Search arXiv⌕ Search

arXiv subjects

Chen Yang

Publications and source records attributed to Chen Yang.

At least 37 records · Page 2Linked to original sources
arXiv2026

RLVR is a Kernel, Not a Function: Statistical Inference for pass@$k$ Crossovers

Reinforcement learning with verifiable rewards (RLVR) often improves pass@1 while falling behind its base model at larger sampling budgets $k$, a crossover read as evidence that RLVR only sharpens existing capability. We identify two limits to this reading. First, a visible crossing need not be statistically established: comparing models on the same prompts, we build confidence bands across sampling budgets $k$ that require evidence of both an early gain and a later loss. Across five public RLVR pairs no crossing is statistically established in the initial evaluations, while a 32k-token evaluation on fresh prompts locates a reversal with first loss between 11 and 61 samples; power analysis shows why failure to detect a crossing need not mean no crossing, and why more prompts can help more than more answers per prompt. Second, base success alone does not determine what RLVR does to a prompt: prompts with the same base success rate have different post-RL success rates, and these differences repeat across independent generation halves. The relationship is a conditional distribution---a Markov kernel---rather than a single curve, and fitting it predicts crossings in independent generations for the same prompts and corrects the simple model's power estimates. Theory further shows how losses on a minority of the hardest prompts can overturn an early lead even when training improves other prompts, separating evidence that a crossover exists from claims about what it means for capability.

stat.ML↗
arXiv2026

How Sensitive Are LLM Leaderboard Claims to Hidden Model Selection?

LLM leaderboard gains can reflect selection among privately evaluated model variants, yet neither the number of variants nor their dependence is public. We ask how many hidden variants a published margin can support while retaining statistical evidence of a provider's advantage over a fixed comparator. For a fixed candidate family under a Gaussian margin model, we derive a sensitivity curve that reports this maximum count as a function of a lower bound on within-family correlation. The relevant correlation must match the score used for ranking and the sampling model: in a controlled family, pooled item correlation is 0.90, whereas composite-score correlation is 0.46 under item resampling and 0.92 when MMLU subjects are resampled. An item-based audit of 394 adjacent-rank claims on the Open LLM Leaderboard finds that 391 lack statistical support even before accounting for selection. Among claims that pass the uncorrected test, certification can depend on assumptions about the hidden family's correlation. The resulting curves make these assumptions explicit without estimating the unobserved search size.

stat.ML↗
arXiv2026

Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typically focus on either frequency-domain decomposition or time-domain pattern extraction in isolation, neglecting their joint structure. This decoupled modeling limits representation expressiveness and undermines performance in tasks requiring simultaneous temporal and spectral reasoning. To address this gap, we propose m-WCN, a novel end-to-end deep learning framework that neuralizes multi-wavelet decomposition for joint extraction of temporal patterns and frequency components. By approximating the classical GHM multi-wavelet transform with trainable convolutional operators and enforcing orthogonality constraints, m-WCN produces interpretable multi-resolution representations. Built on this foundation, we introduce two task-specific architectures: TFBC for time series classification, which boosts discriminative features across frequency scales, and FTB for forecasting, which ensembles frequency-aware predictors. Extensive experiments on 64 UCR datasets and seven public forecasting benchmarks demonstrate the effectiveness of our approach. Built on the neuralized m-WCN, our TFBC and FTB outperform various baseline models across diverse datasets, achieving average improvements of 19.97% in classification and 19.92% in forecasting tasks.

cs.LG↗
arXiv2026

Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems

Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation of AgentX's model research framework, which connects proposal development and model experimentation within sandboxes defined by business inputs and prediction tasks. AgentX-Model adopts a dual-agent architecture comprising a Research Agent and a Model Agent. The Research Agent develops independently reviewed proposals from papers and experimental findings, while the Model Agent conducts multi-round investigations and returns code, measurements, and unresolved questions. Using the returned results, the Research Agent selects a starting implementation and formulates the next research question, allowing subsequent experiments to build on earlier findings. We organize this continuing research around four actions: Reproduce, Follow-up, Composition, and Diagnose. The first three actions drive routine research, while Diagnose acquires the evidence needed to choose a repair, including for issues raised by business feedback and online evaluation, such as prediction bias measured by PCOC. Across the production evaluation, 560 of 636 completed model-changing experiments recorded AUC above their business baselines. As research continued, some experiments recorded AUC above every comparable ancestor in their lineages. The five latest online A/B evaluations across different business settings reported gains including 10-15% in acquisition efficiency, 15-20% in target-segment advertising spend, and 0.3-0.8% in watch time; the watch-time model used approximately 10% fewer FLOPs and parameters. A dependency-aware historical-replay benchmark further evaluates research allocation, with initial results showing no consistent efficiency gain from more complex scheduling when agents already analyze and select concrete candidates.

