Searcharxiv⌕ Search

arXiv subjects

Qiang Luo

Publications and source records attributed to Qiang Luo.

At least 19 recordsLinked to original sources
arXiv2026

LMP-GNN: Probabilistic Reconstruction of Missing Lane Counts for Signed Max-Pressure Traffic Signal Control

Adaptive traffic-signal control relies on timely lane-level observations, yet detector faults, visual obstruction, and communication failures can make part of the traffic state unavailable and distort signal decisions. Prior work has separately advanced traffic-data imputation, state restoration, and estimated-state control. A gap remains at their interface. It is still unclear how to reconstruct only missing lane counts probabilistically using information available at the current decision, preserve all observed measurements, and trace the consequences through an unchanged Signed Max-Pressure controller. To address this gap, we propose LMP-GNN, a compact lane-movement graph neural network that predicts a mean and marginal uncertainty for each lane. Three transparent input rules convert these outputs into missing-lane controller inputs, while observed counts, legal phases, pressure calculation, and phase selection remain unchanged. This design isolates reconstruction effects from policy redesign and evaluates whether they survive lane recovery, pressure and phase fidelity, and closed-loop traffic. A comprehensive study on five CityFlow networks includes additional checks of demand variation, learned comparators, architecture, efficiency, and SUMO transfer. LMP-GNN reconstructs missing lane states accurately and generally preserves controller decisions better than a deterministic Road Mean baseline. Fixed Lane Discount reduces accrued average travel time by up to 13.74% under correlated missingness, while severe random loss reverses the benefit. Compared with two decision-time learned adaptations, the retained model uses 89.4-96.6% fewer parameters and achieves 81.1-95.0% lower median model-path latency. Overall, LMP-GNN provides a lightweight and auditable reconstruction-to-control interface with verified traffic benefits and explicit operating boundaries.

eess.SY↗
arXiv2026

Spin Splitter without Spin-Split Bands: A Reconfigurable Altermagnetic Texture

The altermagnetic spin-splitter effect converts an electric field into a transverse pure spin current, with no net magnetization and no charge-Hall counterpart. In established materials this function is tied to crystal-fixed spin-split bands that lock the polarization axis to the lattice. We show that the noncoplanar counter-spiral ground state of a frustrated honeycomb magnet instead carries the altermagnetic operation through a $\mathbf Q$-locked helicity mirror $g$. The mirror selects the spin-current polarization and forbids the perpendicular one, while an antitranslation $\Theta$ forbids even-parity spin splitting. Band splitting and spin-splitter response therefore rest on different symmetry elements. Either element alone enforces the charge-Hall zero---a redundancy absent from other spin--orbit-free noncollinear routes---and a charge Hall appears only when both elements are removed. Hole doping then realizes a \emph{spin splitter without spin-split bands}---the symmetry-allowed odd-parity residual below $2\times10^{-7}$ of the hopping $t$ at the Fermi level---with $\sigma_H^{(s_y)}=0.082\,e^2/h$ without spin--orbit coupling and with zero charge Hall response. Selecting among the three degenerate $\mathbf{Q}$ orientations rotates the polarization axis in exact $120^\circ$ steps at fixed magnitude and charge-Hall zero; the selection rules persist in a $32$-site cell accessible to programmable photonic and circuit lattices.

cond-mat.str-el↗
arXiv2026

WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models

Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs). Existing approaches typically enhance recommendation with explicit Chain-of-Thought (CoT) under the Think-then-Answer paradigm. However, generating lengthy rationales introduces substantial inference overhead, while fixed CoT templates struggle to model diverse, dynamic, and context-dependent user interests. We propose WhisperRec, an efficient latent reasoning framework for FRMs. WhisperRec compresses teacher-generated CoT into learnable latent reasoning tokens, enabling a Latent-Reason-then-Answer paradigm that performs reasoning in latent space without producing verbose rationales. This design retains decision-relevant reasoning information while avoiding the latency bottleneck of autoregressive rationale generation. Specifically, it first introduces Multi-View Adaptive CoT (MV-ACoT) to construct diverse, high-quality supervision from complementary perspectives on user interests. MV-ACoT also adapts reasoning complexity to each instance, applying lightweight analysis to clear cases and targeted multi-factor reasoning to challenging ones. Building on a pre-trained FRM, WhisperRec then employs a three-stage Latent Reasoning Alignment procedure to progressively internalize teacher CoT into latent representations. Finally, curriculum-based post-training activates latent-token reasoning for downstream recommendation while preserving standard recommendation capability. Experiments on an industrial-scale Kuaishou dataset and the public Kuaishou LLM-Rec benchmark show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines. Compared with explicit CoT Think and No-Think variants, WhisperRec improves SID@64 by 17.44% and 9.33%, respectively, and achieves over 10x higher online inference throughput.

