arXiv subjects

Cong Zhang

Publications and source records attributed to Cong Zhang.

At least 19 recordsLinked to original sources

arXiv2026

HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization

Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization target. HEMO maintains a persistent harness state and updates one module at a time, revising the logic that determines which experience to retrieve, which operators to improve, which parents to select, and how to formulate the orchestration of search steps. Downstream solution quality and runtime guide these updates, while a discounted UCB scheduler directs adaptation toward promising modules as their utility changes. A persistent memory filesystem preserves candidate outcomes and diagnostic feedback across harness states, enabling successive states to build on accumulated optimization experience. Experiments across eight MOCO tasks and two structurally distinct evolutionary backbones demonstrate strong performance against conventional evolutionary, neural, and LLM-based AOD baselines, together with effective transfer to related tasks. HEMO extends automatic operator design beyond evolving individual operators to improving the search process that discovers them.

cs.NE↗

arXiv2026

Dark Parton Shower Effects for Cosmic Ray Boosted Dark Matter

We investigate the effects of dark parton showers on the direct detection of cosmic-ray boosted dark matter (CRDM), focusing on a dark-photon-mediated model with fermionic dark matter--electron interactions. Using a Monte Carlo framework to incorporate Sudakov form factors and kinematic dipole recoil schemes, we simulate the evolution of the CRDM energy spectrum under dark sector splitting. Our results reveal that dark parton showering induces an energy-dependent reshaping of the CRDM flux, particularly characterized by a depletion of the high-energy flux. For a dark matter (DM) mass of 1 keV and a coupling of $g_D=3$, the CRDM flux can be enhanced by up to a factor of 1.12 in the $\mathcal{O}(10^{-2} \sim 1)$ MeV energy range for $2m_χ\lesssim m_{A^\prime} \lesssim 10^{-2}$ MeV, whereas it is suppressed by more than 50% at energies around 100 MeV for $m_{A^\prime} \lesssim 10^{-3}$ MeV. We then translate these effects into experimental sensitivities for PandaX-4T, Super-Kamiokande, and JUNO. For $m_{A^\prime} = 10^{-3}$ MeV and $g_D=3$, the bounds on the kinetic mixing parameter $ε^2$ are relaxed by factors of 1.02, 1.6, and 1.4, respectively. Incorporating the effects of DM parton distribution functions (PDFs) at neutrino detectors alongside dark parton shower effects further relaxes these bounds.

hep-ph↗

arXiv2026

Capturing Electrical Windows Through Reconfigurable Optical Networks: Transfer-aware Scheduling of Multi-Region AI Data Centers

Artificial-intelligence data centers (AIDCs) can provide spatiotemporal load flexibility by migrating training workloads in response to regional electricity prices and renewable-energy (RE) availability. However, transfer-blind scheduling may overestimate migration benefits by overlooking transfer time or prevent training from resuming within renewable-rich or low-price windows when considering transfer time. This paper proposes a transfer-aware compute-electricity-network scheduling framework that coordinates training placement, checkpoint transmission, and optical circuit switching (OCS) to improve local RE utilization and reduce grid-purchase cost. A compact compute-electricity master problem generates candidate schedules using estimated transfer delays. The framework then schedules optical circuits, verifies checkpoint delivery under shared-link capacity constraints, and revises infeasible schedules using updated delay estimates. It integrates day-ahead planning, event-triggered intraday updates, and real-time dispatch. In a five-AIDC benchmark with equal completed work and network resources, the proposed method reduces the real-time grid purchase cost by 12.50% and increases the local RE utilization by 2.724 percentage points relative to static optical operation. Sensitivity and ablation analyses indicate that OCS is particularly beneficial when renewable-rich or low-price windows shift across sites and network bottlenecks hinder timely checkpoint delivery.

