arXiv subjects

Wenhao Zhao

Publications and source records attributed to Wenhao Zhao.

18 recordsLinked to original sources

arXiv2026

Nanoscale Storage of Incompatible Elements at Olivine Grain Boundaries in Natural Basalts

Grain boundaries are pervasive in polycrystalline olivine, yet their structure and trace-element chemistry remain poorly constrained. We characterize boundaries in undeformed olivine aggregates from Piton de la Fournaise (La Reunion) and Mauna Loa (Hawaii) by correlating electron backscatter diffraction, transmission electron microscopy, and atom probe tomography. The boundaries are crystalline, with a structural width of about 1 nm and no continuous glassy film resolved. Ca, Al, P, Na, and Ti are selectively enriched, whereas Mg, Fe, Ni, and Mn remain homogeneous. Several enriched mass windows coincide with nominal rare-earth-element ion positions, but unresolved isobars and the lack of a diagnostic isotope envelope preclude secure assignments. Divalent-cation segregation follows an ionic-size-misfit trend, while aliovalent departures require unconstrained contributions. The Ca interfacial excess is 2.94-2.97 atoms per square nanometer, equivalent to 0.327-0.330 monolayers, and lies near the upper published 1523 K equilibrium segregation isotherm of Hiraga et al. (2004), within the range of basaltic olivine crystallization temperatures. This supports boundary formation during crystal growth, although synneusis followed by high-temperature residence could produce a similar signature. Ca chemical widths are about 6-9 nm, and those of the most strongly enriched elements reach about 10-15 nm, demonstrating decoupling between the narrow structural core and broader chemical segregation. Compared with published atom-probe data on deformed olivine, these boundaries preserve broader halos, although analytical differences make the contrast tentative. Olivine grain boundaries therefore constitute a distinct nanoscale reservoir that should be included alongside crystal interiors and residual melt in trace-element mass balances of olivine-rich aggregates.

astro-ph.EP↗

arXiv2026

FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which strategy choices drive performance remains unclear. Answering this question requires a benchmark that separates agent strategy (e.g., search topology) from execution infrastructure (e.g., code editor), so that performance differences are attributable to strategy rather than infrastructure, and that provides process-level metrics beyond final scores to analyze exploration behaviors. Existing benchmarks offer limited support. We propose FML-Bench, a benchmark of 18 fundamental ML research tasks across 10 domains that separates agent strategy from execution infrastructure and defines 12 process-level behavioral metrics. Evaluating six representative agents, we find that: (1) strategy complexity alone does not guarantee strong performance: a simple greedy hill-climber nearly matches the best-performing tree-search agent, both well above the remaining agents; (2) our analysis suggests this pattern relates to improvement opportunity structure: greedy search tends to be more effective when opportunities are dense, while tree-search and evolutionary strategies tend to be more effective when opportunities are sparse; an adaptive agent built on this insight switches to broader exploration upon detecting improvement stagnation and outperforms the other six agents, lending initial support to this observation; and (3) process-level analysis reveals that early convergence and directionally focused exploration are significantly associated with final performance, while solution diversity and compute cost are not. Our benchmark is available at: https://github.com/qrzou/FML-bench.

cs.LG↗

arXiv2026

Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching

Multi-objective optimization (MOO) has been widely studied in literature because of its versatility in human-centered decision making in real-life applications. Recently, demand for dynamic MOO is fast-emerging due to tough market dynamics that require real-time re-adjustments of priorities for different objectives. However, most existing studies focus either on deterministic MOO problems which are not practical, or non-sequential dynamic MOO decision problems that cannot deal with some real-life complexities. To address these challenges, a preference-agile multi-objective optimization (PAMOO) is proposed in this paper to permit users to dynamically adjust and interactively assign the preferences on the fly. To achieve this, a novel uniform model within a deep reinforcement learning (DRL) framework is proposed that can take as inputs users' dynamic preference vectors explicitly. Additionally, a calibration function is fitted to ensure high quality alignment between the preference vector inputs and the output DRL decision policy. Extensive experiments on challenging real-life vehicle dispatching problems at a container terminal showed that PAMOO obtains superior performance and generalization ability when compared with two most popular MOO methods. Our method presents the first dynamic MOO method for challenging \rev{dynamic sequential MOO decision problems

