Searcharxiv⌕ Search

arXiv subjects

Tianyu Zhao

Publications and source records attributed to Tianyu Zhao.

At least 19 recordsLinked to original sources

Wide Field 3D Color Topography for Steep-slope Structures

Three-dimensional (3D) topography measurement is essential for industrial inspection and scientific research. However, existing techniques are limited by an inherent trade-off between resolution, speed, color imaging capability and the ability to measure large-angle surfaces. To overcome these limitations, we propose a novel method that integrates ring light illumination based wide-field 3D imaging with an iterative shape-from-focus (SFF) algorithm. The system employs coaxial epi-illumination combined with ring light illumination to simultaneously acquire information from flat regions and steep slopes. The proposed iterative SFF algorithm achieves high-resolution 3D topography measurement. Full-color 3D reconstructions of electronic chips and PCBs demonstrate that the proposed method enables fast scanning and sub-micrometer resolution and significantly extending the measurable inclination range for large-angle structures. This method fills a critical gap in existing technology for fast, natural-color, 3D imaging and measurement of samples with steep topographies.

physics.optics↗

Beyond the Log-Linear Frontier: Pre-Asymptotic Analysis of Finite-Budget Neural Scaling Laws

Classical neural scaling laws model excess risk as a separable power law in model capacity $N$ and dataset size $D$. At finite budgets, however, empirical learning curves and compute-optimal allocations depart from this log-linear frontier. This paper analyzes how spectral and domain heterogeneity govern these finite-scale departures. Along the capacity axis, Mellin--Barnes analysis of covariance resolvents yields a three-term expansion where competing spectral and regularization modes produce finite-scale curvature and logarithmic transitions. Because fitting multiple power laws on narrow pilot grids is ill-conditioned, we eliminate the loss floor via first-order Aitken differencing to obtain a well-conditioned closed-form initializer. Along the data axis, KKT duality reduces $K$-domain mixing to scalar water-filling, yielding finite-budget bottleneck bounds, an online sampling curriculum, and a simplex Hessian metric for cross-domain transfer. Along the iso-compute frontier $C=6ND$, we prove that the optimal allocation exponent drifts in proportion to capacity and data exponent variances, while Schur-complement reduction separates intrinsic drift from frozen-hyperparameter bias. Across 45 operator spectra, Pythia (70M--12B), Chinchilla (245 runs), and RegMix (17 domains), our estimators achieve $5.89\%$ holdout MAPE, cut high-compute allocation regret by up to $76.4\%$, and reduce cross-scale mixture RMSE by $59.4\%$ with zero selection regret.

cs.LG↗

TriTD: Tri-Partite Trajectory-Distribution Distillation for Real-Time Autoregressive Video Generation

Autoregressive (AR) video diffusion has emerged as a leading paradigm for efficient video generation, yet its practical deployment remains bottlenecked by the trade-off between generation quality and inference efficiency. We attribute this bottleneck to three error sources in AR rollouts: the base model error, the train-inference distribution mismatch, and the upstream error propagation. Building on this decomposition, we derive closed-form upper bounds on the per-step and cumulative errors, providing a principled basis for jointly optimizing generation quality and inference efficiency. Guided by this analysis, we propose TriTD, a Tri-Partite Trajectory-Distribution co-optimized distillation framework with three complementary modules. First, for ODE initialization, we adopt a Next-Node Trajectory Distillation (NTD) objective, which shortens the supervision horizon and admits a lower regression-error floor. Second, we introduce Chunk-Graded Noising (CGN), a monotonically non-decreasing per-chunk noising schedule that helps narrow the expected train-inference noise mismatch and removes redundant KV-cache updates, yielding substantial speedups at no quality cost. Third, we propose Orthogonal-Parallel DMD (OP-DMD), a distribution-matching loss that retains the original DMD supervision while introducing an additional regression constraint in the orthogonal subspace to suppress off-axis drift, improving both training stability and final generation quality. Extensive experiments show that TriTD consistently surpasses existing baselines in visual quality while reaching a real-time throughput of 26.8 FPS on a single H100 GPU, delivering a balanced quality-efficiency solution for interactive streaming video generation.

cs.CV↗

Learning-to-Memorize: Dynamic Context Management for Long-Horizon Autoregressive Video Generation