cs.DC↗

arXiv2026

Rethinking Relative Policy Differences Transfer of On-Policy Distillation

On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantially more capable than the target. Recent work relaxes this requirement by transferring the relative policy difference between an expert and a reference policy rather than the expert's absolute distribution. Yet it remains unclear which differences provide useful supervision and which targets can benefit from them. We develop a unified view in which the log-probability ratio between a proxy expert and a proxy reference defines an implicit reward for KL-regularized policy optimization. This formulation induces an on-policy update for the target, recovers conventional OPD as a special case, and enables any-to-any transfer across models that differ in scale, training stage or generation. Our systematic experiments yield three findings. First, a stronger expert is not necessarily a better source of supervision: differences induced by task-specific training, including reinforcement learning and supervised fine-tuning, transfer consistently, whereas those arising from model scale alone transfer weakly or not at all. Second, the expert and reference serve complementary roles: the expert provides the capability to be transferred, while the reference filters out shared behavior and isolates the relevant residual. Third, even a useful difference does not transfer to every target: success requires the induced update to move the target toward the expert and generalize beyond sampled rollouts. Raw policy distance does not predict transferability, whereas an appropriate reference can rescue otherwise unsuccessful transfer. These results characterize when relative policy differences provide effective supervision for OPD.

cs.LG↗

arXiv2026

SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors

Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuristics. However, the dominant paradigm embeds LLMs as narrow, fixed components, such as crossover or mutation, within heavily hand-engineered evolutionary frameworks. We argue this misapprehends LLMs. It treats them as specialized tools rather than general reasoners, constrains them to low-level operations, and underutilizes their autonomy. Moreover, the extensive human priors in these frameworks violate the bitter lesson principle that general methods scaling with computation surpass hand-crafted solutions. This raises a key question: which AHD framework designs best convert stronger LLM capabilities into better heuristics? To address this, we propose metrics for LLM-driven AHD framework handcraftedness (AHI) and intelligence conversion efficiency (ICE). Evaluating ten LLMs across three challenging combinatorial optimization problems, we obtain a notable finding that frameworks with fewer human priors consistently yield higher ICE. Based on this finding, we propose SimpleEvol, an agent-loop framework for AHD which removes nearly all human priors and allows the LLM to operate autonomously. SimpleEvol consistently achieves the highest ICE, often by a large margin. Our results challenge the trend toward complex AHD pipelines and point to a lighter and more model-centric alternative, suggesting that reducing human priors is a more effective strategy to scale up with model intelligence. The source code is available at https://github.com/HenryZhu1029/SimpleEvol-Master.

cs.AI↗

arXiv2026

Dynamics of Regge calculus with torsion

The discrete geometry on an $n$-dimensional simplicial manifold are studied, in order to incorporate torsion into Regge calculus. In each simplex, the edge vectors are assigned to the edges to encode the information of their lengths and directions. In addition, the holonomies along the curves across the interfaces of two adjacent simplices are represented by the internal gauge group elements. The torsion manifests itself as the difference between an edge vector on an interface belonging to one simplex and the parallel transported edge vector, via the holonomy, of the same edge but belonging to the adjacent simplex. The simplicial Einstein--Cartan actions are then constructed as functions of the edge vectors and holonomies in three and four dimensions with Euclidean and Lorentzian signatures, respectively. It is shown that they return to the corresponding Regge actions for the torsion-free cases. The variations of the 4-dimensional discrete action with respect to the edge vectors and holonomies, respectively, give two equations of motion. It is shown that the former is consistent with the corresponding equation in the continuum theory, and the torsion-free holonomies satisfy the latter equation as in the continuous case. Thus, the resulting theory on the simplicial manifold can be regarded as a discrete analogue of Einstein--Cartan theory.

gr-qc↗

arXiv2026

Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in vision-language models and recently explored for embodied agents. In embodied agents, tokens not only support perception and semantic understanding but also directly affect latency-sensitive closed-loop robot action prediction. Existing schemes typically guide compression using redundancy or importance cues, such as visual similarity, attention scores, and saliency. However, these cues only indirectly measure the key factor for safe compression: how much a token can change before causing an unacceptable deviation in downstream actions. This receiver-dependent tolerance is closely related to the principle of just noticeable difference (JND). Classical JND characterizes signal tolerance in the human visual system, while machine-oriented JND extends this concept to downstream machine responses. Building on this progression, we introduce Action-JND, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control. A token change is considered admissible only when the induced action deviation remains within a tolerated margin. To realize this concept, we develop a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum tolerable perturbation while preserving policy responses. The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms, including stale-KV reuse and token pruning, prioritizing action-tolerant tokens for compression. Experiments on the LIBERO benchmark with OpenVLA and OpenVLA-OFT demonstrate that Action-JND consistently improves compression reliability, especially under aggressive compression ratios.