cs.AI↗

arXiv2026

Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and other generative models. Despite its prevalence, the characteristics and behaviors of vector quantization in generative models remain largely underexplored. In this study, we systematically investigate the issue of collapses in vector quantization, where collapsed representations are observed across discrete codebook tokens and continuous latent embeddings. By leveraging both synthetic and real datasets, we identify the severity of each type of collapses and triggering conditions. Our analysis reveals that random initialization and limited encoder capacity result in tokens collapse and embeddings collapse. Building on these findings, we propose potential solutions aimed at mitigating each collapse. To the best of our knowledge, this is the first comprehensive study examining representation collapsing problems in vector quantization.

cs.LG↗

arXiv2026

Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization

Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discretization before the encoder has captured the underlying data manifold. We term this phenomenon Premature Discretization. To resolve this, we propose Progressive Quantization (ProVQ), which incorporates the dynamics of quantization hardness as a fundamental yet previously overlooked axis in VQ training. By treating quantization as a curriculum that smoothly anneals from a continuous latent space to a discrete one, ProVQ effectively guides the codebook toward the well-expanded manifolds. Extensive experimental results demonstrate the broad effectiveness of ProVQ across diverse modalities. We report improved reconstruction and generative performance on the ImageNet-1K and ImageNet-100 benchmarks, highlighting the ProVQ's boost for generative modeling. Furthermore, ProVQ proves highly effective for modeling complex biological sequences, establishing a new performance ceiling for protein structure tokenization on the StrutTokenBench leaderboard.

cs.LG↗

arXiv2025

Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models

Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottleneck (IB) theory, to analyze the underlying strategies resolving this behavior. The framework models generation as a conflict between a 'Compression Pressure' - a drive to minimize overall codebook entropy - and a 'Diversity Pressure' - a drive to maximize conditional entropy given an input. We further decompose this diversity into two primary sources: 'Path Diversity', representing the choice of high-level generative strategies, and 'Execution Diversity', the randomness in executing a chosen strategy. To make this decomposition operational, we introduce three zero-shot, inference-time interventions that directly perturb the latent generative process and reveal how models allocate and express diversity. Application of this probe-based framework to representative AR, MIM, and Diffusion systems reveals three distinct strategies: "Diversity-Prioritized" (MIM), "Compression-Prioritized" (AR), and "Decoupled" (Diffusion). Our analysis provides a principled explanation for their behavioral differences and informs a novel inference-time diversity enhancement technique.

cs.LG↗

arXiv2025

Tidal Heating of the Lunar Magma Ocean: Reconciling an Old Moon with a Young Solidification

The timing of the Moon's formation is fundamental to understanding the early Earth-Moon system. Ages of lunar magma ocean (LMO) crystallization have long been regarded as a key proxy for that event. Yet returned lunar sample ages cluster near the relatively young age of ~4.35 billion years ago (Ga). These ages are commonly interpreted as recording either a young-Moon formation age or later thermal resetting. Here we show that, for an old Moon (>4.5 Ga), the ~4.35 Ga age cluster can instead arise naturally from early LMO thermal evolution under Earth's tidal forcing. We identify tidal heating within a partially molten LMO as a major internal heat source. It offsets much of the early heat loss and maintains a long-lived high-energy state for >150 million years. As crystallization proceeded, this stable state was ultimately lost through the rapid collapse of tidal heating. The last stages of LMO solidification were compressed into a short interval near ~4.35 Ga. The tidal heat source decouples Moon formation from final LMO solidification. As an outcome of LMO evolution, we predict asymmetric late-stage crystallization between the lunar nearside and farside, potentially linking tidally modulated LMO evolution to the long-term lunar dichotomy.

