Search arXiv⌕ Search

arXiv subjects

Jie Jiang

Publications and source records attributed to Jie Jiang.

At least 19 recordsLinked to original sources
arXiv2026

Universal Leading Quantum Stress Near the Schwarzschild Singularity

Determining the local quantum source near a spacelike singularity is essential for assessing semiclassical backreaction inside black holes. By standard point splitting, we provide, to our knowledge, the first complete numerical determination of the renormalized stress-energy tensor (RSET) of a massless scalar field at arbitrary curvature coupling in the four-dimensional Schwarzschild interior. Calculations in the Unruh and Hartle--Hawking states reach $r/M\simeq10^{-4}$, yielding a common leading $r^{-6}$ coefficient tensor and coupling-dependent anisotropic pressure ratios. Uniform estimates of the complete mode sums then establish a rigidity theorem: at each fixed coupling, any Hadamard-state change on the common interior evolution domain contributes only subleading stress. The leading tensor is therefore insensitive to time and directional dependence of the quantum environment, in contrast with state-dependent leading Cauchy-horizon coefficients in asymptotically flat Reissner--Nordström spacetime. Its directional null projections define positive, mixed-sign, and negative regimes in coupling and direction, specifying the local mean focusing source; at conformal coupling, all leading projections are positive.

gr-qc↗
arXiv2026

PRISM: Parallel Residual Iterative Sequence Model

Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear updates, while powerful iterative methods like Test-Time Training (TTT) break hardware parallelism due to two dimensions of serial dependency: token-level state reliance and step-level iteration loops. We propose PRISM (Parallel Residual Iterative Sequence Model) to resolve this tension. PRISM explicitly approximates the expressive gate-residual-direction iteration pattern of TTT in a parallelizable form. We employ a Write-Forget Decoupling strategy that isolates non-linearity within the injection operator. To bypass the serial dependency of explicit solvers, PRISM utilizes a two-stage proxy architecture: a short-convolution anchors the initial residual using local history energy, while a learned predictor estimates the refinement updates directly from the input. This design distills structural patterns associated with iterative correction into a parallelizable feedforward operator. Theoretically, we prove that this formulation achieves Rank-$L$ accumulation, structurally expanding the update scheme beyond the single-step Rank-$1$ bottleneck. Empirically, it achieves comparable performance to explicit optimization methods while achieving \textbf{174x higher throughput}. Codes are available in https://github.com/gpr-prism/prism/.

cs.LG↗
arXiv2026

The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction Circuits

Hybrid language models can improve capability as well as efficiency, raising the question of how architectural complementarity becomes learned computation. We examine the established induction roles of Carrying predecessor information, Matching a source by content, and Copying its value. How are these position-sensitive and content-based computations allocated across heterogeneous layers? We introduce layer-type-agnostic paired probes that track Carrying and Matching through a common block-update interface. In recurrent--global and local--global hybrids, Carrying concentrates in efficient layers and Matching in global receivers. The measured local contribution concentrates on lag one: the token immediately before the historical value. Changing predecessor support through lag-one masking, convolution removal, or early learning-rate reduction can relocate Carrying and Matching between stages. Source-key restoration and fixed-value selection trace the receiver's dependence on the prepared source. These interventions also change natural-text recall, with outcomes depending on configuration and target. Varying local windows and induction-enriched training text changes the early development of functional Carrying and Matching, connecting architectural priors and training evidence to formation timing. Together, the probes and interventions shift the explanatory focus upstream: the organization of Matching follows how Carrying is learned. The token before the value provides a concrete link between a hybrid's architecture, circuit development, and recall. Code is available in https://github.com/ckpassenger/bind-match-copy/tree/main.

cs.LG↗
arXiv2026

Discrete Coupling and Localized Motion for Pinching-Antenna Systems (PASS)

The practical implementation of pinching-antenna systems (PASS) is challenging due to hardware limitations in large-scale antenna movement and continuous radiation power adjustment. This paper proposes a practical PASS-enabled downlink multi-user multiple-input multiple-output communication framework that enables discrete radiation power control and localized discrete antenna movement. Specifically, a discrete coupling strength model is exploited to tune the radiation power at each pinching antenna (PA) through quantized coupling spacing levels. Moreover, each PA can only move among discrete locations within a limited region determined by the movement speed and duration. Based on the proposed framework, a joint optimization problem of the PA positions, coupling strength, and transmit beamforming is formulated. Considering waveguide attenuation, the total average power consumption is minimized, subject to each user's minimum SINR requirement and localized motion constraints. To address this coupled mixed-integer nonconvex optimization problem, a globally optimal branch-and-bound-based algorithm is first developed for the multi-waveguide single-user scenario. To further reduce complexity, a scalable genetic algorithm-assisted particle swarm optimization (GA-PSO) method is developed for the multi-waveguide multi-user scenario, where GA operations are incorporated to preserve population diversity and alleviate premature convergence. Simulation results demonstrate that the proposed design significantly reduces the power consumption compared with the conventional PASS schemes and MIMO architectures.