cs.CV↗

arXiv2026

P$^3$-SAM: SAM with Perceptual Parallel Prompt for Few-Shot Strip Steel Surface Defect Segmentation

Few-shot semantic segmentation (FSS) of strip steel surface defects (S$^3$D) has posed significant challenges distinct from natural scenes. Unlike natural images, S$^3$D task exhibits unique characteristics including low local contrast, uneven illumination, and complex fine-grained texture patterns. Although recent methods based on Segment Anything Model (SAM) have shown promise in FSS on natural images by leveraging SAM's powerful pre-trained representations, these unique industrial characteristics of S$^3$D images lead to performance drop when directly applying SAM to industrial defect scenarios. In this paper, we propose a novel Perceptual Parallel Prompt (P$^3$) framework that empowers SAM, creating the P$^3$-SAM model to address these challenges through two core strategies. First, we develop a Perceptual-Optimized Encoding (POE) strategy that enhances local contrast and preserves critical texture details for S$^3$D segmentation. Second, we introduce the Parallel Prompt Generator (PPG) strategy that simultaneously generates both semantic and spatial prompts, enabling comprehensive guidance for SAM's decoder across varying images. Extensive experiments on three few-shot S$^3$D benchmarks demonstrate that P$^3$-SAM achieves state-of-the-art performance, with particularly notable improvements of 12.00% in mIoU on Surface Defects-4i dataset.

cs.CV↗

arXiv2026

Cluster-induced target shift and synthetic approximation for high-dimensional clustered data

In high-dimensional clustered data, covariates whose distributions differ across clusters can act as proxies for unobserved cluster effects. We show that the marginal-model LASSO implicitly uses sparse combinations of such covariates to shift the estimation target from structural coefficients to a contaminated vector, which inflates false selections. We therefore propose the Synthetic Heterogeneous-Effects LASSO (SHEL), which augments the regression design with separately penalized, outcome-independent, cluster-constant synthetic covariates to correct the cluster-induced target shift. Under a fixed nuisance-effects formulation, we derive oracle properties and establish consistency of the structural coefficients when the residual heterogeneity is weakly aligned with the augmented design. We also demonstrate the distinction between the structural parameter under small residual heterogeneity and the population working parameter when residual heterogeneity persists. Further, we develop a debiased estimator with a cluster-robust sandwich variance, and establish asymptotic results. Simulations show far fewer false selections than the marginal LASSO, and an analysis of longitudinal neutrophil transcriptomic data from hospitalized COVID-19 patients yields a more parsimonious gene set that retains the severity markers of the original study.

stat.ME↗

arXiv2026

Design-Assisted Regression

We consider regression problems in which the marginal distribution of the covariates is informative for estimation and variable selection, rather than merely auxiliary. Motivated by random-design, high-dimensional, and latent-effect settings, we propose a general design-assisted regression framework in which the estimating criterion depends on both the conditional model for $Y \mid \bfX$ and structured features of the covariate distribution. The framework identifies two roles of design information: stabilizing weak design directions through quadratic regularization and correcting latent-effect distortion through nuisance augmentation. We establish oracle properties for the resulting estimator, separate the effects of stochastic error, shrinkage, and approximation, and compare it with a benchmark sparse procedure that ignores design information. These results show that the proposed framework improves estimation while preserving first-order prediction performance. Numerical studies and two real-data applications illustrate the practical impact of incorporating design information.

stat.ME↗

arXiv2026

Consistent Gauge Conditions for Dust-Shell Dynamics in Effective Quantum Gravity

Previous analyses of shocks generated by shell-crossing singularities are affected by inappropriate gauge choices, and no systematic method is available for selecting a consistent gauge. To address this issue, we focus on the shock dynamics, which can be effectively described by a thin dust shell interacting with the surrounding dust. As a first step toward the full shell-crossing problem, we neglect this interaction and study an isolated thin shell, for which we develop a systematic method for constructing consistent gauges in generally covariant effective gravity. We apply this method to a generally covariant effective Hamiltonian model of quantum gravity characterized by a quantum parameter $ζ$, with classical GR recovered in the limit $ζ\to0$. In this classical limit, the resulting shell dynamics reproduces the Israel junction conditions, providing a nontrivial validation of our method, whereas for $ζ\neq0$, it exhibits genuine quantum-gravity corrections. We also show that gauges such as the Painlevé-Gullstrand and Schwarzschild ones are incompatible with the presence of a dust shell when imposed on the whole spatial slice. This explains the difficulties in previous treatments. The framework developed here provides a basis for studying shell-crossing singularities and shock dynamics in generally covariant effective black-hole models.