astro-ph.EP↗

arXiv2025

FML-bench: Benchmarking Machine Learning Agents for Scientific Research

Large language models (LLMs) have sparked growing interest in machine learning research agents that can autonomously propose ideas and conduct experiments. However, existing benchmarks predominantly adopt an engineering-oriented perspective: they emphasize application-oriented tasks and evaluate primarily on final performance and computational cost, overlooking agents' research processes and limiting assessment of their capabilities in scientific research settings. To more comprehensively evaluate agents in scientific research settings, we introduce FML-bench, a benchmark comprising 8 diverse and fundamental ML research tasks, and further propose complementary metrics, notably Exploration Diversity, which quantifies the variance of proposals across iterations and reveals how exploration patterns influence research outcomes. We evaluate state-of-the-art research agents on FML-bench, showing that agents employing broad exploration strategies exhibit higher exploration diversity and achieve superior performance, and that exploration diversity positively correlates with performance improvements across multiple tasks. We hope these findings and our benchmark inform future agent design and support the community in further investigating agent behavior. Our benchmark is available at https://github.com/qrzou/FML-bench.

cs.CL↗

arXiv2025

Ergodicity of infinite volume $Φ^4_3$ at high temperature

We consider the infinite volume $Φ^4_3$ dynamic and show that it is globally well-posed in a suitable weighted Besov space of distributions. At high temperatures / small coupling, we furthermore show that the difference between any two solutions driven by the same realisation of the noise converges to zero exponentially fast. This allows us to characterise the infinite-volume $Φ^4_3$ measure at high temperature as the unique invariant measure of the dynamic, and to prove that it satisfies all Osterwalder--Schrader axioms, including invariance under translations, rotations, and reflections, as well as exponential decay of correlations.

math.PR↗

arXiv2025

The diffusivity of supercritical Bernoulli percolation is infinitely differentiable

We prove that, the diffusivity and conductivity on $\mathbb{Z}^d$-Bernoulli percolation ($d \geq 2$) are infinitely differentiable in supercritical regime. This extends a result by Kozlov [Uspekhi Mat. Nauk 44 (1989), no. 2(266), pp 79 - 120]. The key to the proof is a uniform estimate for the finite-volume approximation of derivatives, which relies on the perturbed corrector equations in homogenization theory. The renormalization of geometry is then implemented in a sequence of scales to gain sufficient degrees of regularity. To handle the higher-order perturbation on percolation, new techniques, including cluster-growth decomposition and hole separation, are developed.

math.PR↗

arXiv2025

Unveiling Markov Heads in Pretrained Language Models for Offline Reinforcement Learning

Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing question: what kind of knowledge from PLMs has been transferred to RL to achieve such good results? This work first dives into this problem by analyzing each head quantitatively and points out Markov head, a crucial component that exists in the attention heads of PLMs. It leads to extreme attention on the last-input token and performs well only in short-term environments. Furthermore, we prove that this extreme attention cannot be changed by re-training embedding layer or fine-tuning. Inspired by our analysis, we propose a general method GPT2-DTMA, which equips a pretrained DT with Mixture of Attention (MoA), to accommodate diverse attention requirements during fine-tuning. Extensive experiments corroborate our theorems and demonstrate the effectiveness of GPT2-DTMA: it achieves comparable performance in short-term environments while significantly narrowing the performance gap in long-term environments.

cs.LG↗

arXiv2025

A frequency-independent bound on trigonometric polynomials of Gaussians and applications

We prove a frequency-independent bound on trigonometric functions of a class of singular Gaussian random fields, which arise naturally from weak universality problems for singular stochastic PDEs. This enables us to reduce the regularity assumption on the nonlinearity of the microscopic models in KPZ and dynamical $Φ^4_3$ in [HX19] and [FG19] to that required by PDE structures.

math.PR↗

arXiv2025

Interface fluctuations for $1$D stochastic Allen-Cahn equation revisited

We revisit the interface fluctuation problem for the $1$D Allen-Cahn equation perturbed by a small space-time white noise. We show that if the initial data is a standing wave solution to the deterministic equation, then under proper long time scale, the solution is still close to the family of traveling wave solutions. Furthermore, the motion of the interface converges to an explicit stochastic differential equation. This extends the classical result in \cite{Fun95} to full small noise regime, and recovers the result in \cite{BBDMP98}. The proof builds on the analytic framework in \cite{Fun95}. Our main novelty is the construction of a series of functional correctors that are designed to recursively cancel potential divergences. Moreover, to show these correctors are well-behaved, we develop a systematic decomposition of Fréchet derivatives of the deterministic Allen-Cahn flow of all orders. This decomposition is of its own interest, and may be useful in other situations as well.