cs.IR↗
arXiv2026

Crossover and Changeover in Spin-1 Kitaev-$\Gamma$ Chain with Uniaxial Single-ion Anisotropy

Recent advances in bond-directional spin chains have revealed extensive emergent phenomena and unconventional criticality. Here we investigate the spin-1 Kitaev-$\Gamma$ chain with uniaxial single-ion anisotropy (SIA) using large-scale density-matrix renormalization group calculations and bosonization analysis. Tuning the SIA strength reveals a crossover from the Kitaev phase to the large-$D$ phase, evidenced by the excitation gap changing from quadratic to linear, the coexistence and smooth evolution of spin-nematic and string order parameters, and the suppression of the double-peak specific heat. For negative SIA, we uncover a changeover from a first-order transition to a continuous one between the dimerized and Haldane phases. The continuous transition belongs to the \textrm{SU(2)$_2$} Wess-Zumino-Witten universality class with central charge $c=3/2$, a rare instance in a system without continuous symmetry. Our results establish the Kitaev-$\Gamma$ chain as a minimal platform for controlling crossover and changeover phenomena.

cond-mat.str-el↗
arXiv2026

Beyond-adiabatic flat Chern bands from a double-helix skyrmion crystal

A central challenge in flat-band engineering is suppressing kinetic energy without sacrificing Berry curvature. We show that a double-helix skyrmion crystal (DHSKX)--two sublattice-resolved skyrmion textures locked at opposite helicities, obtained here as the classical ground state of a frustrated honeycomb spin model--provides such a route under double exchange. The key mechanism is a single real-space organization, phase clustering: the $\pi$-locked helicities expel the wave function's phase winding from the skyrmion cores, and the magnetic $C_3$ symmetry pins it into three phase-locked clusters whose distributed destructive interference cancels net transport while preserving the Berry curvature. Ordinary skyrmion crystals, even with the same symmetry, do not develop this organization. Phase clustering yields isolated flat $|C| = 1$ Chern bands over broad coupling windows, one of which surpasses the adiabatic reference in quantum geometry at intermediate coupling. In this beyond-adiabatic window, band-projected exact diagonalization gives finite-size evidence consistent with $\nu = 1/3$ Laughlin-type fractional-Chern-insulator physics; the same texture also hosts a higher-Chern ($C = -2$) flat band. Built from site-resolved complex hoppings alone, the DHSKX architecture is directly programmable in topolectric, acoustic, and photonic platforms.

cond-mat.str-el↗
arXiv2026

POEM: Partial-Order Enhanced Real-Time Sequential Modeling for Recommendation

Real-time recommendation systems suffer from the dynamic drift of user interests and varying contextual conditions. Conventional sequential recommendation models only exploit static historical click sequences, which fail to capture instant preference changes and overlook structured signals hidden within the multi-stage ranking pipeline of industrial recommendation systems. To tackle these limitations, we propose POEM (Partial-Order Enhanced Modeling), a new real-time sequential modeling framework built upon intrinsic partial-order relations from the recommendation cascade. POEM takes real-time multi-task ranking scores (including predicted CTR and predicted watch duration) generated by upstream ranking modules as supervision to construct dynamic partial-order sequences, supporting fine-grained real-time interest modeling and consistent optimization between system ranking targets and user behavioral patterns. We summarize our core contributions as three aspects: (1) a partial-order guided sequence construction paradigm, which enriches vanilla chronological sequences via dynamic grouping and sampling conditioned on real-time ranking scores to reassess user interests per request; (2) a multi-objective score fusion module that unifies heterogeneous ranking signals into a compact quintuple representation with normalized rank-aware weighting; (3) a hierarchical sample learning strategy, which adopts system-favored high-ranked items and user positive feedback (e.g., long-duration watched videos) as positive instances, paired with graph-mined hard negatives and a margin-based pairwise loss for robust training. Fully deployed on Kuaishou online traffic, POEM achieves significant online gains: average per-user watch time lifts by 0.249% on the KS Single Page and 0.213% on the KS Lite Page.