gr-qc↗

arXiv2026

See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning

Unsupervised action segmentation aims to discover latent action categories and their temporal organization without action annotations. Optimal transport-based methods provide structured frame-to-action assignments, however, their pseudo-label quality is fundamentally conditioned on the representation space used to construct the transport cost. We argue that reliable OT pseudo-labeling requires a representation geometry that is simultaneously sensitive to discriminative action changes and coherent along local temporal progressions. Based on this insight, we propose SpecT-OT, a spectral-temporal representation learning framework built upon an unbalanced optimal transport pseudo-labeling concept. SpecT-OT introduces a Spectral Reparameterization Projector (SRP), which parameterizes projector weights with fixed Fourier bases and learnable coefficients to improve the modeling of rapidly varying discriminative features, and Temporal Affinity Regularization (TAR), which imposes distance-aware, label-free constraints on pairwise frame affinities to stabilize local temporal structure. The two components jointly produce more discriminative and temporally stable transport costs, yielding more reliable pseudo-labels for iterative representation learning. Experiments on four benchmarks demonstrate strong performance compared with state-of-the-art methods. SpecT-OT achieves the best results on 13 of 15 metrics, including 4.1-point MoF and 7.4-point F1 gains over the baseline on Breakfast and Desktop Assembly, respectively.

cs.CV↗

arXiv2026

A Minkowski-core black hole with cosmological constant and electric charge

Within a covariant effective Hamiltonian framework, we employ an inverse construction to derive the gravitational Hamiltonian constraint for a Minkowski-core regular black hole without invoking exotic matter. We then extend the constraint by coupling it to a spherically reduced Maxwell field and including a cosmological constant. The resulting charged anti-de Sitter (AdS) and de Sitter (dS) solution is gauge independent and reduces to the Reissner--Nordström--AdS (RN-AdS) black hole when the regularization parameter vanishes. Electric charge and a cosmological constant preserve the Minkowski core: the metric approaches the Minkowski geometry at the center, the Kretschmann scalar vanishes there, and the spacetime exhibits a multi-horizon structure. Focusing on AdS backgrounds, we investigate the black hole thermodynamics. For a regularization parameter below a critical value, the model exhibits a phase transition with consistent signatures across these thermodynamic quantities, demonstrating that Minkowski-core regularization can preserve center regularity while modifying the AdS thermodynamic phase structure relative to the RN-AdS benchmark.

gr-qc↗

arXiv2026

The interface of intonation and lexical tone: Boundary phenomena in Mandarin varieties

This chapter explores the intricate interplay between intonation and tone in Mandarin Chinese varieties, focusing on f0, the primary acoustic cue for both intonation and tone. The main empirical base is intonation boundary phenomena, where intonation and tone intersect and influence each other in conveying a range of sentence-level linguistic functions -- such as question vs. statement -- and a rich array of speakers' attitudinal information. Theoretical models and emerging techniques are also discussed to account for the observed interactions of tonal aspects and boundary phenomena to convey multiple levels of communicative meanings.

cs.CL↗

arXiv2026

Integrating Human Linguistic Insights into AI: Theory-Driven Representation for Multilingual Text-to-Speech