math.PR↗

arXiv2025

An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer with Differentiable Simulation

The sim-to-real gap remains a critical challenge in robotics, hindering the deployment of algorithms trained in simulation to real-world systems. This paper introduces a novel Real-Sim-Real (RSR) loop framework leveraging differentiable simulation to address this gap by iteratively refining simulation parameters, aligning them with real-world conditions, and enabling robust and efficient policy transfer. A key contribution of our work is the design of an informative cost function that encourages the collection of diverse and representative real-world data, minimizing bias and maximizing the utility of each data point for simulation refinement. This cost function integrates seamlessly into existing reinforcement learning algorithms (e.g., PPO, SAC) and ensures a balanced exploration of critical regions in the real domain. Furthermore, our approach is implemented on the versatile Mujoco MJX platform, and our framework is compatible with a wide range of robotic systems. Experimental results on several robotic manipulation tasks demonstrate that our method significantly reduces the sim-to-real gap, achieving high task performance and generalizability across diverse scenarios of both explicit and implicit environmental uncertainties.

cs.RO↗

arXiv2025

Properties of QCD axion in two-flavor color superconductive matter with massive quarks

We investigate the properties of QCD axion at low temperature and moderate density in the Nambu-Jona-Lasinio model with instanton induced interactions by simultaneously considering the scalar and pseudo-scalar condensates in both quark-antiquark and diquark channels. We derive the analytical dispersion relations of quarks with four-type condensates at nonzero theta angle $θ=a/f_a$. The axion mass, quartic self-coupling, and the axion potential are calculated in both the chiral symmetry breaking and two-flavor color superconducting phases. Using the commonly adopted model parameters, we find that due to the emergence of color superconductivity, the chiral phase transition not only does not lead to a significant decrease in axion mass and self-coupling, but rather results in an obvious enhancement of them. As a $θ$ function, the axion potential exhibits an appropriate period of $π$, which is quite different from the case without considering the color superconductivity. The surface tension of axion domain wall is also calculated in the presence of color superconductivity.

hep-ph↗

arXiv2024

Representation Collapsing Problems in Vector Quantization

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and other generative models. Despite its prevalence, the characteristics and behaviors of vector quantization in generative models remain largely underexplored. In this study, we investigate representation collapse in vector quantization - a critical degradation where codebook tokens or latent embeddings lose their discriminative power by converging to a limited subset of values. This collapse fundamentally compromises the model's ability to capture diverse data patterns. By leveraging both synthetic and real datasets, we identify the severity of each type of collapses and triggering conditions. Our analysis reveals that restricted initialization and limited encoder capacity result in tokens collapse and embeddings collapse. Building on these findings, we propose potential solutions aimed at mitigating each collapse. To the best of our knowledge, this is the first comprehensive study examining representation collapsing problems in vector quantization.

cs.LG↗

arXiv2024

Ergodicity of 2D singular stochastic Navier-Stokes equations

We consider the 2D stochastic Navier-Stokes equations driven by noise that has the regularity of space-time white noise but doesn't exactly coincide with it. We show that, provided that the intensity of the noise is sufficiently weak at high frequencies, this systems admits uniform bounds in time, so that it has an invariant measure, for which we obtain stretched exponential tail bounds.

math.PR↗

arXiv2024

Locally Differentially Private In-Context Learning

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem with this promising commercial use is that LLMs have been shown to memorize their training data and their prompt data are vulnerable to membership inference attacks (MIA) and prompt leaking attacks. In order to deal with this problem, we treat LLMs as untrusted in privacy and propose a locally differentially private framework of in-context learning(LDP-ICL) in the settings where labels are sensitive. Considering the mechanisms of in-context learning in Transformers by gradient descent, we provide an analysis of the trade-off between privacy and utility in such LDP-ICL for classification. Moreover, we apply LDP-ICL to the discrete distribution estimation problem. In the end, we perform several experiments to demonstrate our analysis results.

cs.CR↗