goals of undertaking other fundamental tests of physics and astronomy. Recently, compelling evidence has emerged in established PTA experiments for the presence of a gravitational-wave background. To accelerate a confident detection of such a signal and then study gravitational-wave emitting sources, it is necessary to observe a larger number of millisecond pulsars to greater timing precision. The SKAO telescopes, which will be a factor of three to four greater in sensitivity compared to any other southern hemisphere facility, are poised to make such an impact. In this chapter, we motivate an SKAO pulsar timing array (SKAO PTA) experiment. We discuss the classes of gravitational waves present in PTA observations and how an SKAO PTA can detect and study them. We then describe the sources that can produce these signals. We discuss the astrophysical noise sources that must be mitigated to undertake the most sensitive searches. We then describe a realistic PTA experiment implemented with the SKA and place it in context alongside other PTA experiments likely ongoing in the 2030s. We describe the techniques necessary to search for gravitational waves in the SKAO PTA and motivate how very long baseline interferometry can improve the sensitivity of an SKAO PTA. The SKAO PTA will provide a view of the Universe complementary to those of the other large facilities of the 2030s.

astro-ph.HE↗

arXiv2025

The NANOGrav 12.5-year Data Set: Chromatic Noise Characterization & Mitigation with Time-Domain Kernels

Pulsar timing arrays (PTAs) have recently entered the detection era, quickly moving beyond the goal of simply improving sensitivity at the lowest frequencies for the sake of observing the stochastic gravitational wave background (GWB), and focusing on its accurate spectral characterization. While all PTA collaborations around the world use Fourier-domain Gaussian processes to model the GWB and intrinsic long time-correlated (red) noise, techniques to model the time-correlated radio frequency-dependent (chromatic) processes have varied from collaboration to collaboration. Here we test a new class of models for PTA data, Gaussian processes based on time-domain kernels that model the statistics of the chromatic processes starting from the covariance matrix. As we will show, these models can be effectively equivalent to Fourier-domain models in mitigating chromatic noise. This work presents a method for Bayesian model selection across the various choices of kernel as well as deterministic chromatic models for non-stationary chromatic events and the solar wind. As PTAs turn towards high frequency (>1/yr) sensitivity, the size of the basis used to model these processes will need to increase, and these time-domain models present some computational efficiencies compared to Fourier-domain models.

astro-ph.IM↗

arXiv2025

A User-customized and Untethered Electro-haptic Device for Immersive Human-Machine Interaction

Haptic feedback is essential for human-machine interaction, as it bridges physical and digital experiences and enables immersive engagement with virtual environments. However, current haptic devices are frequently tethered, lack portability and flexibility. They also have limited ability to deliver fine-grained, multi-dimensional feedback. To address these challenges, we present a flexible, ultra-thin, and user-customized electro-haptic device fabricated with soft materials and printable liquid metal ink. Its highly integrated and lightweight design minimizes interference with natural hand movements while maintaining reliable skin contact. By delivering finely controlled electrical stimulation through 15 electrodes, it can evoke a wide range of tactile sensations that cover diverse interaction scenarios. Our user study demonstrates that the device is comfortable to wear and capable of generating tunable, precise electro-haptic feedback, thereby significantly enhancing immersion and realism in human-machine interactions.

cs.HC↗

arXiv2025

End-to-end Autonomous Vehicle Following System using Monocular Fisheye Camera

The increase in vehicle ownership has led to increased traffic congestion, more accidents, and higher carbon emissions. Vehicle platooning is a promising solution to address these issues by improving road capacity and reducing fuel consumption. However, existing platooning systems face challenges such as reliance on lane markings and expensive high-precision sensors, which limits their general applicability. To address these issues, we propose a vehicle following framework that expands its capability from restricted scenarios to general scenario applications using only a camera. This is achieved through our newly proposed end-to-end method, which improves overall driving performance. The method incorporates a semantic mask to address causal confusion in multi-frame data fusion. Additionally, we introduce a dynamic sampling mechanism to precisely track the trajectories of preceding vehicles. Extensive closed-loop validation in real-world vehicle experiments demonstrates the system's ability to follow vehicles in various scenarios, outperforming traditional multi-stage algorithms. This makes it a promising solution for cost-effective autonomous vehicle platooning. A complete real-world vehicle experiment is available at https://youtu.be/zL1bcVb9kqQ.

cs.RO↗

arXiv2025

Conceptual Design of the Muonium-to-Antimuonium Conversion Experiment (MACE)

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. The Muonium-to-Antimuonium Conversion Experiment (MACE) is designed to utilize a high-intensity muon beam, a Michel electron magnetic spectrometer, a positron transport system, and a positron detection system, to either discover or constrain this rare process with a conversion probability of $\mathcal{O}(10^{-13})$. This article presents an overview of the theoretical framework as well as a detailed description of the experimental design for the search for muonium-to-antimuonium conversion.