cs.AI↗
arXiv2026

Deep-learning-aided dismantling of interdependent networks

Identifying the minimal set of nodes whose removal breaks a complex network apart, also referred as the network dismantling problem, is a highly non-trivial task with applications in multiple domains. Whereas network dismantling has been extensively studied over the past decade, research has primarily focused on the formulations of the optimization problem for single-layer networks, neglecting that many, if not all, real networks display multiple layers of interdependent interactions. In such networks, the optimization problem is fundamentally different as the effect of removing nodes propagates within and across layers in a way that can not be predicted using a single-layer perspective. Here, we propose a dismantling algorithm named MultiDismantler, which leverages multiplex network representation and deep reinforcement learning to optimally dismantle multi-layer interdependent networks. MultiDismantler is trained on small synthetic multiplex graphs; when applied to large, real and synthetic networks, it displays exceptional dismantling performance, clearly outperforming all existing methods that rely on a single-layer approach to network dismantling. We show that MultiDismantler is effective in guiding strategies for the containment of diseases in social networks characterized by multiple layers of social interactions. Also, we show that MultiDismantler is useful in the design of protocols aimed at delaying the onset of cascading failures in interdependent critical infrastructures.

cs.SI↗
arXiv2026

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectories extend. While in practice, many queries do not require the capabilities of the largest available model, and routinely directing such queries to a high-capability model can introduce unnecessary, considerable computation and energy consumption. In this paper, we investigate whether adaptive routing across a heterogeneous pool of LLMs can reduce this energy burden without substantially compromising task performance. We design a language-model-based router that reads in each query and selects an answer model from a fixed candidate pool. The candidate models are first profiled through an offline tournament that records their correctness, latency, power, and GPU energy for each query. Using these measurements, the router is trained through supervised fine-tuning followed by group relative policy optimization (GRPO) with the tailored paradigms. Results demonstrate that learned routing can selectively allocate expensive model capacity based on query context and improve the accuracy-energy tradeoff in multi-LLM serving. Across seven benchmark tasks, we also observe a sharp accuracy-energy phase transition among routers, providing practical insights into improving energy efficiency while maintaining LLM performance.

cs.PF↗
arXiv2026

Distributional sentiment modeling and anomaly detection for consumer complaint assessment

Sentiment analysis is a common tool for converting unstructured text into quantitative signals in finance and risk management. Yet most applications reduce the output to a discrete polarity label or a single predictive feature, overlooking the distributional structure of sentiment intensity in consumer complaint narratives. In this paper we treat negative sentiment in consumer complaints as a bounded continuous variable and study its full distribution rather than a single label. We score each narrative with a transformer classifier, model the scores with Beta distributions, and compare the fitted distributions of meritorious and non-meritorious complaints through the Kullback Leibler divergence and the squared Hellinger distance. The fitted distributions are then linked with dollar amounts and company response outcomes to construct anomaly diagnostics that flag complaints whose textual severity is inconsistent with the recorded relief. We find that the two groups have strongly overlapping distributions, so negative sentiment intensity is not a sharp classifier of outcomes on its own; combined with monetary and categorical attributes, it isolates unusually severe complaints for operational risk monitoring. Treating sentiment analysis as continuous distributional measurement, this study links sentiment extraction, bounded response modeling, and anomaly detection in a unified framework for consumer complaint assessment.

cs.CL↗
arXiv2026

Covariance-Regulated Recursive Koopman Learning for Nonlinear Systems with Uncertain Time-Varying Dynamics