cs.IR↗
arXiv2026

From Extraction to Navigation: Progressive Retrieval with Indirectly Infinite Depth

Modern large-scale recommender retrieval is shifting from static similarity matching to dynamic item space navigation, framing retrieval as iterative goal-driven graph traversal. Conventional item-to-item (i2i) methods fall into the "interest tunnel" and fail to excavate deep user interests, while existing index-based retrieval suffers from persistent "search drift", caused by static entry nodes and fixed graph topologies unable to track shifting real-time user intent. To resolve the above defects, we present IID-Nav, a framework modeling retrieval as stateful autonomous graph exploration with three core contributions: (1) A goal-aware navigation policy substituting passive neighborhood expansion with active intent routing supervised by a target discriminator; (2) A recursive state evolution mechanism supporting Indirectly Infinite Depth (IID) via cross-request state reuse, which enables logical unlimited-depth graph traversal without linearly rising inference latency; (3) A trajectory-aligned training paradigm equipped with graph hard negative sampling to stabilize optimization over full navigation paths. Evaluations on billion-level industrial datasets show IID-Nav surpasses mainstream retrieval baselines under strict latency budgets. Empirical results verify that our method alleviates search drift remarkably and retains high precision for deep retrieval paths, offering an efficient, robust retrieval solution for industrial recommendation systems.

cs.IR↗
arXiv2026

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the agents themselves -- making the system not merely automated, but self-improving.

cs.AI↗
arXiv2026

OneReason Technical Report

Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the reasoning-style ``think before answer'' paradigm in the LLM field, we conduct preliminary studies (i.e., OneRec-Think, OpenOneRec) to explore reasoning capability in generative recommendation. Nevertheless, we notice an unexpected phenomenon: the thinking mode does not show advantages over the non-thinking mode. Drawing insights from recent findings on CoT robustness in multi-modal language models, we argue that effective reasoning in recommendation rests on two factors: perception, the ability to ground itemic tokens in their underlying language semantics, and cognition, the ability to reorganize a user's behavior sequence into coherent latent interest points. We therefore propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL to enhance the thinking ability.

cs.IR↗
arXiv2026

Stabilization of zigzag order in NiPS$_3$ via positive biquadratic interaction

Despite extensive research, the precise spin Hamiltonian of the van der Waals antiferromagnet NiPS$_3$ -- which hosts a zigzag-ordered ground state -- remains debated. While consensus has emerged on ferromagnetic nearest-neighbor ($J_1$) and antiferromagnetic third-nearest-neighbor ($J_3$) Heisenberg interactions, recent studies suggest a biquadratic ($B$) exchange term may also play a role, though its estimated magnitude varies widely. To address this controversy, we perform density functional theory calculations and extract a positive biquadratic interaction with $B/J_3 \approx 0.44$. Within the minimal $J_1$-$J_3$-$B$ model, we show that these parameters naturally stabilize zigzag ordering using minimally augmented spin-wave theory. Density-matrix renormalization group calculations further validate our extracted parameters as a reasonable description of the ground state. Although fully resolving the spin Hamiltonian of NiPS$_3$ requires further investigation, our findings provide new insights into its biquadratic interaction.

cond-mat.str-el↗
arXiv2026

MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation

Recommender systems (RecSys) are increasingly emphasizing scaling, leveraging larger architectures and more interaction data to improve personalization. Yet, despite the optimizer's pivotal role in training, modern RecSys pipelines almost universally default to Adam/AdamW, with limited scrutiny of whether these choices are truly optimal for recommendation. In this work, we revisit optimizer design for scalable recommendation and introduce MuonRec, the first framework that brings the recently proposed Muon optimizer to RecSys training. Muon performs orthogonalized momentum updates for 2D weight matrices via Newton-Schulz iteration, promoting diverse update directions and improving optimization efficiency. We develop an open-source training recipe for recommendation models and evaluate it across both traditional sequential recommenders and modern generative recommenders. Extensive experiments demonstrate that MuonRec reduces converged training steps by an average of 32.4\% while simultaneously improving final ranking quality. Specifically, MuonRec yields consistent relative gains in NDCG@10, averaging 12.6\% across all settings, with particularly pronounced improvements in generative recommendation models. These results consistently outperform strong Adam/AdamW baselines, positioning Muon as a promising new optimizer standard for RecSys training. Our code is available.