hep-ex↗

arXiv2025

Quantum Acoustics Demystifies the Strange Metals

Phonons have long been thought to be incapable of explaining key phenomena in strange metals, including linear-in-\textit{T} Planckian resistivity from high to very low temperatures. We argue that these conclusions were based on static, perturbative approaches that overlooked essential time-dependent and nonperturbative electron-lattice physics. In fact ``phonons'' are not the best target for discussion, just like ``photons'' are not the best way to think about Maxwell's equations. Quantum optics connects photons and electromagnetism, as developed 60 years ago by Glauber and others. We have been developing the parallel world of quantum acoustics. Far from being only of academic interest, the new tools are rapidly exposing the secrets of the strange metals, revealing strong vibronic (vibration-electronic) interactions playing a crucial role forming polarons and charge density waves, linear-in-$T$ resistivity at the Planckian rate over thousands of degrees, resolution of the Drude peak infrared anomaly, and the absence of a $T^4$ low-temperature resistivity rise in 2D systems, and of a Mott-Ioffe-Regel resistivity saturation. We derive Planckian transport, polarons, CDWs, and pseudogaps from the Fröhlich model. The ``new physics'' has been hiding in this model all along, in the right parameter regime, if it is treated nonperturbatively. In the course of this work we have uncovered the generalization of Anderson localization to dynamic media: a universal Planckian diffusion emerges, a ``ghost'' of Anderson localization. Planckian diffusion is clearly defined and is more fundamental than the popular but elusive, model dependent concept of ``Planckian speed limit''.

cond-mat.str-el↗

arXiv2025

High-Precision Physics Experiments at Huizhou Large-Scale Scientific Facilities

In response to the capabilities presented by the High-Intensity Heavy Ion Accelerator Facility (HIAF) and the Accelerator-Driven Subcritical System (CiADS), as well as the proposed Chinese Advanced Nuclear Physics Research Facility (CNUF), we are assembling a consortium of experts in relevant discipline--both domestically and internationally--to delineate high-precision physics experiments that leverage the state-of-the-art research environment afforded by CNUF. Our focus encompasses six primary domains of inquiry: hadron physics--including endeavors such as the super eta factory and investigations into light hadron structures; muon physics; neutrino physics; neutron physics; the testing of fundamental symmetries; and the exploration of quantum effects within nuclear physics, along with the utilization of vortex accelerators. We aim to foster a well-rounded portfolio of large, medium, and small-scale projects, thus unlocking new scientific avenues and optimizing the potential of the Huizhou large scientific facility. The aspiration for international leadership in scientific research will be a guiding principle in our strategic planning. This initiative will serve as a foundational reference for the Institute of Modern Physics in its strategic planning and goal-setting, ensuring alignment with its developmental objectives while striving to secure a competitive edge in technological advancement. Our ambition is to engage in substantive research within these realms of high-precision physics, to pursue groundbreaking discoveries, and to stimulate progress in China's nuclear physics landscape, positioning Huizhou as a preeminent global hub for advanced nuclear physics research.

hep-ph↗

arXiv2025

DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation

We present DexCanvas, a large-scale hybrid real-synthetic human manipulation dataset containing 7,000 hours of dexterous hand-object interactions seeded from 70 hours of real human demonstrations, organized across 21 fundamental manipulation types based on the Cutkosky taxonomy. Each entry combines synchronized multi-view RGB-D, high-precision mocap with MANO hand parameters, and per-frame contact points with physically consistent force profiles. Our real-to-sim pipeline uses reinforcement learning to train policies that control an actuated MANO hand in physics simulation, reproducing human demonstrations while discovering the underlying contact forces that generate the observed object motion. DexCanvas is the first manipulation dataset to combine large-scale real demonstrations, systematic skill coverage based on established taxonomies, and physics-validated contact annotations. The dataset can facilitate research in robotic manipulation learning, contact-rich control, and skill transfer across different hand morphologies.

cs.RO↗

arXiv2025

Fast Subspace Fluid Simulation with a Temporally-Aware Basis

We present a novel reduced-order fluid simulation technique leveraging Dynamic Mode Decomposition (DMD) to achieve fast, memory-efficient, and user-controllable subspace simulation. We demonstrate that our approach combines the strengths of both spatial reduced order models (ROMs) as well as spectral decompositions. By optimizing for the operator that evolves a system state from one timestep to the next, rather than the system state itself, we gain both the compressive power of spatial ROMs as well as the intuitive physical dynamics of spectral methods. The latter property is of particular interest in graphics applications, where user control of fluid phenomena is of high demand. We demonstrate this in various applications including spatial and temporal modulation tools and fluid upscaling with added turbulence. We adapt DMD for graphics applications by reducing computational overhead, incorporating user-defined force inputs, and optimizing memory usage with randomized SVD. The integration of OptDMD and DMD with Control (DMDc) facilitates noise-robust reconstruction and real-time user interaction. We demonstrate the technique's robustness across diverse simulation scenarios, including artistic editing, time-reversal, and super-resolution. Through experimental validation on challenging scenarios, such as colliding vortex rings and boundary-interacting plumes, our method also exhibits superior performance and fidelity with significantly fewer basis functions compared to existing spatial ROMs. The inherent linearity of the DMD operator enables unique application modes, such as time-reversible fluid simulation. This work establishes another avenue for developing real-time, high-quality fluid simulations, enriching the space of fluid simulation techniques in interactive graphics and animation.