Offline models for autonomous robots often fail under time-varying dynamics outside their training distribution. While Koopman operator theory offers a linear representation of nonlinear dynamics via lifting, its transition to online recursive estimation may suffer numerical vulnerabilities: covariance windup under low excitation when using exponential forgetting, and vanishing gain without forgetting. To prevent covariance explosion and parameter freezing, this paper introduces a unified Covariance-Regulated Recursive Koopman Learning (CR-RKL) framework that systematically incorporates and evaluates several covariance-regulated methods. Specifically, we propose a novel error dead-zone covariance skipping strategy, along with adaptations of constant-trace normalization and directional forgetting to the Koopman-specific setting. Validated on a non-holonomic differential-drive robot with wheel slip and Stribeck friction, as well as on a two-winged, tailless flapping-wing micro aerial vehicle, CR- RKL achieves numerically stable and accurate online modeling relative to its offline and vanilla recursive counterparts. When embedded in model predictive control, it maintains reliable tracking performance under uncertain, time-varying dynamics with bounded dictionaries. However, we also identify a structural limitation: while covariance-regulated methods achieve low off-policy prediction error, pairing them with unbounded dictionaries can lead to control failure.

cs.RO↗
arXiv2026

OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation

Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or repeatedly replay shared history, incurring substantial memory and traffic overhead. To address this, we present OneLA, a linear-attention decoding framework that exploits the shared prompt and short divergent suffixes of GR workloads. Specifically, OneLA represents all beam states using a single shared prompt-derived state and compact, append-only records of their divergent transitions. Using this representation, OneLA computes only the state information required at each decoding step, without reconstructing a full recurrent state for every beam. Furthermore, OneLA uses a lightweight ancestry index to track the transition records that make up each beam's history, allowing beams to be updated without moving or copying existing records. A fused GPU kernel further reuses the shared state across beams. Our analysis shows that OneLA achieves 1.54-2.46x end-to-end decode speedups while substantially reducing recurrent-state memory use and data movement.

cs.AI↗
arXiv2026

Probing Inflationary Origins of Primordial Black Holes with LIGO--Virgo--KAGRA O1--O4a data

Large primordial curvature perturbations not only produce primordial black holes (PBHs) but also inevitably source a scalar-induced stochastic gravitational-wave background upon horizon reentry. We analyze the combined LIGO--Virgo--KAGRA O1--O4a data to constrain two representative inflationary mechanisms for generating such perturbations: ultra-slow-roll inflation and an inflationary phase transition. Detecting no evidence for either scenario, we place 95% credible upper limits on the curvature-spectrum amplitude across the frequency range accessible to ground-based interferometers. Translated into the PBH context, these limits already exceed conventional constraints, probing abundance fractions far below unity. Our results remain robust even when the PBHs themselves are too rare to be directly detected or have evaporated. This work demonstrates that stochastic gravitational-wave observations offer a powerful and complementary probe of small-scale inflationary physics and PBH formation, with upcoming interferometers promising to extend sensitivity to a wider range of inflationary epochs and PBH masses.

astro-ph.CO↗
arXiv2026

Arbitrage on Decentralized Exchanges

Decentralized exchanges using automated market makers create arbitrage opportunities with centralized exchanges, where gas fees and transaction ordering are critical. Existing models largely overlook competition among arbitrageurs, despite price discrepancies being public information. We develop the first equilibrium model of gas fee competition between two arbitrageurs under three transaction reversion settings: no-revert, auto-revert, and selectable-revert. We show that pure symmetric equilibria do not exist, but unique mixed equilibria can be characterized. Using data from Binance and Uniswap V2, we empirically confirm that arbitrageurs face positive inventory risk and validate our model's implications: gas fees increase with price discrepancies and liquidity, while trading amounts rise with both price discrepancies and gas fees. Comparative analysis reveals that under low inventory risk, the no-revert setting favors arbitrageurs in terms of profit, while auto-revert and selectable-revert settings enhance market efficiency. Under high inventory risk, the no-revert and selectable-revert settings dominate the auto-revert setting in both profitability and efficiency.