eess.SP↗
arXiv2026

ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling

Modeling ultra-long user behavior sequences is crucial for industrial recommendation and online advertising, yet directly feeding thousands of historical actions into ranking models is computationally prohibitive, while truncation discards long-range signals. Existing lifelong-interest methods retrieve target-relevant behaviors for each candidate, coupling long-sequence modeling with candidate scoring and repeated online cost. Recent target-independent compression methods enable cached user summaries, but often append query tokens at the sequence end and use bidirectional encoding, producing unordered and redundant summaries that overlook temporal structure. We propose ChronicleRec, a pre-train-and-transfer framework that compresses an ultra-long behavior sequence once into a chronologically ordered set of Chronicle Tokens. ChronicleRec applies a recency-aware multi-granularity merge, preserving recent behaviors while coarsening distant history. It then interleaves query tokens with the merged sequence and uses a causal encoder, so each query summarizes only the history before its temporal anchor. A multi-horizon design masks different recent-history windows across parallel branches to learn complementary long-range interests. The compressor is pre-trained with a mask-and-predict objective that reconstructs held-out recent behaviors from compressed older history, aligning historical signals with near-present intent. Since Chronicle Tokens are target-independent, they can be cached per user, decoupling ultra-long sequence modeling from online candidate scoring. Experiments on KuaiRand and Tencent AdLive show that ChronicleRec outperforms recent-window and single-pass compression baselines while approaching full-attention performance. Token analyses reveal temporally organized and complementary representations, and a seven-day online A/B test confirms significant production gains.

cs.IR↗
arXiv2026

Distillation as Probability Transport: Routed On-Policy Distillation

On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribution to scalar credit on individual tokens. Such credit indicates whether a token should gain or lose probability, yet leaves the corresponding redistribution unspecified. We recast OPD as teacher-guided probability transport and propose RouteOPD (Routed On-Policy Distillation), which decomposes local teacher--student disagreement into student-excess sources and teacher-deficit destinations and couples them into explicit transport pairs. RouteOPD optimizes pairwise log-odds toward jointly realizable targets obtained from a bounded teacher potential, while adapting the transport budget to the concentration of teacher demand. This formulation directs updates toward teacher-preferred destinations and controls their magnitude within a single transport operator. Experiments across four teacher--student settings and four mathematical-reasoning benchmarks demonstrate that RouteOPD consistently outperforms sampled reverse-KL OPD, with improvements accompanied by higher routing fidelity and lower background leakage. These results demonstrate the effectiveness of explicitly modeling probability transport in on-policy distillation.

cs.LG↗
arXiv2026

SiriusDeliver: Automating Data Warehouse Delivery at Tencent

Enterprise data warehouses (DWs) support business-critical analytics, but warehouse task delivery remains a complicated production process involving context retrieval, workflow configuration, code generation, platform submission, and failure diagnosis. Although large language models (LLMs) and coding agents have improved software development, they are insufficient for production DW delivery, which requires dependency-aware orchestration, lifecycle-aware artifact control, and continuous adaptation to evolving platform practices. We present SiriusDeliver, an end-to-end delivery automation agent for production warehouse task submission. SiriusDeliver integrates three components: a hierarchical delivery agent that orchestrates warehouse skills, an artifact lifecycle control module that verifies and revises artifacts before and after platform execution, and a trace-driven skill evolution mechanism that maintains reusable skills from delivery trajectories. We evaluate SiriusDeliver through offline datasets and large-scale production deployment on Tencent Cloud WeData. Offline experiments on real-world warehouse delivery cases show that SiriusDeliver improves delivery success and automation efficiency over representative baselines. During a two-month deployment across 6 business teams and 4 warehouse task types, SiriusDeliver served 3,600 monthly active users and supported 18,240 delivery sessions, achieving an 87.2% end-to-end success rate and a 73.5% autonomous submission rate. A one-month A/B test shows that SiriusDeliver reduces median delivery time from 228 to 23 minutes and engineer effort from 95 to 11 minutes, while maintaining comparable final delivery success.

