Search arXiv⌕ Search

arXiv subjects

Jian Song

Publications and source records attributed to Jian Song.

At least 19 recordsLinked to original sources
arXiv2026

Generalized Wishart processes under nonlinear expectation

We develop a theory of generalized Wishart processes within the framework of $G$-expectation, with $G$-Dyson Brownian motion and the $G$-Wishart process as two typical examples. In contrast to the classical setting, we show that $G$-Dyson Brownian motion may exhibit collisions and provide a sufficient condition ensuring the non-collision of the eigenvalues of generalized Wishart processes. We then derive the equations governing the high-dimensional limits of the empirical spectral measures under $G$-expectation, leading to the corresponding semicircle law for $G$-Dyson Brownian motion and Marchenko--Pastur law for the $G$-Wishart process.

math.PR↗
arXiv2026

OpenEarth-OVS44: A Multimodal Remote Sensing Dataset for Open-Vocabulary Segmentation

In remote sensing, open-vocabulary segmentation is particularly important for flexible and scalable land-cover understanding across diverse regions, as it improves generalization to novel categories without requiring exhaustive pixel-level annotations. Despite its great promise, progress in this area remains largely constrained by existing datasets with limited category coverage and overly coarse taxonomies, and therefore struggles to support fine-grained semantic understanding required in real-world applications such as urban functional zoning, carbon accounting, and post-disaster assessment. To address these challenges, we present OpenEarth-OVS44, a multimodal benchmark with 290,587 expert-verified segments from 2,832 RGB images and 1,341 strictly registered RGB-SAR pairs at sub-meter spatial resolution, covering 40 cities across France, Japan, and the United States under a unified 44-class taxonomy organized into 9 base categories. Three evaluation tracks are provided: an RGB-only fine-grained benchmark, a multimodal track with diverse synthetic cloudy conditions for weather-robust evaluation, and a held-out cross-region track. Extensive experiments on representative open-vocabulary segmentation models demonstrate that training on OpenEarth-OVS44 substantially improves fine-grained segmentation performance over the strongest training-free baseline, with improvements of up to 7.1 mIoU points on unseen categories and 27.6 mIoU points on seen categories. The dataset and code will be released.

cs.CV↗
arXiv2026

RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis

Rheumatoid arthritis (RA) assessment from hand radiographs requires multi-level analysis and modeling of anatomical structures and fine-grained local pathological changes. However, existing public resources do not support such unified multi-level analysis, often lacking full-hand coverage, fine-grained annotations, and consistent integration with clinical scoring systems. In particular, annotations that enable quantitative analysis of bone erosion (BE) remain scarce. RAM-H1200 contains 1,200 hand radiographs collected from six medical centers, with multi-level annotations including (i) whole-hand bone structure instance segmentation, (ii) pixel-level BE masks, (iii) SvdH-defined joint regions of interest, and (iv) joint-level SvdH scores for both BE and joint space narrowing (JSN). It is designed to evaluate whether models can jointly capture anatomical structure, localized erosive pathology, and clinically standardized RA severity from hand radiographs. The proposed BE masks enable, for the first time, quantitative BE analysis beyond coarse categorical grading by providing explicit spatial supervision for lesion extent and morphology. To our knowledge, RAM-H1200 is the first public large-scale benchmark that jointly supports whole-hand bone structure instance segmentation, pixel-level BE delineation, and clinically grounded joint-level SvdH scoring for both BE and JSN. Results across benchmark tasks show that anatomical modeling is substantially more mature than quantitative BE analysis: whole-hand bone segmentation achieves strong performance, whereas BE segmentation remains a major open challenge. By unifying anatomical structure modeling, quantitative lesion analysis, and clinically grounded SvdH scoring, RAM-H1200 provides a single benchmark for comprehensive RA analysis on hand radiographs.