cs.IR↗
arXiv2026

GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder

While generative recommendations (GR) possess strong sequential reasoning capabilities, they face significant challenges when processing extremely long user behavior sequences: the high computational cost forces practical sequence lengths to be limited, preventing models from capturing users' lifelong interests; meanwhile, the inherent "recency bias" of attention mechanisms further weakens learning from long-term history. To overcome this bottleneck, we propose GEMs (Generative rEcommendation with a Multi-stream decoder), a novel and unified framework designed to break the long-sequence barrier by capturing users' lifelong interaction sequences through a multi-stream perspective. Specifically, GEMs partitions user behaviors into three temporal streams$\unicode{x2014}$Recent, Mid-term, and Lifecycle$\unicode{x2014}$and employs tailored inference schemes for each: a one-stage real-time extractor for immediate dynamics, a lightweight indexer for cross attention to balance accuracy and cost for mid-term sequences, and a two-stage offline-online compression module for lifelong modeling. These streams are integrated via a parameter-free fusion strategy to enable holistic interest representation. Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-of-the-art methods in recommendation accuracy. Notably, GEMs is the first lifelong GR framework successfully deployed in a high-concurrency industrial environment, achieving superior inference efficiency while processing user sequences of over 100,000 interactions.

cs.IR↗
arXiv2026

OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation

Live-streaming recommender system serves as critical infrastructure that bridges the patterns of real-time interactions between users and authors. Similar to traditional industrial recommender systems, live-streaming recommendation also relies on cascade architectures to support large-scale concurrency. Recent advances in generative recommendation unify the multi-stage recommendation process with Transformer-based architectures, offering improved scalability and higher computational efficiency. However, the inherent complexity of live-streaming prevents the direct transfer of these methods to live-streaming scenario, where continuously evolving content, limited lifecycles, strict real-time constraints, and heterogeneous multi-objectives introduce unique challenges that invalidate static tokenization and conventional model framework. To address these issues, we propose OneLive, a dynamically unified generative recommendation framework tailored for live-streaming scenario. OneLive integrates four key components: (i) A Dynamic Tokenizer that continuously encodes evolving real-time live content fused with behavior signal through residual quantization; (ii) A Time-Aware Gated Attention mechanism that explicitly models temporal dynamics for timely decision making; (iii) An efficient decoder-only generative architecture enhanced with Sequential MTP and QK Norm for stable training and accelerated inference; (iv) A Unified Multi-Objective Alignment Framework reinforces policy optimization for personalized preferences.

cs.IR↗
arXiv2026

Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation

Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a transformative paradigm, they face hurdles in effectively modeling extensive historical sequences. To address this challenge, we propose GLASS, a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search. We first introduce SID-Tier, a module that maps long-term interactions into a unified interest vector to enhance the prediction of the initial SID token. Unlike traditional retrieval models that struggle with massive item spaces, SID-Tier leverages the compact nature of the semantic codebook to incorporate cross features between the user's long-term history and candidate semantic codes. Furthermore, we present semantic hard search, which utilizes generated coarse-grained semantic ID as dynamic keys to extract relevant historical behaviors, which are then fused via an adaptive gated fusion module to recalibrate the trajectory of subsequent fine-grained tokens. To address the inherent data sparsity in semantic hard search, we propose two strategies: semantic neighbor augmentation and codebook resizing. Extensive experiments on two large-scale real-world datasets, TAOBAO-MM and KuaiRec, demonstrate that GLASS outperforms state-of-the-art baselines, achieving significant gains in recommendation quality. Our codes are made publicly available to facilitate further research in generative recommendation.

cs.IR↗
arXiv2026

ALPBench: A Benchmark for Attribution-level Long-term Personal Behavior Understanding