cs.DB↗
arXiv2026

AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models

While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mounted camera, they inevitably suffer from perception forgetting as objects exit the field of view, and temporal task-progress forgetting} during multi-step execution. To overcome these bottlenecks, we propose AtlasVLA, a novel framework that transitions from direct reactive manipulation to proactive reasoning through a persistent world-ego state. AtlasVLA features a dual-memory architecture: a 4D Persistent World State Memory that lifts transient 2D observations into a globally updated, voxel-hashed spatial state to resolve visual blind spots, and an Ego-Working State Memory that tracks historical ego state and task progress. By conditioning a diffusion transformer (DiT) on this joint World-Ego state, AtlasVLA enables robust spatial reasoning. Extensive evaluations across LIBERO, RLBench, and real-world benchmarks demonstrate that AtlasVLA achieves state-of-the-art performance using solely a wrist camera. Remarkably, it decisively outperforms multi-view baselines, yielding absolute success rate improvements of 9.4% on LIBERO-Long and 17.5% in real-world long-horizon tasks.

cs.RO↗
arXiv2026

An Explicit Logistic Damping Criterion for Boundedness in a Fully Parabolic Keller--Segel System

We study the fully parabolic Keller--Segel system \[ u_t=Δu-χ\nabla\!\cdot(u\nabla v)+λu-μu^2, \qquad τv_t=Δv-v+u \] in a bounded smooth convex domain. For every fixed $τ>0$, we prove that \[ μ>\frac{Nχ}{4} \] guarantees global existence and uniform-in-time boundedness. This coefficient-explicit sufficient condition is independent of $τ$ and involves no embedding or maximal-regularity constants. To the best of our knowledge, it is the first coefficient-explicit boundedness criterion that remains unchanged for all $τ>0$ in arbitrary space dimension. The proof is built on a new auxiliary comparison function \[ Y_τ =u+\frac{χτ}{2}|\nabla v|^2-(τ-1)Δv, \] which satisfies a closed scalar parabolic inequality for every $τ>0$. When $τ\ge1$, this inequality yields a direct pointwise comparison and an explicit bound for $u$. When $0<τ<1$, it instead provides a uniform upper bound for $v$. Applying a parabolic squeezing argument to the transform $z=e^{-χv/2}$ then yields a uniform Hölder bound for $v$. Hölder--Sobolev interpolation and weighted maximal $L^p$-regularity subsequently give an $L^p$-bound for $u$ with sufficiently large $p$, and standard parabolic smoothing closes the argument.

math.AP↗
arXiv2026

StaleFlow: Staleness-Aware Data Management for Mitigating Data Skewness in Fully Disaggregated RL Post-Training

Reinforcement learning (RL) post-training has become pivotal for enhancing the capabilities of modern large models. A recent trend is to develop RL systems with a fully disaggregated architecture, which decouples the three RL phases (rollout, reward, and training) onto separate resources and executes them asynchronously. However, two critical data-level concerns arise: (1) asynchronous execution leads to data staleness in trajectories (the data generated by rollout) as the model parameters used in rollout may not be up to date, which impairs RL convergence; and (2) the length variation of trajectories introduces severe data skewness, leading to workload imbalance and degraded system performance. Existing systems fail to address these two concerns in a unified manner. Techniques that tightly control data staleness often constrain effective data skewness mitigation, while aggressive data skewness mitigation tends to exacerbate data staleness. As a result, systems are forced to trade off convergence for performance, or vice versa. To address this, we propose StaleFlow, an RL post-training system that jointly tackles data staleness and skewness. First, to control staleness, StaleFlow introduces a global consistency protocol that tracks the full lifecycle of each trajectory and constrains staleness. Second, to mitigate skewness, StaleFlow re-designs the RL system architecture by constructing data servers for trajectories and parameters to achieve flexible rollout coordination. Subsequently, we develop a suite of staleness-aware, throughput-oriented strategies to enhance system performance. Evaluations show that StaleFlow achieves up to 1.42-2.68$\times$ (1.18-1.91$\times$ on average) higher throughput than state-of-the-art systems, without compromising convergence. Our source code is available: https://github.com/psrl-project/psrl.