cs.CV↗
arXiv2026

Type I estimates for the Kähler-Ricci flow II

In this paper, we establish geometric consequences of our Type I scalar curvature estimate for finite-time solutions of the Kähler-Ricci flow on compact Kähler manifolds. We prove a uniform global diameter bound and a Type I diameter bound for every fibre of finite time holomorphic contraction. These estimates yield Gromov-Hausdorff convergence to a unique compact metric space homeomorphic to the normal Kähler space determined by the limiting cohomology class. We also establish a local partial $C^0$ estimate for the normalized flow and show that the tangent shrinkers are normal complex analytic varieties with log terminal singularities.

math.DG↗
arXiv2026

Inverse identification of thermal-radiative parameters for reduced effective-temperature uncertainty in an ion optical clock

The blackbody-radiation (BBR) shift remains a leading systematic uncertainty of room-temperature single-ion optical clocks. Accurate evaluation of this shift requires the effective temperature at the ion position, which is difficult because RF heating, low and spatially varying surface emissivity and inaccessible trap surfaces make this quantity difficult to measure directly. Here, we developed a hybrid inversion framework that combines radiance-domain infrared thermography, black-painted high-emissivity reference regions, a finite-element model of a 171Yb+ end-cap ion trap and a reduced-order surrogate for repeated forward calculations and parameter identification. The surrogate reproduced the FE test fields with a full-field mean absolute error (MAE) of 0.02220 mK. The calibrated model predicted the ion-position effective temperature with a combined standard uncertainty of 155.0 mK, corresponding to a temperature-related BBR frequency-shift uncertainty of 1.647 x 10^-19 for the 2S1/2-2F7/2 (467 nm) E3 transition. This method provides a reproducible route for reducing and tracing the BBR uncertainty of room-temperature trapped-ion optical clocks.

physics.atom-ph↗
arXiv2026

Fundamental groups of Calabi-Yau spaces

We study the fundamental groups of a normal projective Calabi-Yau variety $X$ with klt singularities and of its regular locus $X_{reg}$. We prove that both groups are almost abelian, and that their ranks are determined by the irregularities of finite etale and quasi-etale covers, respectively. Our approach is differential geometric, and relies on recent advances in the geometric theory of complex Monge-Ampere equations.

math.DG↗
arXiv2026

Type I estimates for the Kahler-Ricci flow I

We establish the Type I estimate for the scalar curvature of the Kahler-Ricci flow on compact Kahler manifolds, for arbitrary smooth initial metrics, whenever the flow develops finite time singularities. This estimate is a building block for the analytic minimal model program with Ricci flow.

math.DG↗
arXiv2026

Stability and gradient estimates for fully nonlinear elliptic equations on hermitian manifolds

The known proofs of the gradient estimate for complex Hessian equations rely on the second order estimate of Hou-Ma-Wu and on a Liouville theorem of Dinew-Kolodziej. In this paper, we give a direct proof of the gradient estimate for concave fully nonlinear elliptic equations on compact Hermitian manifolds, which uses neither the Hou-Ma-Wu estimate nor the Liouville theorem. Instead, the proof combines a stability estimate with a comparison argument against nearby smooth admissible functions. We also give an independent proof of the complex Hessian estimate on compact Kähler manifolds, based on Dirichlet Green's functions, under additional assumptions on the operator.

math.AP↗
arXiv2026

Geometric stability for complex Monge-Ampere equations

Let $X$ be a compact Kahler manifold. The analytic stability theorem of Kolodziej for complex Monge-Ampere equation states that for any Kahler metrics $ω$ and $ω'$ in the same cohomology class, if their volume measures are bounded in $L^p(X)$ (for some $p>1$) and close in $L^1(X)$, then their Kahler potentials are close in $L^\infty(X)$. In this paper, we establish the geometric stability for complex Monge-Ampère equations that $L^1$-closeness of volume measures implies $L^\infty$-closeness for the induced distance functions by $ω$ and $ω'$. Consequently, we prove that any non-smooth Kahler current with volume measure bounded in $L^p$ (for some $p>1$) and Ricci current bounded below induces a unique metric space, which turns out to be a compact RCD space homeomorphic to $X$ itself.