This paper explores the integration of human linguistic insights into multilingual text-to-speech (TTS) systems by evaluating the Featurally Underspecified Lexicon (FUL) as a theory-driven input representation. Unlike data-intensive end-to-end models, FUL offers a compact, interpretable feature set grounded in phonological principles, enabling scalable and equitable TTS development for low-resource languages. We provide a mapping from language-specific phones to FUL feature vectors via a SAMPA intermediate and incorporate these features into a modified FastSpeech architecture. Experiments were conducted to evaluate their ability to generate native, non-native, and code-mixed speech in English and Mandarin. We ran an experiment with a small dataset and one with a larger dataset, which showed that TTS with FUL features as input could produce intelligible native speech with as little as 8 hours of training data; with 100 hours of training data, intelligible speech could be generated for a language not present in the training data. The approach further supports code-mixed synthesis while preserving consistent timbre and interpretable phonetic control. These results highlight the potential of theory-driven representations for building efficient, scalable, and linguistically informed TTS systems, demonstrating that phonological features can function as both analytical tools and practical inputs for speech technology.

cs.CL↗

arXiv2026

MemHarness: Memory Is Reconstructed, Not Replayed

Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the agent's current situation. This ``replay'' paradigm ignores the gap between the abstract, general nature of stored experience and the concrete, ever-changing states encountered at decision time, frequently causing negative transfer. In contrast, humans rarely recall past experiences verbatim; instead, they reorganize and adapt retrieved memories to fit the present context. Inspired by this, we propose MemHarness, a framework that equips LLM agents to actively harness and reconstruct past experiences based on the present context. At each decision step, a unified policy model critiques and reconstructs the retrieved experience conditioned on the current state, producing context-grounded guidance before acting. This reconstructive ability emerges naturally through end-to-end training with GRPO. Experiments on ALFWorld and WebShop show that MemHarness substantially outperforms pure RL and static memory-augmented baselines, demonstrating strong robustness in out-of-distribution (OOD) scenarios. Furthermore, our analyses reveal that this reconstruction objective not only prevents negative transfer but also serves as latent guidance during training, fundamentally improving the agent's intrinsic reasoning capabilities.

cs.AI↗

arXiv2026

A Bayesian predictive framework for adaptive interim-analysis timing with robust borrowing in confirmatory trials

Confirmatory phase III trials require rigorous evidence, yet for first-in-class (FIC) therapies they must often be designed when same-mechanism evidence is scarce. This uncertainty motivates planned interim analyses and makes phase II data from the same therapy a relevant source of prior evidence. However, both borrowing and repeated interim analyses must be calibrated to control the overall type I error rate. Because borrowing changes the evidence available at interim analyses relative to a non-borrowing group sequential design (GSD), it also raises the question of whether interim analysis timing should be prospectively adapted to the borrowing-adjusted evidence base. We propose a prespecified adaptive interim-timing framework based on Bayesian information borrowing and Bayesian predictive probability $B^2$-FIC. The borrowing model is calibrated against phase II--phase III discrepancy scenarios to control overall type I error rate. At the first interim analysis (IA1), the calibrated model combines phase II information with accumulating phase III data to update the posterior. Bayesian predictive probabilities from this posterior select the earliest information fraction for the second interim analysis (IA2) that meets the efficacy criterion. In simulations, $B^2$-FIC maintained empirical type I error and improved interim power across different scenarios. Predictive probabilities derived from phase II and phase III IA1 data selected earlier IA2 than GSD when evidence was favorable. Two oncology case studies illustrate the framework. Overall, $B^2$-FIC provides a calibrated framework for adapting interim timing to borrowing-adjusted evidence, an emerging design problem in confirmatory trials.

stat.AP↗

arXiv2026

A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models

Predictions by machine learning (ML) and artificial intelligence (AI) models are often received skeptically unless they are paired with intelligible explanations. In the context of just-in-time defect prediction, highlighting small portions of a software change (diff) -- beyond rule-based lints -- where risk may be concentrated has not yet been extensively investigated. In this work, we leverage attention weights from an LLM-based Diff Risk Score (DRS) model to highlight parts of a diff that the model focuses on when predicting risk. We aggregate token-level attention into interpretable code units (lines, hunks, and files), and present the top-K units to developers as a lightweight form of guidance during code review. We evaluate our approach using expert-labeled changes that have caused real outages. Results show that the highlighted snippets cover expert-labeled outage-causing change lines 53.85% of the time when highlighting the top-2 hunks, while requiring developers to review 26.28% of the changed lines on average. Because attention is produced during standard model inference, the approach is scalable for large development workflows and can be surfaced in the code review UI with low additional latency.

cs.SE↗