arXiv subjects

Chi Lu

Publications and source records attributed to Chi Lu.

At least 19 recordsLinked to original sources

arXiv2026

Load-Path Redistribution and Damage Asymmetry in Reinforced Concrete Beams under Eccentric Drop-Weight Impact: A Coupled SPH--FEM Study

Reinforced concrete (RC) beams under impact are commonly assessed using central-impact configurations, but practical impacts may deviate from midspan and create unequal shear spans. This study investigates how impact eccentricity changes force transfer and damage development using a validated coupled smoothed particle hydrodynamics--finite element method (SPH--FEM) model. Concrete is modeled with SPH particles, while reinforcement, supports, and the impactor are modeled with FEM solid elements. After validation against central drop-weight tests, full-span eccentric-impact cases are compared with matched short-span references. The first contact-force peak changes only slightly with eccentricity, whereas the response distribution changes clearly. At the largest eccentricity, shorter-span shear reaches up to 2.23 times the central-impact value, showing shear-dominated redistribution. Absorbed energy per unit length follows the same trend in shorter-span, reaching up to 4.29 times the longer-span-side value. Matched references show that full-span eccentric beams can develop up to 18.4 kN higher local shear than symmetric short-span beams. Damage fields shift from symmetric central damage to asymmetric shorter-span-side damage with clearer fragmentation in low-strength cases. Eccentric impact should therefore be evaluated as a full-span shear-transfer and damage-asymmetry problem.

cs.CE↗

arXiv2026

RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems

Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes. While LLM-based agents can automate this trial-and-error process, allowing the LLM to both select modification directions and generate concrete hypotheses often leads to unstable search under limited experiment budgets. Inspired by the above challenge, we propose RecHarness, a Bandit-Routed Agentic Harness for automated recommender model optimization. RecHarness separates the optimization process into two steps: a bandit router selects the next modification direction according to historical validation feedback, while the LLM generates a concrete optimization hypothesis and executable code edit within the selected direction. To sustain long-horizon exploration, RecHarness uses a jump-basin mechanism to activate a structural-jump arm when local edits stagnate. Across multiple recommendation tasks, datasets, and model backbones, RecHarness achieves more stable performance improvements and uses limited trial budgets more effectively than LLM-reasoning search. During a 7-day online A/B test on a large-scale short-video advertising platform, the selected candidate improves ADVV by 2.084%, Revenue by 0.534%, and Exposure by 0.559%. Code is available at https://github.com/6lyc/RecHarness.

cs.IR↗

arXiv2026

Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation

Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space with the recommender's ID space via post-training (e.g., SFT and RL) remains challenging. Existing LLM4Rec paradigms are bottlenecked by two main issues: (1) the difficulty of measuring and improving chain-of-thought (CoT) quality in open-domain recommendation during SFT, and (2) the neglect of the trade-off between LLM semantic rewards and recommendation preference rewards during RL alignment. Inspired by these challenges, we present Taiji, a novel LLM-as-Enhancer framework designed for industrial recommender systems. To overcome the SFT bottleneck, we utilize reverse-engineered reasoning and open-ended rejection sampling to generate high-quality, domain-specific CoT data. To resolve the RL alignment issue, we propose Pareto Optimal Policy Optimization (POPO), which adaptively adjusts cross-domain reward weights. Theoretically, it achieves an optimal trade-off between the semantic world knowledge of LLMs and the collaborative ID features representing online user preferences. Extensive offline evaluations and online A/B tests validate the effectiveness of Taiji. Deployed on Kuaishou's advertising platform since May 2026, Taiji currently serves over 400 million users daily, yielding significant commercial revenue and demonstrating its robust scalability in web-scale environments.