math.DG↗
arXiv2026

Geometric Holder estimates for complex Monge-Ampere equations

This paper is the continuation of our earlier work on Holder estimates for Kahler potentials on compact normal Kahler spaces. We establish a geometric counterpart for analytic Holder regularity of Kolodziej. If a singular metric $ω_ϕ$ has Holder continuous potentials with respect to a smooth background metric, then its distance function is Holder continuous with respect to a smooth background distance. The result holds on normal Kahler spaces and yields compactness of the metric completion as well as its identification with the underlying complex space if $ω_ϕ$ is a Kahler current. Under this positivity assumption, our estimates establish the Holder equivalence between the intrinsic canonical Kahler metrics and the extrinsic smooth metrics on Kahler-RCD spaces, particularly on smoothable Kahler-Einstein spaces.

math.DG↗
arXiv2026

Ricci entropy, RCD structures and Kahler spaces

This paper is the final installment in our series on the geometric theory of complex Monge-Ampere equations. We study singular Kahler metrics on compact normal Kahler spaces with klt singularities whose volume densities lie in $L^p$ for some $p>1$. We show that a lower bound for the Ricci current in the sense of pluripotential theory is equivalent to a synthetic Ricci lower bound in the sense of RCD theory. As a consequence, every Kahler class on a compact normal Kahler space with klt singularities admits an RCD structure, which makes differential geometric analysis available on singular complex spaces. As an application, we show that the fundamental group of a compact Kahler Calabi-Yau space with klt singularities is almost Abelian. We further establish compactness results for singular Kahler-Einstein spaces.

math.DG↗
arXiv2026

The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding

Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (RS) imagery within a limited visual-input budget. Existing selection-based methods either prune tokens and select patches through relevance scoring, or crop actively through repeated inspection. Neither strategy directly redistributes pixels within a continuous full-scene view: the first retains selected tokens or patches, and the second re-encodes a crop detached from its surroundings. Our pilot study finds that a frozen MLLM already produces useful question-guided spatial requests, yet crop-based inspection of the selected regions does not consistently improve its answers. We therefore formulate UHR understanding as a question of where to spend a fixed pixel budget. Based on this, we introduce GazeEarth, a simple-yet-effective training-free framework that couples question-guided region selection with full-scene foveated observation. The MLLM selects evidence cells from an indexed overview; a deterministic, topology-preserving warp resamples the original image onto a fixed-size canvas, enlarging their shared neighborhood while compressing the periphery; the same frozen model answers from this focused view, using at most two MLLM calls and no external selector or iterative search. Across three UHR remote sensing benchmarks and four frozen backbones, GazeEarth improves benchmark-averaged accuracy by 4.6 to 9.4 percentage points over direct answering and 3.4 to 4.3 over overview answering, outperforming task-trained methods. Our analyses show that existing MLLMs can guide where to look in UHR images on their own, and that what they can infer from the selected evidence depends on how that evidence is presented.

cs.CV↗
arXiv2026

Finite-Time Singularities of the Kähler--Ricci Flow on Fano Bundles II

The analytic minimal model program proposed in \cite{SongTianSingularities, JST} seeks to describe the birational transitions and fibre collapsing of the Kähler--Ricci flow through the geometry of its singularities. A fundamental conjecture of \cite{JST} predicts Type I bounds for the scalar curvature and diameter of every fibre contratced by the limiting cohomological class at the finite singular time. This paper is a continuation of \cite{Splitting} that establishes the Type I conjecture for collapsing solutions on Fano bundles with arbitrary smooth Fano fibres. If the fibre admits a smooth Kähler-Einstein metric, the Type I bound holds for the full curvature tensor.

