Searcharxiv⌕ Search

arXiv subjects

Yihong Wu

Publications and source records attributed to Yihong Wu.

At least 19 recordsLinked to original sources

Self-regularization and structural adaptation of NPMLE for Gaussian mixture models in all dimensions

We establish structural properties of the nonparametric maximum likelihood estimator (NPMLE) for $d$-dimensional Gaussian mixtures whose means lie in a hypercube. We show that, with high probability, the NPMLE based on $n$ independent observations self-regularizes by fitting a mixture model with $O((\frac{\log n}{\log\log n})^d)$ components, achieving the optimal model complexity without explicit model selection. Furthermore, the NPMLE exhibits a structural adaptation property: For data drawn from a finite mixture, the number of fitted components is bounded in probability as $n\to\infty$. Our proof applies a multivariate Jensen-type bound to control the typical number of critical points of the KKT function associated with the first-order optimality conditions. The key step is to lower bound its gradient norm uniformly on complex spheres. We establish this lower bound by decomposing the KKT function into an empirical fluctuation term and a relative density estimation error term, combining small-ball probability estimates for the former with polynomial approximation and Hellinger error bounds for the latter.

math.ST↗

Beyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries

Formal languages are widely used in software engineering to specify and verify program properties. Because their mathematical notation and logic are hard to read, developers often rely on natural-language documentation to understand the functions in formal libraries. Yet a documentation statement can be provably true and still hold after the function's behavior changes. We call a statement's dependence on the function's specific behavior attribution, and we give a method to check it. We design and implement DocAuth, a documentation-generation method that uses attribution to decide what to publish and attaches to each published sentence the formal property recovered from it, together with checkable evidence. On 150 functions from the Community Books library of the ACL2 theorem prover, three large language models produce proved but non-attributable properties for about a third of the functions. DocAuth matches or exceeds the attribution rate of a mutation-based filter while delivering 37% more attributable sentences. Compared with a pipeline that checks truth alone, it raises the share of published sentences that a second model confirms as attributable from 82.9% to 94.7%. These results show that provable truth does not guarantee that documentation reflects what a function actually does. Attribution complements truth as a criterion for generating and evaluating documentation for formal libraries.

cs.SE↗

The START mission: Probing the 2029 Apophis Flyby via a Low-Cost Geocentric SmallSat

The Student-led Threatening Asteroid Reconnaissance of Tsinghua (START) marks the inaugural mission of the Tianxing Program, a deep-space exploration initiative led by students at Tsinghua University. Conceived as a low-cost, rapid-response small-satellite mission, START will investigate the near-Earth asteroid (99942) Apophis during its close approach to Earth in April 2029, when significant terrestrial tidal forces will offer a rare opportunity to observe the physical and dynamical response of a rubble-pile asteroid in real time. The 300 kg spacecraft is scheduled for rideshare launch into low Earth orbit in early 2028 and will then use solar electric propulsion to transfer to a circular mission orbit with a semimajor axis of approximately 38,000 km and an inclination of 55 degrees. START will execute a high-speed flyby of Apophis from a closest distance of 7 km at the asteroid's closest approach to Earth, to capture its tidal response. The payload suite consists of a high-resolution narrow-field camera, a wide-field navigation camera, and three near-infrared multispectral imagers. By acquiring centimeter-scale imagery and meter-scale reflectance spectra, the mission will characterize the asteroid's surface morphology and composition and monitor immediate tidally induced surface modifications. Ultimately, START will provide geometrically complementary, high-cadence datasets to international flagship missions to Apophis, demonstrating a highly scalable and cost-effective architecture for future planetary defense and small-body exploration.

astro-ph.EP↗

VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program Structure

Static Application Security Testing (SAST) reports flag operations whose safety depends on project-specific context, and maintainers must decide which reports describe real defects. Large language models (LLMs) can interpret this context, but adjudicating a report with them requires the decisive code, which often lies far from the reported line, and a decision basis that program analysis can check. We present VulnSAGE, an adjudication system for SAST reports that connects LLM reasoning to program structure in both directions. Its report-centered slicer recovers the dependencies of the reported operation together with the program structure that explains them, such as the caller object on which a helper acts. CLAIM, an intermediate representation for report judgments, records each model interpretation as a semantic fact that cites the program relations it assumes. Program analysis checks these premises, and the verdict follows from the facts whose premises hold. Both mechanisms share a program graph, which lets the model cite the code it reads and lets the checker query those citations. Statically supported true positives then guide proof-of-concept generation and runtime reproduction. Across 187 labeled reports from four corpora covering five vulnerability families, VulnSAGE rejects 89 of 97 false alarms and retains 85 of 90 real defects. Under a common PoC procedure, 25 of its positive verdicts reproduce at runtime, compared with three for the LLM-based adjudicator LLM4SA. Applied to 45,440 alerts raised by five SAST tools on the 200 most-starred C/C++ projects on GitHub, it reproduces 104 defects at runtime. Maintainers have confirmed 24 of the 26 defects they have responded to, including ten previously unknown defects, nine of which are already fixed.