cs.DC↗
arXiv2026

UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent

Generative Recommendation (GR) reformulates recommendation as next-token generation over item Semantic IDs (SIDs) and has shown promise in industrial applications. However, extending GR to advertising is non-trivial, as advertising recommendation must jointly account for user relevance and commercial value. This creates a mismatch: high generation likelihood does not necessarily imply high advertising utility. As a result, valuable ads may be poorly distinguished in the SID space, pruned during autoregressive decoding, or missed when request-invalid branches consume limited beam capacity during online serving. To address this problem, we propose UniVA, a Unified Value Alignment framework for generative advertising recommendation. UniVA aligns commercial value across the entire pipeline of SID construction, autoregressive decoding, and online serving. Commercial SID Tokenization injects business attributes and bid information into SID construction. A Generation-as-Ranking SID Decoder then fuses generation scores with token-level value estimates during autoregressive decoding. {Finally, Value-Aware Constrained Serving restricts the fused decoding process to request-valid SID paths through a personalized trie.} Experiments on the Tencent WeChat Channels advertising platform show that UniVA achieves a 37.04\% relative improvement in offline Hit Rate@100 over the baseline and lifts gross merchandise value (GMV) by 1.5\% in online A/B tests.

cs.IR↗
arXiv2026

The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape

Online recommendation has traditionally taken place after a user enters a platform, which determines the candidate pool and the ranking shown to the user. LLM-based user agents enable a different recommendation process: a user specifies a need before choosing a platform, leaving platforms to compete for the user's attention, which we refer to as an agentic recommendation market. In our controlled LLM-based experiments across three product domains, we find this new setting of recommendation creates a tension between access and attention. Compared with traditional platform-centric recommendation, user-centric recommendation greatly expands the opportunity for relevant items to enter comparison; yet broader participation does not translate directly into effective exposure. Competition directly triggers platforms' strategic play: selectively positive explanations occupy 73--78% of first-ranked positions. When the user agent relates platforms' actions to subsequent user feedback, this share falls to 36--41%, while the chance of a user purchasing the relevant item increases. A user agent is therefore more than a ranker over a larger pool of candidates: its querying, ranking, and feedback mechanism governing who can compete, how scarce attention is allocated, and how earlier outcomes shape the evaluation of platforms directly affect user utility. Designing agentic recommendation therefore requires treating access, attention, and accountability as a joint mechanism design problem.

cs.AI↗
arXiv2026

Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising

Recent advances in LLM-based user simulation have shown promise for offline evaluation of recommendation and advertising systems. However, existing simulators typically infer user preferences from single-domain interaction histories and are primarily optimized to reproduce observable actions such as clicks. Consequently, they capture only a partial view of user preferences, while action-only prediction easily induces model shortcuts and limits both the fidelity and diagnostic value of simulation. To address these challenges, we propose DASH, a decision-aware user simulator that jointly generates thinking traces and predicts behavioral actions from heterogeneous cross-domain histories. DASH first introduces a Context Engineering stage that folds heterogeneous cross-domain histories into decision-relevant context, together with prompt optimization for effective reasoning over the folded context. To train a user simulator, DASH distills thinking trajectories from strong LLMs as SFT data, and further tailors a rubric-based reward model that evaluates thinking traces along form, content, and logic for RL training. Combined with the action reward, these signals jointly improve action prediction and thinking quality. Extensive experiments on real-world Tencent advertising data spanning five heterogeneous content domains demonstrate the effectiveness, efficiency, fidelity, and diagnostic value of DASH.

cs.IR↗
arXiv2026

Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates

Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that repeated reuse can turn this useful signal into excessive repulsion: as the learner moves away from a historical negative action, subsequent updates make that action increasingly remote without necessarily reducing its update strength. Our aggregate theory characterizes the resulting transition from a stable displacement beyond the positive-only target to persistent drift and the loss of finite stable equilibria; controlled strength sweeps show that an intermediate displacement can improve held-out reward. The relevant learner-relative coordinate is squared standardized distance for Gaussian policies and surprisal for categorical policies. We introduce Dynamic Remoteness-Aware Policy Optimization (DRPO), which leaves the negative update unchanged in the near field and exponentially attenuates its remote tail. DRPO restores eventual inward Gaussian drift for every fixed finite negative-to-positive mass ratio, yields an explicit ultimate-bound radius, and changes categorical support suppression from exponential to polynomial probability decay. External diagnostics and controlled interventions isolate remoteness-dependent policy geometry as a source of negative-update amplification and show that selective tapering can remove its far-field effect without discarding useful local feedback.

