Searcharxiv⌕ Search

arXiv subjects

Wenhao Zhao

Publications and source records attributed to Wenhao Zhao.

At least 19 recordsLinked to original sources
arXiv2026

Construction of the 2D non-Abelian Yang-Mills-Higgs measure via stochastic quantisation

We provide the first mathematical construction of the non-Abelian Yang-Mills-Higgs measure on a two-dimensional torus by implementing Parisi and Wu's ``stochastic quantisation'' procedure. We use a specific gauge covariant (but non-Markovian) approximation to the previously constructed associated Langevin dynamics and develop a covariant paracontrolled calculus for it. This allows us to obtain short-time control over times that are much longer than what the cubic nonlinearity naïvely suggests. When combined with the decay properties of the Yang-Mills-Higgs action under the deterministic gradient flow, as well as a quantitative measure of how the noise pushes the dynamic away from Yang-Mills connections, this is good enough to yield uniform-in-time bounds. We finally show that there exists a renormalisation under which our gauge covariant approximation converges to the Langevin dynamics (modulo gauge transformation) and that the latter is topologically irreducible and strong Feller. It therefore admits a unique invariant measure, providing the sought-after construction. Our construction is non-perturbative and works in particular for any fixed values of the coupling constants.

math.AP↗
arXiv2026

Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy

Psychotherapy clients may experience distress before they can coherently describe it, and their expression changes with emotion, perceived safety, and trust. Large language model-based client simulators often rely on clinically organized case descriptions, which can encourage responses explaining the client's difficulties more clearly than their current understanding warrants. We propose Pandora, a psychotherapy client simulation framework that models how psychological experience becomes situated, individual expression. Pandora updates psychological and relational states in response to therapist interventions, constructs subjective appraisals and attributions, and plans response content and strategy. A separate expression planner combines these decisions with language patterns distilled from the client's utterances to guide linguistic realization. We evaluate Pandora against five baselines on 115 cases from four counseling and motivational interviewing datasets. It achieves the highest expression similarity and overall disclosure-alignment score among the compared systems. In a four-evaluator study of 45 matched disclosure items, Pandora receives AI-like judgments in 7.2% of ratings, compared with 43.3--67.2% for the baselines and 35.6% without expression planning. The ablation also reduces expression similarity. These results support explicit expression planning in client simulation to improve alignment with individual language patterns and reduce perceived AI-like expression in the evaluated setting.

cs.HC↗
arXiv2026

Auto-MD-bench: Evaluating Autoresearch Agents for Real-World Medical Tasks

Autonomous agents are increasingly capable of developing machine learning (ML) models end to end. In medical practice, however, strong performance on the target metric does not fully characterize how good the models are in real-world use cases. For example, medical ML models should also provide well-calibrated risk estimates and remain robust across patient populations. Yet autonomous model development is typically guided by task objectives that emphasize simple predictive discrimination (e.g. AUROC). This raises a key question: are these objectives sufficient to guide agents toward models that meet the broader requirements of real-world medical use? In this study, we introduce Auto-MD-bench, a benchmark of 15 real-world medical tasks from 10 clinical datasets, spanning survival analysis, classification and sequential prediction, with external validation across cohorts, hospitals and time periods. We evaluate four agents: AIDE, AI Scientist v2, Codex, and Autoresearch. The strongest agents achieve competitive primary scores, yet their predicted risks are less calibrated than those of the simple baseline models, which could lead to severe medical accidents. Moreover, models with nearly identical primary scores can exhibit markedly different calibration, while performance varies substantially across population shifts. These findings show that primary task performance alone is insufficient to assess autonomous clinical modeling and multiple different metrics widely used in healthcare practice need to be taken into consideration.

cs.LG↗
arXiv2026

PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation

Polarization imaging provides physical cues beyond intensity imaging but typically requires specialized hardware. Recent methods infer polarization from RGB-like inputs, yet predict only normalized Stokes components or relative descriptors, from which the radiometric scale needed for full Stokes reconstruction has been divided out. We introduce PolarScale, a benchmark that makes this scale an explicit prediction and evaluation target. Built on existing trichromatic full-Stokes measurements, PolarScale takes the per-scene normalized total-intensity image $s_0$ (a scene-referred linear image, not a consumer sRGB photograph) and asks models to predict normalized Stokes components, AoLP/DoLP/DoCP, and a per-scene scale. Because the scale is divided out of the input, it is not physically identifiable; PolarScale therefore evaluates dataset-conditioned semantic scale estimation against a constant-scale control, together with angular, self-consistency, and physical-bound metrics. Across seven restoration-based and generative backbones and three prediction strategies, the strongest restoration models estimate the scale with 3.6-4.3% mean relative error versus 5.7% for the constant control and violate physical bounds on fewer than 0.25% of pixels, whereas two generative baselines collapse to a near-zero scale; explicit descriptor supervision improves descriptor accuracy (23.66 vs. 18.88 dB PSNR for MAE). Predicted full-Stokes representations improve diffuse/specular separation, material segmentation, and glare classification, although in diffuse/specular separation the learned scale performs only on par with the constant control.