cs.IR↗

arXiv2026

Reinforced Preference Optimization for Reasoning-Augmented Recommendations

Recommender systems are critical for delivering personalized content across digital platforms, and recent advances in Large Language Models (LLMs) offer new opportunities to enhance them with richer world knowledge and explicit reasoning capabilities. With the help of reasoning knowledge, recommendations can better infer users' underlying intents, adapt to evolving preferences, and leverage semantic relationships for improved accuracy and interpretability. However, existing reasoning-based recommendation methods often fail to fully align the LLM's reasoning process with recommendation-specific objectives due to structural disruption during integration and difficulties in translating free-form generation into accurate item predictions. In this paper, we introduce RPORec, a reinforced preference optimization framework that unifies an LLM backbone's reasoning ability with a dedicated recommendation head (Rechead) for precise item retrieval. RPORec comprises two stages: (1) Reasoning-Augmented Recommendation Modeling, where high-quality Chain-of-Thought (CoT) reasoning is generated and used as auxiliary knowledge to guide the Rechead in learning recommendation-specific representations; and (2) Advanced Reasoning Refinement and Alignment, in which the trained Rechead produces verifiable rewards to fine-tune the LLM backbone via reinforcement learning, enhancing reasoning quality, structural consistency, and task relevance. Extensive experiments on public benchmarks and large-scale online deployments show that RPORec consistently outperforms state-of-the-art LLM-based recommendation methods, demonstrating the effectiveness of reasoning-augmented recommendation modeling in real-world systems.

cs.IR↗

arXiv2026

Programmable cavity-enhanced telecom quantum memory in thin-film lithium niobate

Spectrally multiplexed telecom quantum networks require quantum memories combining efficient storage with programmable frequency addressing. An integrated implementation should therefore unite a native telecom transition, efficient storage, and fast on-chip spectral control. Here we demonstrate a cavity-enhanced memory in an isotopically purified $^{167}\mathrm{Er}^{3+}$-doped thin-film lithium niobate microring. Long-lived hyperfine shelving states enable persistent, high-contrast atomic frequency comb preparation with a single-component lifetime of $277.6(52.6)$~s, while cavity impedance matching yields $23.3(5)\%$ on-chip efficiency for 100-ns storage. The intrinsic electro-optic response enables frequency-selective storage and routing at rates up to 20~MHz. We further store and retrieve time-energy-entangled telecom photons, violating an entanglement-witness bound by more than 11 standard deviations. Our results establish erbium-doped thin-film lithium niobate as a programmable light--matter interface for spectrally multiplexed quantum networks.

quant-ph↗

arXiv2026

Sequential Regression for Continuous Value Prediction using Residual Quantization

Continuous value prediction plays a crucial role in industrial-scale recommendation systems, including tasks such as predicting users' watch-time and estimating the gross merchandise value (GMV) in e-commerce transactions. However, it remains challenging due to the highly complex and long-tailed nature of the data distributions. Existing generative approaches rely on rigid parametric distribution assumptions, which fundamentally limits their performance when such assumptions misalign with real-world data. Overly simplified forms cannot adequately model real-world complexities, while more intricate assumptions often suffer from poor scalability and generalization. To address these challenges, we propose a residual quantization (RQ)-based sequence learning framework that represents target continuous values as a sum of ordered quantization codes, predicted recursively from coarse to fine granularity with diminishing quantization errors. We introduce a representation learning objective that aligns RQ code embedding space with the ordinal structure of target values, allowing the model to capture continuous representations for quantization codes and further improving prediction accuracy. We perform extensive evaluations on public benchmarks for lifetime value (LTV) and watch-time prediction, alongside a large-scale online experiment for GMV prediction on an industrial short-video recommendation platform. The results consistently show that our approach outperforms state-of-the-art methods, while demonstrating strong generalization across diverse continuous value prediction tasks in recommendation systems.

cs.IR↗

arXiv2026

RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment

Integrating large language model (LLM) representations into multimodal recommendation has shown promise, yet a fundamental challenge remains largely overlooked: the semantic heterogeneity between generative LM representations and the ID-based collaborative signals that recommendation systems rely on. Naively injecting LM features without alignment degrades recommendation performance rather than improving it. To resolve this, we propose RecGOAT, a dual-granularity semantic alignment framework built on graph neural networks and optimal transport theory. RecGOAT first enriches collaborative semantics through multimodal attentive graphs that capture item-item, user-item, and user-user relationships, initializing user representations via LLM-inferred behavioral preferences. It then aligns LM-derived modality representations with recommendation IDs at two complementary granularities: (1) instance-level alignment via cross-modal contrastive learning (CMCL), which produces discriminative per-sample representations; and (2) distribution-level alignment via optimal adaptive transport (OAT), which minimizes the 1-Wasserstein distance between ID distributions and LLM semantics to produce a unified, consistently aligned feature space. Theoretically, we prove that the unified representation achieves strictly lower target error than any single-modality representation, with the gap bounded by the Wasserstein distance and the InfoNCE loss, providing rigorous guarantees for both alignment consistency and fusion comprehensiveness. Extensive experiments on three public benchmarks demonstrate state-of-the-art performance. Deployment on a large-scale online advertising platform further validates RecGOAT's industrial scalability. Our code is available at https://github.com/6lyc/RecGOAT-LLM4Rec.