math.DG↗
arXiv2026

Rough backward stochastic differential equations

We develop an intrinsic well-posedness theory for nonlinear backward stochastic differential equations (BSDEs) driven simultaneously by Brownian motion and a (level-$2$) rough path of finite $p$-variation. Unlike earlier approaches based on smooth approximation or transformation methods, we formulate the equation directly by viewing its solution as a rough semimartingale (in the sense of \cite{friz2023rough}). This framework is particularly suited to BSDEs, whose Brownian martingale component is only implicitly defined and lacks the \emph{a priori} time regularity required by stochastic-sewing-based controlled rough path methods \cite{fhl21,allan2024rough}. We establish comparison, existence, uniqueness, and stability under the natural regularity condition $H\in C_b^γ$, $γ>p$. The main analytical difficulty, namely, the loss of integrability arising from nonlinear composition, is overcome through conditional $p$-variation norms with BMO-type properties. Finally, by randomizing the rough driver as a Brownian rough path, we establish a direct correspondence between rough BSDEs and backward doubly stochastic differential equations (BDSDEs).

math.PR↗
arXiv2026

Scaling limit for the pinning model in correlated Gaussian environment beyond the $L^2$-regime

In this paper, we study the scaling limit of the pinning model in correlated Gaussian environment. The tail probability of the underlying renewal process of the model has a polynomial decay with exponent $α>0$. The covariance of the Gaussian environment $\{ω_n\}_{n\in\mathbb N}$ is given by $\text{Cov}_{\mathbb P}(ω_n,ω_m)\sim |n-m|^{2H-2}$ with $H\in(0,1)$. Assuming $α\in(0,\frac12]$, $H\in(\frac12,1)$ and $α+2H>2$, we show that the partition function of the disordered pinning model, under the appropriate scaling, converges in distribution to the $L^1$-solution of the fractional stochastic heat equation driven by Gaussian noise correlated in time and localized at the origin. In particular, it is known that the solution is not $L^2$-integrable when $α<\frac12$.

math.PR↗
arXiv2026

Finite-Time Singularities of the Kähler--Ricci Flow on Fano Bundles

We study collapsing finite-time singularities of the unnormalized Kähler--Ricci flow on Fano bundles arising in the analytic minimal model program. For a Fano bundle $X^n\rightarrow Y^m$, we prove a maximal splitting theorem by the Kähler-Ricci flow that every tangent space at a fixed limiting point splits globally as \((\C^m,g_{\rm E},J_0)\times(Z',d',J')\). If the fibre has complex dimension one, we prove a global Type-I bound for the full curvature tensor and show that the ambient and intrinsic diameters of every fibre are uniformly comparable to \(\sqrt{T-t}\). Furthermore, every tangent flow at any fixed limiting point is the round shrinking cylinder \(\C^m\times\PP^1\).

math.DG↗
arXiv2026

Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher

On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant success in Large Language Models (LLMs) and has recently been adapted to flow matching models. However, this paradigm suffers from two major issues: First, training a separate, task-specific teacher for every new objective incurs high computational costs. Second, the discrepancy between teacher and student distributions often leads to compounding errors along the generation trajectory. In this paper, we introduce \textbf{Self-OPD}, a teacher-free OPD framework for flow matching models that turns the student's own self-exploration into step-wise supervision. At each timestep, Self-OPD branches the deterministic next-state prediction into $K$ stochastic SDE candidates, rolls them out with the ODE sampler, and compares their rewards against a deterministic self-reference baseline to obtain normalized advantages. The velocity field is optimized with an all-branch pull-push objective, where high-advantage branches attract the student and low-advantage branches repel it under direction-aware attenuation and SDE-variance normalization. For multi-objective alignment, Self-OPD fuses normalized scores at the reward level, avoiding direct gradient conflict. Experiments on single and mixed reward benchmarks show that Self-OPD outperforms prior RL and OPD methods without task-specific teachers.

cs.CV↗