q-fin.MF↗
arXiv2026

BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints

Converting in-service reinforced-concrete (RC) building blueprints into simulation-ready models---structured frame representations that support deterministic FEM export and qualified-engineer review---underpins safety assessment and seismic retrofit, but the process remains manual. Direct prompting of a multimodal large language model (MLLM) over a scanned sheet is unreliable: outputs often violate engineering constraints on beam--column support, span count, or 3D continuity. We present BlueprintAgent (BPA), a constraint-triggered multimodal agent for simulation-ready frame extraction from scanned blueprints. BPA treats the MLLM as the primary reader and decision maker, with OCR and computer vision supplying localized evidence. Its central mechanism realizes engineering constraints as callable validators whose entity-level conflict reports trigger targeted MLLM revisits over the local region---an inference-time control distinct from fixed pipelines and free-form self-reflection. We evaluate BPA on 300 real scanned blueprint sheets from 20 anonymized RC frame projects, against five baselines and six ablations. BPA reaches a macro-averaged Beam F1 of 0.994, against 0.301 for single-MLLM zero-shot and 0.820 for a fixed pipeline; removing MLLM-led axis adjudication collapses Beam and Column F1 on complex multi-sheet projects. For dense technical drawings, engineering constraints are best deployed as triggers for entity-level targeted revisits rather than as post-hoc output filters.

cs.CL↗
arXiv2026

Matter-Mediated Entanglement by Classical Gravity under Realistic Matter Dynamics

Gravity-induced entanglement (GIE) is widely regarded as key evidence of nonclassical gravity. Recent work, however, argues that a classical gravitational background can generate entanglement through virtual matter propagation between separated masses. Here we show that this mechanism is negligible once realistic matter dynamics is taken into account. For bound or condensed matter, the binding potential converts the claimed long-range matter-mediated interaction into an exponentially short-ranged one, with an attenuation length of only a few picometers for representative binding energies-well below atomic dimensions and therefore negligible under experimentally relevant distances. For unbound matter, the channel remains negligible before significant wave-packet overlap, while after overlap the packets no longer represent two spatially separated subsystems. Thus the proposed classical matter-mediated mechanism does not challenge the usual interpretation of GIE as evidence for nonclassical gravity once physical localization and finite-time matter dynamics are treated consistently.

quant-ph↗
arXiv2026

Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging

Inductive kriging estimates values at unobserved locations from sparse sensor data, enabling continuous field reconstruction when dense deployment is impractical. However, common 2 x 2 and 2 x 3 evaluation protocols can leak spatial information through model selection and obscure true out-of-distribution (OOD) behavior. We propose a leakage-free 3 x 3 partition that separates training, validation, and testing in both space and time, so that model fitting, checkpoint selection, and final reporting are performed on distinct spatio-temporal domains. Under this stricter setting, we introduce DRIK (Distribution-Robust Inductive Kriging), a framework with three task-specific mechanisms: Spatial Continuity Regularization (SCR) perturbs coordinates to reduce dependence on one discretized graph; Masked Flow Disambiguation (MFD) prunes ambiguous propagation from zero-padded masked nodes; and Structural Domain Expansion (SDE) uses validation-node topology without labels to reduce train-inference structural mismatch. Experiments on six spatio-temporal datasets show that DRIK consistently outperforms state-of-the-art baselines, reducing MAE by up to 12.48% and achieving lower test-to-validation MAE ratios under leakage-free evaluation. These results indicate that robust inductive kriging requires both leakage-free evaluation and mechanisms that explicitly address the structural shifts introduced by unseen nodes.

cs.LG↗
arXiv2026

Gravitational Waves and Primordial Black Holes produced by Dark Meta Stable Vacuum Decay

Inspired by string theory and cosmological constant problem, it is plausible that the Universe's vacuum structure is characterized by a landscape of metastable vacua. The existence of dark matter and dark energy further suggests that the dark sector may inhabit its own "dark landscape". If the dark vacuum is metastable, bubbles of lower-energy phases can nucleate at an approximately constant rate. Because the Hubble expansion rate is monotonically non-increasing with cosmic time, such nucleation can eventually lead to percolation and completion of a dark-sector phase transition. In this work, we investigate the phenomenological consequences of this transition, focusing on the resulting stochastic gravitational-wave background and the potential formation of primordial black holes. We find that the gravitational wave spectrum peaks at $k_{\mathrm{peak}}=3.1 H_{\mathrm{PT}}$, with an amplitude $Ω_{\mathrm{GW}}^{\mathrm{peak}}\simeq1.5 Ω_γ(Δρ/ρ_{\mathrm{tot}})^2$. Furthermore, the formation of primordial black holes is suppressed due to $ΔN_{\mathrm{eff}}$ constraint.