cs.LG↗
arXiv2026

NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems

Industrial advertising recommender systems are continually improved through architecture modifications, yet production iteration remains expert-intensive because coordinated changes to model topology, feature configuration, and interaction modules must satisfy strict interface, resource, and serving constraints. AutoML is limited to predefined search spaces, while generic coding agents verify runnability rather than recommender-specific semantic validity. Executable candidates may therefore violate architectural contracts, while the lack of structured reuse of semantic diagnostics and evaluation outcomes can lead to repeated invalid or ineffective modifications. We present NOVA, a verification-aware agent harness that organizes production architecture modification as multi-round search over concrete implementations within a fixed evaluation budget. At each round, NOVA generates multiple candidates under production constraints, rejects semantic violations, and ranks the valid survivors for local testing and offline evaluation. Across rounds, trajectory memory synthesizes semantic diagnostics, local-test outcomes, and offline metric changes into modification directions and forbidden patterns that guide subsequent search. Under the same maximum offline-evaluation budget for automated methods, NOVA achieves the highest effective pass rate, reaching 53.3% on ScaleUp and 51.7% on Literature-to-Production tasks. In a production A/B test covering 5% of traffic in an advertising system serving over one billion users, the selected Literature-to-Production candidate yields GMV gains of +1.25%, +1.70%, and +2.02% across three major pCVR objectives, with corresponding relative reductions in absolute pCVR bias of 58.8%, 66.7%, and 37.3%, respectively.

cs.IR↗
arXiv2026

Diffusion Language Model for Recommendation

Large language model (LLM)-empowered recommender systems have emerged as a promising paradigm for generative recommendation, leveraging their strong semantic reasoning and generative capacity to model complex, diverse user preferences. However, most existing approaches rely on an autoregressive paradigm that is suboptimal for recommendation. The next-token objective emphasizes sequential order rather than the structural inter-item dependencies underlying user preferences. In addition, prefix-constrained generation restricts bidirectional context and commits to left-to-right decoding, causing early errors to accumulate without correction. Inspired by the success of diffusion language models, we propose \textbf{DLMRec}, a discrete diffusion language model tailored for recommendation that offers a compelling alternative to autoregressive generation. Specifically, DLMRec introduces three key components to bridge diffusion language modeling with recommendation. First, a collaborative-aware stochastic tokenizer encodes multi-hop collaborative signals into expressive discrete tokens compatible with diffusion modeling. Second, a curriculum-driven training strategy aligns the denoising process with preference recovery through progressive item- and token-level learning. Third, a stability-aware voting mechanism aggregates iterative predictions to improve generation consistency and robustness.

cs.IR↗
arXiv2026

Investigation on the Relation between Active Regions' Compliance with Empirical Laws and Flare Productivity

It remains evasive whether solar active regions (ARs) obeying or violating Hale's polarity law, Joy's tilt law, and the hemispheric helicity rule (HHR) differ in flare productivity. Here we conduct a comprehensive statistical analysis of ARs during the Solar Cycle 24 and the ascending phase of Cycle 25. ARs are automatically detected from full-disk line-of-sight magnetograms acquired by the Michelson Doppler Imager (MDI) and the Helioseismic and Magnetic Imager (HMI). We calculate tilt angles via flux-weighted polarity centroids, estimate magnetic twist by the force-free parameter $α_{\mathrm{best}}$ from HMI vector magnetograms, and measure flare productivity using the flare index (FI) built from GOES C-class-and-above events. Our results substantiate that the majority of ARs follow the aforementioned three empirical laws. The compliance rate tends to be higher for ARs emerging at higher latitudes or having larger centroid distance, while total unsigned magnetic flux exerts limited influence, with a clear positive correlation only for Hale's law. Overall, FI shows no significant discrepancies across different compliance groups, except that Cycle 24 ARs that satisfy Hale's and Joy's laws but violate the HHR exhibit higher FI than other groups. We also identify empirical thresholds for centroid distance and total unsigned flux, above which the median FI of binned ARs becomes nonzero. Combining the flux and distance thresholds effectively separates flare-productive from flare-quiet ARs. We hence conclude that the flare productivity of ARs is not dependent on the compliance with the empirical laws, but more closely associated with sufficiently large and strong magnetic systems.

astro-ph.SR↗
arXiv2026

R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement

Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements. However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser's original semantic intent merely to satisfy compliance. In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose R^3, a novel framework designed to harmonize compliance with original semantic intent preservation. Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via a group-Relative compliance experience extractor; (2) a curriculum Reinforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency; and (3) a comprehensive video Rectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment. Extensive experiments on industrial datasets and online A/B testing demonstrate that R^3 significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.

cs.CL↗