cs.SE↗

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native models developed to explore this path through agentic post-training. Our system combines a heterogeneous model pool with intelligent routing, recording the predicted capability demand, selected service tier, and subsequent interaction for each user turn. These records are converted into training examples that preserve interleaved reasoning, tool calls, and harness context, and are admitted through structural validation, six-dimensional semantic evaluation, and subscene-level labeling. Routing signals organize supervised fine-tuning into a three-stage curriculum and extend to routing-guided on-policy distillation, where a teacher supervises student-generated responses under the same progression. Capability-guided allocation then converts evaluation feedback into the next training mixture, closing an evaluation-selection-update loop in which what the system learns to do shapes what it learns from next. Across eleven benchmarks covering harness-based agents, tool use, coding, and instruction following, post-training raises the macro-average from 58.94 to 64.87 at 4B and from 65.60 to 69.04 at 9B, substantially narrowing the aggregate gap between the post-trained 4B model and the 9B base model. We further adapt NeoHorse-1-4B into NeoHorse-Jev-4B, a prefill-only model that returns structured decisions and probabilities for agent workflows. NeoHorse-1 provides an initial prototype of this feedback-driven process and a path toward harness-mediated RSI across successive iterations.

cs.CL↗

Anomalous Hall enhancement in fully compensated non-collinear antiferromagnetic Cr-doped Mn3Sn

The non-collinear antiferromagnet (AFM), Mn3Sn, exhibits ultrafast spin dynamics and negligible stray fields, making it a promising candidate for fast and energy-efficient spintronic devices. However, its practical applications remain limited by the relatively small Hall response compared with ferromagnets. Here, we demonstrate through both first-principles calculations and experiments that Cr-doping is a promising strategy to enhance the anomalous Hall transport in Mn3Sn without breaking the antiferromagnetic order. Our first-principles calculations reveal an effective Cr-doping window that enhances the anomalous Hall conductivity while largely preserving the host coplanar inverse triangular AFM order. Berry curvature and Wannier Hamiltonian analyses further reveal that Cr substitution amplifies the pre-existing Berry curvature hotspots through coordinated changes in the energy alignment, local interband gap, and Mn-derived orbital weight of the relevant bands. Experimentally, we have found that Cr doping not only supports our computational predictions (enhancement of the anomalous Hall conductivity), but also suppresses the transition to helical or spin-glass phases at low temperatures. These findings demonstrate that Cr-doping is an effective strategy for stabilizing the AFM order while simultaneously improving the anomalous Hall transport properties over a wide temperature range in Mn3Sn.

cond-mat.mtrl-sci↗

Sharp detection thresholds for random geometric graphs with polynomial average degrees

We study the random geometric graph formed by connecting $n$ independent uniform points on $\mathbb S^{d-1}$ whenever their inner product exceeds a threshold chosen to give edge density $p$. We establish the conjectured dimensionality threshold for indistinguishability from the Erdös-Rényi graph $G(n,p)$ throughout the sparse regime with polynomially growing average degree. Specifically, for every fixed $δ>0$, if $p\to0$, $p\ge n^{-1+δ}$, and $d\gg (np\log(1/p))^3$, then the Kullback-Leibler (KL) divergence between the two distributions vanishes. Our proof builds on the posterior analysis framework introduced in previous work of the authors, combining a truncated second moment analysis with Fourier and spherical harmonic expansions. As in prior works, we reduce the KL bound to controlling a truncated $χ^2$-divergence $Δ$ for the neighborhood of the last vertex conditional on the graph induced by the preceding vertices. We then bound $Δ$ using a Fourier expansion of the conditional likelihood ratio for this neighborhood, where the high-frequency contribution is made negligible by truncation to a typical-degree event, while a spherical harmonic expansion approximates the low-frequency contribution in terms of posterior moments of bounded-degree harmonic polynomials. The key observation is that these moments and $Δ$ satisfy a coupled system of cavity recurrences, yielding a self-bounding inequality that implies the desired KL bound.