cs.GR↗

arXiv2025

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for automating kernel optimization, this field suffers from a fragmented ecosystem of isolated and incomparable approaches with unclear problem formulations. Furthermore, general-purpose LLM code evolution methods cannot meet strict correctness requirements of CUDA kernel optimization. We address these fundamental challenges by first formalizing CUDA kernel optimization as a code optimization task with a clear objective, constraints, and evaluation metrics. We then establish the first systematic LLM-based code evolution framework, EvoEngineer, that provides guidance for designing and adapting optimization strategies to achieve a balance between performance and correctness. Finally, we implement a kernel optimization system based on this framework and conduct extensive experiments on 91 real-world CUDA kernels. Our results demonstrate that EvoEngineer achieves a principled balance between performance and correctness, with the highest averaged median speedup of \textbf{2.72}$\times$ over baseline CUDA kernels and a code validity rate of \textbf{69.8}\%, outperforming existing methods on both dimensions. Our method achieves a maximum speedup of \textbf{36.75}$\times$ among all operations over PyTorch kernels and delivers the highest speedup on \textbf{28} (\textbf{56.0\%}) of 50 operations that achieve over \textbf{2$\times$} acceleration.

cs.LG↗

arXiv2025

Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models

Automated kernel design is critical for overcoming software ecosystem barriers in emerging hardware platforms like RISC-V. While large language models (LLMs) have shown promise for automated kernel optimization, demonstrating success in CUDA domains with comprehensive technical documents and mature codebases, their effectiveness remains unproven for reference-scarce domains like RISC-V. We present Evolution of Kernels (EoK), a novel LLM-based evolutionary program search framework that automates kernel design for domains with limited reference material. EoK mitigates reference scarcity by mining and formalizing reusable optimization ideas (general design principles + actionable thoughts) from established kernel libraries' development histories; it then guides parallel LLM explorations using these ideas, enriched via Retrieval-Augmented Generation (RAG) with RISC-V-specific context, prioritizing historically effective techniques. Empirically, EoK achieves a median 1.27x speedup, surpassing human experts on all 80 evaluated kernel design tasks and improving upon prior LLM-based automated kernel design methods by 20%. These results underscore the viability of incorporating human experience into emerging domains and highlight the immense potential of LLM-based automated kernel optimization.

cs.SE↗

arXiv2025

Rapid Construction of Joint Pulsar Timing Array Datasets: The Lite Method

The International Pulsar Timing Array (IPTA)'s second data release (IPTA DR2) combines decades of observations of 65 millisecond pulsars from 7 radio telescopes. IPTA datasets should be the most sensitive datasets to nanohertz gravitational waves (GWs), but take years to assemble, often excluding valuable recent data. To address this, we introduce the IPTA "Lite" analysis, where a Figure of Merit is used to select an optimal PTA dataset to analyze for each pulsar, enabling immediate access to new data and preliminary results prior to full combination. We test the capabilities of the Lite analysis using IPTA DR2, finding that "DR2 Lite" can be used to detect the common red noise process with an amplitude of $A = 4.8^{+1.8}_{-1.8} \times 10^{-15}$ at $γ= 13/3$. This amplitude is slightly large in comparison to the combined analysis, and likely biased high as DR2 Lite is more sensitive to systematic errors from individual pulsars than the full dataset. Furthermore, although there is no strong evidence for Hellings-Downs correlations in IPTA DR2, we still find the full dataset is better at resolving Hellings-Downs correlations than DR2 Lite. Alongside the Lite analysis, we also find that analyzing a subset of pulsars from IPTA DR2, available at a hypothetical "early" stage of combination (EDR2), yields equally competitive results as the full dataset. Looking ahead, the Lite method will enable rapid synthesis of the latest PTA data, offering preliminary GW constraints before the superior full dataset combinations are available.

astro-ph.HE↗

arXiv2025

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncertainty. Agents must not only gather and interpret vast amounts of dynamic information but also integrate diverse data sources, weigh uncertainties, and adapt predictions based on emerging trends, just as human experts do in fields like politics, economics, and finance. Despite its importance, no large-scale benchmark exists for evaluating agents on future prediction, largely due to challenges in handling real-time updates and retrieving timely, accurate answers. To address this, we introduce $\textbf{FutureX}$, a dynamic and live evaluation benchmark specifically designed for LLM agents performing future prediction tasks. FutureX is the largest and most diverse live benchmark for future prediction, supporting real-time daily updates and eliminating data contamination through an automated pipeline for question gathering and answer collection. We evaluate 25 LLM/agent models, including those with reasoning, search capabilities, and integration of external tools such as the open-source Deep Research Agent and closed-source Deep Research models. This comprehensive evaluation assesses agents' adaptive reasoning and performance in dynamic environments. Additionally, we provide in-depth analyses of agents' failure modes and performance pitfalls in future-oriented tasks, including the vulnerability to fake web pages and the temporal validity. Our goal is to establish a dynamic, contamination-free evaluation standard that drives the development of LLM agents capable of performing at the level of professional human analysts in complex reasoning and predictive thinking.

cs.AI↗