cs.CV↗
arXiv2026

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

The sim-to-real gap remains a critical challenge in robotics, hindering the deployment of algorithms trained in simulation to real-world systems. We propose a flexible Real-to-Sim-to-Real (RSR) framework whose central contribution is an information-theoretic cost function that explicitly accounts for sim-to-real discrepancies. This cost balances two objectives, completing the task and steering the policy to collect real-world samples that are maximally informative for improving transfer. It can be integrated seamlessly into existing reinforcement learning algorithms (e.g., PPO, SAC) and ensures a balanced exploration of critical regions in the real domain. The framework treats differentiable simulation as optional: when a differentiable simulator is available, the collected informative data can also be used to tune simulator parameters. We implement the framework with the MuJoCo MJX platform and demonstrate its generality by evaluating on both manipulation tasks with a 6-DOF robotic arm and locomotion tasks on a legged robot. Empirical results show that our RSR loop yields more efficient data acquisition and substantially improves task performance in real-world that achieves a smoother sim-to-real transfer.

cs.RO↗
arXiv2026

OmniRisk: Omnidirectional Trajectory-Risk Learning for Agile Quadrotor Dynamic Avoidance

Agile quadrotor avoidance of fast-moving obstacles requires anticipating collisions and selecting feasible maneuvers within short reaction windows. Reliable predictive avoidance remains challenging because sparse range observations do not directly reveal obstacle motion, while online trajectory optimizers either scale poorly with obstacle count or remain efficient at the expense of reliability in dense, high-speed encounters. We present OmniRisk, an omnidirectional planning framework that learns trajectory-level risk offline for efficient onboard evasion. A fixed-dimensional tensor combines LiDAR range panoramas, dynamic masks, and Cartesian surface velocities to represent geometry and motion jointly. We formulate an asymmetric risk field aligned with obstacle velocity that emphasizes approaching interactions and attenuates receding ones. Accumulating this risk along predicted relative trajectories provides dense supervision and discourages unnecessary hesitation after obstacles pass. A dual-branch circular convolutional network predicts terminal boundary states and dynamic risks for candidate primitives over an omnidirectional anchor lattice in a single forward pass, followed by selection and closed-form reconstruction of the selected candidate primitive. This formulation removes online risk accumulation along trajectories and makes risk-inference cost independent of obstacle count. OmniRisk enables efficient onboard avoidance, with real-world flights demonstrating consecutive evasive maneuvers at relative encounter speeds up to 15 m/s without fine-tuning. Code is available at https://github.com/VANdexj/OmniRisk.

cs.RO↗
arXiv2026

TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer

Autonomous nano-UAV navigation requires accurate ego-motion estimation under stringent size, weight, power, and computing (SWaP-C) constraints, where visual sensors and LiDARs exceed payload limits, optical flow degrades in low-texture scenes, and inertial-only state estimation is susceptible to accumulated drift. While multi-zone time-of-flight (ToF) arrays provide a lightweight metric complement, 6-DoF estimation from merely 384 ranges per frame is challenged by invalid returns, anisotropic observability, and temporal computational scaling. We propose TIO-FORMER, a camera-free, optical-flow-free, and mapless range-inertial odometry framework driven by an IMU and an ultra-lightweight (15 g) payload of six orthogonal 8 x 8 ToF arrays. Our frontend pairs consecutive range grids with a bilateral gated difference, while IMU-guided cross-attention dynamically routes directional features conditioned on platform kinematics. A Streaming Causal Transformer couples an uncompressed Local KV cache with compressed Chunk-FIFO memory, maintaining bounded inference cost and memory footprint independent of flight duration. In real-flight evaluations, TIO-FORMER reduces open-loop position error by 54.4% compared to nano-UAV optical flow and by 66.4%-89.1% over learned inertial baselines. We also evaluate performance across multiple environments and robustness under severe sensing degradation. Deployed on an edge RISC-V companion computer, TIO-FORMER achieves a P95 latency of 10.466 ms and peak resident memory of 6.324 MiB (less than 5 percent system RAM), demonstrating that sparse range sensing provides practical geometric anchoring for resource-constrained micro-aerial robots. Code is available at https://github.com/Ly041021/TIO-Former.

cs.RO↗
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

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↗
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↗
arXiv2026

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

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

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↗
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↗