math.PR↗

FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA

Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-improvement methods can turn failures into new behaviors, but offer limited control over where a correction should apply or which previously correct answers it may break. We therefore frame post-deployment improvement as controlled behavioral maintenance: recurring failures should become scoped skill patches, and each patch should earn deployment with- out introducing regressions. We instantiate this view in FINSKILLOPS, a multi-agent system for SEC filing QA. FINSKILLOPS derives reusable skills from evidence-grounded, typed failure diagnoses and governs them through targeted validation, protected-case regression checks, negative controls, and versioned replacement or retirement. Across six financial QA benchmarks, a single frozen skill registry achieves the highest verdict-weighted correctness and reference consistency among the evaluated systems. Evolved skills raise correctness from 3.70 to 4.55 on our enhanced benchmark. In a separate 12-round operational study, only six of 33 proposed skills are promoted, while the monitoring non-correct rate falls from 20.0% to 12.5%. These results establish controlled skill scope, admission, and lifecycle management as the foundation for reliable self-improvement.

cs.AI↗

Entropy of Bernoulli Measures Conditioned on Affine Subspaces and a Problem of Ancheta--Massey

A textbook result in information theory is that linear encoders achieve the entropy for lossless compression of Bernoulli source with parameter $p$. For lossy compression, however, linearity is known to incur strict suboptimality compared to the rate-distortion function. Massey asked whether the optimal rate for linear encoding is achieved simply by compressing a fraction of the bits linearly and losslessly and estimating the rest by zero \cite{Massey1978}. For $p=\frac12$, Ancheta answered this question affirmatively \cite{Ancheta1978}. This note extends Ancheta's result to all $p<\frac12$. The key argument is to bound the entropy of the posterior distribution conditioned on an affine subspace in terms of its marginals. The proof was discovered by GPT-5.6 Sol in an interactive process guided by the author. The purpose of the present note is to communicate a simplified version of this proof and to make connections with the existing literature on coding theory and spin glass theory.

cs.IT↗

Empirical Bayes linear regression in high dimensions: Method of moments and sub-linear sample complexity

We study empirical Bayes estimation of the prior in high-dimensional linear regression $\mathbf{y}=\mathbf{X}\mathbfβ+\mathbf{\varepsilon}$, where the regression coefficients are drawn independently from an unknown sub-Gaussian prior. In contrast to the sequence model, the design matrix couples the latent coefficients, so that recovering the prior requires deconvolving it from both the noise and copies of itself. We introduce the \emph{Empirical Bayes Method of Moments} (EBMoM), a computationally efficient procedure for general designs that recursively estimates the prior moments through a lower-triangular system of estimating equations and runs in time $O(np^2)$. Under mild design conditions, satisfied in particular by a broad class of correlated random designs, we show that EBMoM consistently estimates a growing number of moments and hence the prior itself, provided that $n\geq p^{1-o(1)}$. A matching information-theoretic lower bound, valid for a broad class of designs, shows that this sub-linear sample complexity is optimal for nonparametric prior estimation. This improves on existing results for likelihood-based methods whose consistency requires a linear sample size $n=Ω(p)$.

math.ST↗

Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models

Layer-wise post-training quantization reconstructs each layer from inputs already altered by the quantized prefix. QEP compensates for this drift with one model-wide coefficient, conflating the model-level operating point with residual variation across layers. We present FADE, which constructs layer-specific coefficients from normalized round-to-nearest distortion and a heuristic calibrated-solver response. It requires no training or per-model coefficient search and adds no inference-time operation. We evaluate seven Whisper, Moonshine, and Qwen3-ASR models at 3 and 4 bits on four English ASR benchmarks. Across 38 settings, FADE lowers mean word error rate relative to fixed QEP-0.5 in 31, although a development-tuned global coefficient recovers much of this gap. The largest absolute reductions occur in 3-bit settings whose final error remains too high for practical use; these results measure collapse mitigation rather than deployable accuracy. In two lower-WER 3-bit cases, FADE reduces the tuned-global result from 3.67 to 3.10 and from 13.03 to 11.63. Most 4-bit differences from the tuned control are within a descriptive tolerance, and one reverses. Paired reruns and within-seed permutations on an outcome-informed subset support assignment sensitivity in selected cases, but do not estimate a matrix-wide success rate. FADE is therefore a layer-wise alternative when per-model coefficient search is unavailable, not a universal replacement for tuned global compensation.

cs.SD↗

Sharp regret-Hellinger bounds for Gaussian empirical Bayes via polynomial approximation