cs.IR↗

arXiv2026

FITMM: Adaptive Frequency-Aware Multimodal Recommendation via Information-Theoretic Representation Learning

Multimodal recommendation aims to enhance user preference modeling by leveraging rich item content such as images and text. Yet dominant systems fuse modalities in the spatial domain, obscuring the frequency structure of signals and amplifying misalignment and redundancy. We adopt a spectral information-theoretic view and show that, under an orthogonal transform that approximately block-diagonalizes bandwise covariances, the Gaussian Information Bottleneck objective decouples across frequency bands, providing a principled basis for separate-then-fuse paradigm. Building on this foundation, we propose FITMM, a Frequency-aware Information-Theoretic framework for multimodal recommendation. FITMM constructs graph-enhanced item representations, performs modality-wise spectral decomposition to obtain orthogonal bands, and forms lightweight within-band multimodal components. A residual, task-adaptive gate aggregates bands into the final representation. To control redundancy and improve generalization, we regularize training with a frequency-domain IB term that allocates capacity across bands (Wiener-like shrinkage with shut-off of weak bands). We further introduce a cross-modal spectral consistency loss that aligns modalities within each band. The model is jointly optimized with the standard recommendation loss. Extensive experiments on three real-world datasets demonstrate that FITMM consistently and significantly outperforms advanced baselines.

cs.IR↗

arXiv2025

Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation

Multimodal recommendation aims to integrate collaborative signals with heterogeneous content such as visual and textual information, but remains challenged by modality-specific noise, semantic inconsistency, and unstable propagation over user-item graphs. These issues are often exacerbated by naive fusion or shallow modeling strategies, leading to degraded generalization and poor robustness. While recent work has explored the frequency domain as a lens to separate stable from noisy signals, most methods rely on static filtering or reweighting, lacking the ability to reason over spectral structure or adapt to modality-specific reliability. To address these challenges, we propose a Structured Spectral Reasoning (SSR) framework for frequency-aware multimodal recommendation. Our method follows a four-stage pipeline: (i) Decompose graph-based multimodal signals into spectral bands via graph-guided transformations to isolate semantic granularity; (ii) Modulate band-level reliability with spectral band masking, a training-time masking with a prediction-consistency objective that suppresses brittle frequency components; (iii) Fuse complementary frequency cues using hyperspectral reasoning with low-rank cross-band interaction; and (iv) Align modality-specific spectral features via contrastive regularization to promote semantic and structural consistency. Experiments on three real-world benchmarks show consistent gains over strong baselines, particularly under sparse and cold-start settings. Additional analyses indicate that structured spectral modeling improves robustness and provides clearer diagnostics of how different bands contribute to performance.

cs.IR↗

arXiv2025

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation

The extensive world knowledge and powerful reasoning capabilities of large language models (LLMs) have attracted significant attention in recommendation systems (RS). Specifically, The chain of thought (CoT) has been shown to improve the performance of LLMs on complex reasoning tasks for RS. However, due to the fact that LLMs often suffer from hallucination issues, there is no guarantee that their reasoning CoT is effective. A key challenge is to further enhance the recommendation capabilities of LLMs through effective CoT reasonings. Therefore, we propose \textbf{TrackRec}, a framework designed to enhance reasoning capabilities of LLMs for RS. TrackRec specifically focuses on accurately inferring recommendation CoT \textbf{(RecCoT)} for user preference using the knowledge from LLMs. This RecCoT can serve both as an explanation for the LLM's completion of recommendation tasks and as auxiliary features to assist recommendation models in accomplishing recommendation tasks. TrackRec consists of a RecCoT generator $(G)$ and a RecCoT validator $(V)$. Furthermore, we design alternating feedback learning mechanism that $G$ undergoes direct preference optimization via feedback from $V$ to produce increasingly accurate RecCoT aligned with $V$'s standards. Meanwhile, $V$ is fine-tuned using the inference feedback from $G$ to enhance its validation capabilities in alignment with recommendation tasks. Through iterative alternating feedback learning between $G$ and $V$, TrackRec continuously improves the user preference analysis capability of $G$ and the validation capacity of $V$. Extensive experiments demonstrate the effectiveness of our approach, showing that it surpasses state-of-the-art methods. Moreover, TrackRec has been deployed on a lagre advertising platform with hundreds of millions of users, achieving substantial gains.