hep-ph↗
arXiv2026

Localized Ecological Momentary Assessment for Mental Health Research in China: An Implementation-Oriented Framework and Preliminary Case Application

Background: Ecological momentary assessment (EMA) is increasingly used in mental health research, but research-grade deployment requires platforms supporting protocol configuration, automated delivery, participant management, and data export. In China, these requirements are not consistently supported. Objective: We aimed to identify workflow gaps affecting localized EMA deployment, develop an implementation-oriented framework for platform assessment, and assess Huixin EMAI. Methods: We reviewed EMA platforms reported in Chinese mental health studies in CNKI and Wanfang. A multidisciplinary panel of 6 experts developed the Multi-dimensional EMA Platform Evaluation Framework (MEPEF) and benchmarked 7 platforms across 43 indicators in 6 domains. MEPEF was then applied to Huixin EMAI using deployment logs from 48 participants, questionnaires from 44 participants, and semistructured interviews with 6 researchers. Results: We identified 66 empirical studies. Most relied on instant-messaging-based workflows (36/66, 54.5%), whereas specialized EMA platforms were less common (14/66, 21.2%). MEPEF provided a 6-domain framework for cross-platform benchmarking and highlighted a trade-off between localized deployability and advanced research functions. In a Huixin EMAI deployment, 1893 of 2472 expected prompts were completed (76.6%), with a median response latency of 4.0 minutes (Q1-Q3 0.0-13.0). Participant feedback indicated favorable acceptability; researchers reported support for core workflows but gaps in control, delivery monitoring, and data readiness. Conclusions: The main challenge for EMA in Chinese mental health research appears to lie less in feasibility than in recurring workflow gaps affecting localized deployment. This study translates these gaps into structured evaluation and design targets, providing an implementation-oriented pathway for advancing localized EMA platforms.

cs.HC↗
arXiv2026

Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress

On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level supervision from a teacher. However, OPD implicitly assumes that teacher-derived rewards are an appropriate proxy for reasoning progress, and therefore treats all teacher feedback equally during policy optimization. While in practice, this assumption does not always hold. We observe that teacher-derived rewards often conflict with genuine reasoning progress, as reasoning steps with clear reasoning advancement may still receive lower distillation rewards, simply due to deviation from teacher's outputs. To address this mismatch, we propose Reasoning-Progress-Aware Reward Filtering for On-Policy Distillation (R2-OPD), which constructs two within-trajectory rankings of reasoning spans, one from teacher-derived rewards and the other from independently estimated progress reward. Distillation rewards are selectively suppressed whenever the two rankings disagree, reducing supervision that conflicts with reasoning progress while preserving effective teacher guidance. Our approach shows consistent improvement over standard OPD especially regarding reasoning performances.

cs.AI↗
arXiv2026

SCULPT: Subtractive Composition for 3D Part Generation

Part-aware 3D generation aims to create digital assets that are coherent as complete objects while exposing structural parts for editing, material assignment, animation, and reuse. Existing methods impose this structure outside the native generation loop: segmentation-based methods partition an already generated shape, while additive methods synthesize parts from predefined layouts, boxes, or tokens and then reconcile them into a whole. The former preserves the generated geometry but fixes the object before part boundaries are determined; the latter exposes part cardinality but often leaves shared boundaries vulnerable to gaps, interpenetrations, and material discontinuities. In this paper, we propose SCULPT, a framework that addresses these challenges through subtractive composition. Given a complete object represented in a structured 3D latent space, SCULPT iteratively applies a joint split predictor to generate one extracted part together with the remaining object. The predictor performs a coupled denoising process conditioned on both the image and the current 3D state, so the extracted part and updated remainder are generated together rather than reconciled after generation. The joint split predictor processes both outputs on the union of their native sparse 3D supports, allowing neighboring supports to overlap rather than imposing a disjoint voxel partition. The rollout ends when the remainder support becomes empty or reaches a fixed safety cap, allowing the number of generated parts to adapt to each object within that bound. Extensive experiments demonstrate state-of-the-art geometry on PartObjaverse while preserving strong complete-object reconstruction after part assembly. Results on four dataset images, one text-to-image-generated input, and one real-world photograph further show fine-grained textured part decomposition beyond the benchmark.

cs.CV↗