A central problem in the theory of empirical Bayes is to control the regret (excess risk) of a learned Bayes rule by the Hellinger distance between the estimated and true marginal densities. In the normal means model, the classical result of Jiang and Zhang (2009) achieves this only after regularizing the Bayes rule and incurs an extraneous cubic logarithmic factor through a delicate recursive argument. This paper introduces a new technique, based on polynomial approximation and Bernstein-type inequalities for weighted $L_2$ norms, that bounds the unregularized regret directly. The method is conceptually simpler and yields sharper, sometimes optimal, regret bounds. For compactly supported priors, we prove the sharp bound that the regret is $O(ε^2 \frac{\log(1/ε)}{\log\log(1/ε)})$, where $ε$ is the Hellinger distance between the marginal densities. The same method also extends to priors with exponential tails. Conversely, we show that regularization is genuinely necessary for heavy-tailed priors under only bounded moment assumptions. As statistical consequences, we obtain improved regret bounds for the nonparametric maximum likelihood estimator (NPMLE). Notably, for compactly supported priors, by determining the optimal Hellinger rate of mixture density estimation, we show that the optimal regret for sample size $n$ scales as $Θ(\frac{1}{n}(\frac{\log n}{\log\log n})^2)$, attained by the NPMLE within a $\log\log n$ factor.

math.ST↗

Gradient flows for empirical Bayes in high-dimensional linear models

Empirical Bayes provides a powerful framework for learning and adapting to latent structure in data. In sequence models where an independent observation is associated to each latent parameter, theory and methods around empirical Bayes are well-developed. However, in models where latent parameters and observed data interact through more complex designs, many statistical and algorithmic questions remain unanswered. In this work, we study a canonical setting of empirical Bayes estimation for the distribution of regression coefficients in a high-dimensional Bayesian or random effects linear model. Computationally, we propose a new system of gradient flow equations for computing a nonparametric maximum likelihood estimator (NPMLE), which jointly optimizes over the prior and posterior distributions of the regression coefficients in a Gibbs variational representation of the marginal log-likelihood. A diffusion-based implementation yields an adaptive Langevin dynamics algorithm in which the prior evolves continuously to optimize a sequence model log-likelihood defined by the coordinates of the Langevin sample. Theoretically, we show polynomial-time convergence of the proposed gradient flow to a near-NPMLE from any initialization within a convex sub-level set of the marginal log-likelihood, by developing a high-temperature log-Sobolev inequality for the posterior law. We establish the statistical consistency of any near-NPMLE under deterministic conditions for the regression design as $n,p\rightarrow\infty$.

math.ST↗

FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering

Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardized, and highly redundant disclosures. Existing retrieval-augmented and multi-agent systems typically derive retrieval queries directly from the user's question and rank candidates by semantic similarity. Together, these choices create prior-corpus misalignment: a mismatch between model priors and the target filings' structure, terminology, and evidence standards. As a result, query generation misses corpus-specific evidence, while semantic reranking favors topically similar but evidentially invalid false-positive chunks. We propose FinSAgent, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate. FinSAgent combines (1) role-specialized agents anchored to the mandated 10-K item structure, (2) database-aware query decomposition that conditions each agent's sub-queries on a lightweight, summary-level view of the local corpus, and (3) multi-path retrieval with a learned feature-gated reranker that separates evidential validity from semantic similarity. Across five offline financial QA benchmarks, FinSAgent improves retrieval coverage and answer correctness over strong single-agent and multi-agent baselines; in a three-arm randomized online experiment with 1,000 anonymous user ratings, it also receives higher scores than baselines.

cs.IR↗

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development

Retrieval-augmented generation (RAG) agent development is hindered by the lack of executable ground-truth agent-environment interaction trajectories. Existing datasets provide questions, answers, and evidence, but lack fine-grained supervision for retriever invocation, dynamic planning, and stepwise decision-making. Reinforcement learning offers a potential solution, but often suffers from sparse rewards and cold-start failures when base large language models (LLMs) lack sufficient reasoning capability. Meanwhile, existing data synthesis methods mainly generate post-hoc rationales rather than executable environment-interaction trajectories. In this paper, we propose EviPath, an evidence-anchored reasoning path synthesis paradigm for RAG agent development. EviPath reverse-engineers executable trajectories from question-answer pairs and supporting evidence through three stages: (i) Abductive Subtask Planning, which decomposes questions and plans dependency-aware solution paths; (ii) Faithful Sub-question Answering, which uses supporting evidence as a proxy environment to generate grounded intermediate thoughts and answers; and (iii) Conversational Fine-Tuning, which converts complete trajectories into a dialogue format for supervised fine-tuning. Experiments on widely used question-answering benchmarks show that an 8B model trained on our synthetic corpus significantly and consistently outperforms state-of-the-art baselines, achieving a 14.7% absolute Exact Match gain in open-domain question answering.