cs.IR↗

arXiv2025

R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems

Harnessing Large Language Models (LLMs) for recommendation systems has emerged as a prominent avenue, drawing substantial research interest. However, existing approaches primarily involve basic prompt techniques for knowledge acquisition, which resemble System-1 thinking. This makes these methods highly sensitive to errors in the reasoning path, where even a small mistake can lead to an incorrect inference. To this end, in this paper, we propose $R^{4}$ec, a reasoning, reflection and refinement framework that evolves the recommendation system into a weak System-2 model. Specifically, we introduce two models: an actor model that engages in reasoning, and a reflection model that judges these responses and provides valuable feedback. Then the actor model will refine its response based on the feedback, ultimately leading to improved responses. We employ an iterative reflection and refinement process, enabling LLMs to facilitate slow and deliberate System-2-like thinking. Ultimately, the final refined knowledge will be incorporated into a recommendation backbone for prediction. We conduct extensive experiments on Amazon-Book and MovieLens-1M datasets to demonstrate the superiority of $R^{4}$ec. We also deploy $R^{4}$ec on a large scale online advertising platform, showing 2.2\% increase of revenue. Furthermore, we investigate the scaling properties of the actor model and reflection model.

cs.IR↗

arXiv2025

Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoI

Decision Transformer (DT) has recently demonstrated strong generalizability in dynamic resource allocation within unmanned aerial vehicle (UAV) networks, compared to conventional deep reinforcement learning (DRL). However, its performance is hindered due to zero-padding for varying state dimensions, inability to manage long-term energy constraint, and challenges in acquiring expert samples for few-shot fine-tuning in new scenarios. To overcome these limitations, we propose an attention-enhanced prompt Decision Transformer (APDT) framework to optimize trajectory planning and user scheduling, aiming to minimize the average age of information (AoI) under long-term energy constraint in UAV-assisted Internet of Things (IoT) networks. Specifically, we enhance the convenional DT framework by incorporating an attention mechanism to accommodate varying numbers of terrestrial users, introducing a prompt mechanism based on short trajectory demonstrations for rapid adaptation to new scenarios, and designing a token-assisted method to address the UAV's long-term energy constraint. The APDT framework is first pre-trained on offline datasets and then efficiently generalized to new scenarios. Simulations demonstrate that APDT achieves twice faster in terms of convergence rate and reduces average AoI by $8\%$ compared to conventional DT.

eess.SP↗

arXiv2025

Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model

Large Language Models (LLMs) have garnered significant attention in Recommendation Systems (RS) due to their extensive world knowledge and robust reasoning capabilities. However, a critical challenge lies in enabling LLMs to effectively comprehend and extract insights from massive user behaviors. Current approaches that directly leverage LLMs for user interest learning face limitations in handling long sequential behaviors, effectively extracting interest, and applying interest in practical scenarios. To address these issues, we propose a Hierarchical Tree Search-based User Lifelong Behavior Modeling framework (HiT-LBM). HiT-LBM integrates Chunked User Behavior Extraction (CUBE) and Hierarchical Tree Search for Interest (HTS) to capture diverse interests and interest evolution of user. CUBE divides user lifelong behaviors into multiple chunks and learns the interest and interest evolution within each chunk in a cascading manner. HTS generates candidate interests through hierarchical expansion and searches for the optimal interest with process rating model to ensure information gain for each behavior chunk. Additionally, we design Temporal-Ware Interest Fusion (TIF) to integrate interests from multiple behavior chunks, constructing a comprehensive representation of user lifelong interests. The representation can be embedded into any recommendation model to enhance performance. Extensive experiments demonstrate the effectiveness of our approach, showing that it surpasses state-of-the-art methods.