Recent advances in large language models have highlighted their potential for personalized recommendation, where accurately capturing user preferences remains a key challenge. Leveraging their strong reasoning and generalization capabilities, LLMs offer new opportunities for modeling long-term user behavior. To systematically evaluate this, we introduce ALPBench, a Benchmark for Attribution-level Long-term Personal Behavior Understanding. Unlike item-focused benchmarks, ALPBench predicts user-interested attribute combinations, enabling ground-truth evaluation even for newly introduced items. It models preferences from long-term historical behaviors rather than users' explicitly expressed requests, better reflecting enduring interests. User histories are represented as natural language sequences, allowing interpretable, reasoning-based personalization. ALPBench enables fine-grained evaluation of personalization by focusing on the prediction of attribute combinations task that remains highly challenging for current LLMs due to the need to capture complex interactions among multiple attributes and reason over long-term user behavior sequences.

cs.IR↗
arXiv2026

Robust and Generalized Humanoid Motion Tracking

Learning a general humanoid whole-body controller is challenging because practical reference motions can exhibit noise and inconsistencies after being transferred to the robot domain, and local defects may be amplified by closed-loop execution, causing drift or failure in highly dynamic and contact-rich behaviors. We propose a dynamics-conditioned command aggregation framework that uses a causal temporal encoder to summarize recent proprioception and a multi-head cross-attention command encoder to selectively aggregate a context window based on the current dynamics. We further integrate a fall recovery curriculum with random unstable initialization and an annealed upward assistance force to improve robustness and disturbance rejection. The resulting policy requires only about 3.5 hours of motion data and supports single-stage end-to-end training without distillation. The proposed method is evaluated under diverse reference inputs and challenging motion regimes, demonstrating zero-shot transfer to unseen motions as well as robust sim-to-real transfer on a physical humanoid robot.

cs.RO↗
arXiv2026

OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce

In the wave of generative recommendation, we present OneMall, an end-to-end generative recommendation framework tailored for e-commerce services at Kuaishou. Our OneMall systematically unifies the e-commerce's multiple item distribution scenarios, such as Product-card, short-video and live-streaming. Specifically, it comprises three key components, aligning the entire model training pipeline to the LLM's pre-training/post-training: (1) E-commerce Semantic Tokenizer: we provide a tokenizer solution that captures both real-world semantics and business-specific item relations across different scenarios; (2) Transformer-based Architecture: we largely utilize Transformer as our model backbone, e.g., employing Query-Former for long sequence compression, Cross-Attention for multi-behavior sequence fusion, and Sparse MoE for scalable auto-regressive generation; (3) Reinforcement Learning Pipeline: we further connect retrieval and ranking models via RL, enabling the ranking model to serve as a reward signal for end-to-end policy retrieval model optimization. Extensive experiments demonstrate that OneMall achieves consistent improvements across all e-commerce scenarios: +13.01\% GMV in product-card, +15.32\% Orders in Short-Video, and +2.78\% Orders in Live-Streaming. OneMall has been deployed, serving over 400 million daily active users at Kuaishou.

cs.IR↗
arXiv2026

Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers

Leveraging the vast open-world knowledge and understanding capabilities of Large Language Models (LLMs) to develop general-purpose, semantically-aware recommender systems has emerged as a pivotal research direction in generative recommendation. However, existing methods face bottlenecks in constructing item identifiers. Text-based methods introduce LLMs' vast output space, leading to hallucination, while methods based on Semantic IDs (SIDs) encounter a semantic gap between SIDs and LLMs' native vocabulary, requiring costly vocabulary expansion and alignment training. To address this, this paper introduces Term IDs (TIDs), defined as a set of semantically rich and standardized textual keywords, to serve as robust item identifiers. We propose GRLM, a novel framework centered on TIDs, employs Context-aware Term Generation to convert item's metadata into standardized TIDs and utilizes Integrative Instruction Fine-tuning to collaboratively optimize term internalization and sequential recommendation. Additionally, Elastic Identifier Grounding is designed for robust item mapping. Extensive experiments on real-world datasets demonstrate that GRLM significantly outperforms baselines across multiple scenarios, pointing a promising direction for generalizable and high-performance generative recommendation systems.

cs.IR↗