cs.CL↗

SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts

Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry. Existing 3D-aware models either rely on costly 3D-specific data or utilize RGB-only inputs with heuristic sampling and monolithic, shallow fusion, which respectively disrupt essential spatiotemporal connectivity and induce modality contention across diverse spatial tasks. To overcome these bottlenecks, we introduce SpaR3D-MoE, an end-to-end framework that enables adaptive spatial reasoning by equipping MLLMs with geometry-aware capabilities from only sparse RGB inputs. First, we propose an adaptive spatiotemporal manifold sampling mechanism that constructs a geometry-aware spatiotemporal graph to extract informative keyframes, effectively mitigating sequence redundancy while preserving the scene's topological connectivity. Second, we introduce the heterogeneous geometry-inductive Mixture-of-Experts driven by an instruction-pose aware router, which adaptively routes multimodal tokens to specialized experts, resolving the cross-modal contention inherent in monolithic fusion. Extensive experiments on VSI-Bench, ScanQA, and SQA3D demonstrate that our method achieves state-of-the-art performance. Notably, SpaR3D-MoE achieves the highest average score of 63.5 on VSI-Bench, outperforming the strongest baseline by 7.8 absolute points, alongside relative improvements of 35.4% and 51.4% in Route Plan and Relative Direction tasks, respectively.

cs.CV↗

The broken sample problem revisited: Proof of a conjecture by Bai-Hsing and high-dimensional extensions

We revisit the classical broken sample problem: Two samples of i.i.d.\ data points ${\mathbf{X}}=\{X_{1},\ldots , X_{n}\}$ and ${\mathbf{Y}}=\{Y_{1},\ldots ,Y_{m}\}$ are observed without correspondence with $m\leq n$. Under the null hypothesis, ${\mathbf{X}}$ and ${\mathbf{Y}}$ are independent. Under the alternative hypothesis, ${\mathbf{Y}}$ is correlated with a random subsample of ${\mathbf{X}}$, in the sense that $(X_{π(i)},Y_{i})$'s are drawn independently from some bivariate distribution for some latent injection $π:[m] \to [n]$. Originally introduced by DeGroot, Feder, and Goel to model matching records in census data, this problem has recently gained renewed interest due to its applications in data de-anonymization, data integration, and target tracking. Despite extensive research over the past decades, determining the precise detection threshold has remained an open problem even for equal sample sizes ($m=n$). Assuming $m$ and $n$ grow proportionally, we show that the sharp threshold is given by a spectral and an $L_{2}$ condition of the likelihood ratio operator, resolving a conjecture of Bai and Hsing in the positive. These results are extended to high dimensions and settle the sharp detection thresholds for Gaussian and Bernoulli models.

math.ST↗

Resolution of the Detection Threshold Conjecture for Random Geometric Graphs in the $d>n$ Regime

A random geometric graph (RGG) is generated by first sampling latent points $x_1,\ldots,x_n$ independently and uniformly from the unit sphere in $\mathbb{R}^d$, and then connecting each pair $(i,j)$ if $\langle x_i,x_j\rangle$ exceeds some threshold $τ$. We study the sharp detection threshold -- the largest dimension at which the RGG can be statistically distinguished from the Erdős--Rényi graph with the same edge density $p$. This threshold is conjectured to be $d \asymp (nh(p))^3$, where $h(p)=p \log \frac{1}{p} + (1-p) \log \frac{1}{1-p}$ is the binary entropy function. Previous works proved this conjecture for dense graphs with constant $p$ and, up to polylogarithmic factors, very sparse graphs with $p=Θ(1/n)$. In this paper, we prove that detection is impossible when $d\gg (nh(p))^3$ and $d\ge (1+ε) n$ for any constant $ε>0$, thereby resolving the conjecture in the regime $p\gtrsim n^{-2/3}/\log n$ and improving upon the state of the art in the regime $1/n \ll p \ll n^{-2/3}/\log n$. The key to our proof is a sharp analysis of the posterior distribution of the latent points given the observed graph, obtained through an information-theoretic comparison argument combined with strong log-concavity.

math.PR↗