cs.IR↗

arXiv2025

Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration

Reinforcement Learning (RL) has become a key approach for enhancing the reasoning capabilities of large language models. However, prevalent RL approaches like proximal policy optimization and group relative policy optimization suffer from sparse, outcome-based rewards and weak exploration incentives, limiting their effectiveness. Specifically, sparse rewards offer limited feedback, especially on difficult problems, and introduce biases favoring familiar trajectories over novel reasoning paths. These issues critically undermine performance on complex tasks that inherently require iterative reasoning. To overcome these challenges, we propose Intrinsic MotivAtion Guided exploratIoN for Enhanced reasoning (IMAGINE), which delivers dense rewards and encourages exploration. IMAGINE introduces three innovations: a trajectory-aware exploration reward that reduces token-level bias efficiently; an error-conditioned reward allocation that promotes efficient exploration on hard samples while stabilizing training; and an advantage-preserving integration mechanism that retains distributional integrity during learning. Experiments on four public datasets show that IMAGINE improves performance by 22.23% on AIME 2024.

cs.LG↗

arXiv2025

Entanglement distribution over metropolitan fiber using an on-chip broadband polarization entangled photon source

Entangled photon pairs are of crucial importance in quantum networks. For the future demands of large-scale and secure quantum communication, integrated photon sources are highly effective solutions. Here, we report entanglement distribution over a 30 km metropolitan area using on-chip broadband silicon nanowire biphoton polarization entangled source based on a silicon-on-insulator (SOI) platform. This source generates a continuous spectrum spanning the entire C-band (4.5 THz), achieving a locally detected coincidence counts of about 154 kHz within 100 GHz bandwidth, making it suitable for long-distance entanglement distribution among multiple users. By combining this source with quantum entanglement, enhanced by high-precision clock synchronization that achieves a standard deviation of 56.8 ps over 600 s, we observe a violation of the CHSH inequality by 27.8 standard deviations. Our results showcase the potential of silicon photonic technology as a scalable and practical platform for quantum technologies.

quant-ph↗

arXiv2024

Discrete and parallel frequency-bin entanglement generation from quantum frequency comb

Photons' frequency degree of freedom is promising to realize large-scale quantum information processing. Quantum frequency combs (QFCs) generated in integrated nonlinear microresonators can produce multiple frequency modes with narrow linewidth. Here, we utilize polarization-entangled QFCs to generate discrete frequency-bin entangled states. Fourteen pairs of polarization-entangled photons with different frequencies are simultaneously transformed into frequency-bin entangled states. The characteristic of frequency-bin entanglement is demonstrated by Hong-Ou-Mandel interference, which can be performed with single or multiple frequency pairs in parallel. Our work paves the way for harnessing large-scale frequency-bin entanglement and converting between different degrees of freedom in quantum information processing.

quant-ph↗

arXiv2024

SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without requiring visual inputs; SPORTU-video, consisting of 1,701 slow-motion video clips across 7 different sports and 12,048 QA pairs, designed to assess multi-level reasoning, from simple sports recognition to complex tasks like foul detection and rule application. We evaluate four prevalent LLMs mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting on the SPORTU-text part. We evaluate four LLMs using few-shot learning and chain-of-thought (CoT) prompting on SPORTU-text. GPT-4o achieves the highest accuracy of 71%, but still falls short of human-level performance, highlighting room for improvement in rule comprehension and reasoning. The evaluation for the SPORTU-video part includes 7 proprietary and 6 open-source MLLMs. Experiments show that models fall short on hard tasks that require deep reasoning and rule-based understanding. Claude-3.5-Sonnet performs the best with only 52.6% accuracy on the hard task, showing large room for improvement. We hope that SPORTU will serve as a critical step toward evaluating models' capabilities in sports understanding and reasoning.

cs.CV↗

arXiv2023

Polarization-entangled quantum frequency comb from a silicon nitride microring resonator

Integrated microresonator facilitates the realization of quantum frequency comb (QFC), which provides a large number of discrete frequency modes with broadband spectral range and narrow linewidth. However, all previous demonstrations have focused on the generation of energy-time or time-bin entangled photons from QFC. Realizing polarization-entangled quantum frequency comb, which is the important resource for fundamental study of quantum mechanics and quantum information applications, remains challenging. Here, we demonstrate, for the first time, a broadband polarization-entangled quantum frequency comb by combining an integrated silicon nitride micro-resonator with a Sagnac interferometer. With a free spectral range of about 99 GHz and a narrow linewidth of about 190 MHz, our source provides 22 polarization entangled photons pairs with frequency covering the whole telecom C-band. The entanglement fidelities for all 22 pairs are above 81%, including 17 pairs with fidelities higher than 90%. Our demonstration paves the way for employing the polarization-entangled quantum frequency comb in quantum network using CMOS technology as well as standard dense wavelength division multiplexing technology.

quant-ph↗