Autoregressive video generation has achieved impressive results on short clips, yet generating long videos remains challenging due to error accumulation over extended horizons, where each predicted frame depends on potentially imperfect previous frames. Existing approaches typically rely on static context management strategies, such as sliding-window caches that discard early frames or fixed sink frames that permanently preserve initial content. These designs either lose critical long-range context or anchor generation to outdated information, which can lead to degraded fidelity, motion stagnation, and reduced diversity. In this paper, we propose Learning to Memorize (L2M), a learned context memory management framework that dynamically retains, evicts, and evolves historical frames according to predicted importance. The framework consists of an importance prediction router that estimates the relevance of each historical frame, degradation-aware training that improves robustness to noisy or corrupted context, and a dynamic memory initialization and evolution mechanism that updates long-term memory using exponential moving average (EMA) importance scores. This allows high-quality frames to replace stale anchors and enables memory to adapt naturally to scene evolution. Trained with a teacher-student distillation objective and sparsity regularization, L2M makes efficient use of a fixed KV-cache budget while preserving the most informative contextual information. Extensive experiments demonstrate that L2M improves long-horizon video generation quality and temporal consistency over existing baselines, providing a learned strategy for context memory management in long autoregressive video generation.

cs.CV↗

Density results for $r$-gaps between zeros of the Riemann zeta-function

Let $0<γ_1\leq γ_2\leq \ldots$ denote the positive ordinates of the non-trivial zeros of the Riemann zeta-function. A result first announced by Selberg states that there exist absolute constants $Θ, \vartheta>0$ such that for each $r\in \mathbb{N}$, \[ \limsup_{n\to \infty}\frac{γ_{n+r}-γ_n}{2πr/\log γ_n}\geq 1+\fracΘ{r^α} \qquad \text{and}\qquad \liminf_{n\to \infty}\frac{γ_{n+r}-γ_n}{2πr/\log γ_n}\leq 1-\frac{\vartheta}{r^α} \] where $α$ may be taken as $2/3$, or as $1/2$ if one assumes the Riemann hypothesis. This was recently proved by Conrey and Turnage-Butterbaugh under RH and by Inoue unconditionally. We prove that in fact a positive proportion of $r$-gaps are large (and small) to the above extent, and we provide explicit estimates for the sizes and proportions of these gaps. In the case $r=1$, this quantitatively improves an unconditional result of Simonič, Trudgian and Turnage-Butterbaugh.

math.NT↗

Foundations of the Scaling Law

Empirical scaling laws relate loss to parameters $N$, training tokens $D$ and compute $C$. This technical note explains three mechanisms behind their exponents. Local approximation bounds function error at rate $N_e^{-γs/d}$, with effective parameters $N_e$, smoothness $s$, reuse exponent $γ$ and dimension $d$; the loss function determines the risk bound. Independent feature coverage gives $α_D=(β-1)/ζ$ from predictive-weight decay $β$ and occurrence rarity $ζ$. Separable-loss optimization determines training allocations and deployment crossovers. Nonlinear scoring can produce apparent emergent abilities, while grokking concerns delayed generalization and verification constrains test-time scaling. For regular molecular configurations, the $\mathrm{SE}(3)$ quotient gives $d_{\mathrm{int}}=d-6$ and relative approximation-exponent gain $6/d_{\mathrm{int}}$. Optimized dense-to-equivariant excess-loss ratios scale as $C^{p_{\mathrm{eq}}-p_{\mathrm{dense}}}$, where $p_j$ are compute-loss exponents and the prefactor depends on loss amplitudes and FLOP costs. Domain examples also cover visual resolution, conformational coverage and correlated-sample precision.

cs.LG↗

Target Sensing in Full-Dimensional MIMO-OFDM ISAC Systems Via Coupled Tensor Decomposition

Integrated sensing and communication (ISAC) has been recognized as a key enabler for future wireless communication systems. However, existing ISAC designs based on MIMO-OFDM generally fail to fully exploit the spatial degrees of freedom and the communication data payload, resulting in restricted target sensing performance. To cope with this issue, in this paper we propose a novel target sensing method for full-dimensional (FD) MIMO-OFDM ISAC systems based on coupled tensor decomposition. We first characterize the system model of FD MIMO-OFDM ISAC, where the base station employs a large number of antennas in two dimensions and facilitates both sensing and communication via the data payload of OFDM signals. Then, we formulate the problem of estimating target parameters as a coupled canonical polyadic decomposition (CPD) problem, which jointly leverages the echo signals of communication data payload over multiple subcarriers in the frequency domain. The theoretical analysis indicates that the formulated coupled CPD problem possesses a more relaxed uniqueness condition compared with the ordinary CPD problem, thereby enabling more stable target sensing performance through the pure communication data payload in FD MIMO-OFDM ISAC. In addition, we develop a coupled CPD-based target sensing algorithm, where the target parameters, including azimuth and elevation angles, ranges, and velocities, are extracted from the decomposed factor matrices. Numerical results show that the proposed target sensing method achieves a higher success rate and more accurate parameter estimation than existing tensor decomposition methods.

eess.SP↗

The Evolving Bottleneck in Speech Generation: Interface Co-design and Staged Alignment from CosyVoice to Qwen-Audio-3.0-TTS

Speech synthesis systems are commonly narrated as a sequence of larger models, better tokenizers, and broader data. This technical retrospective offers a different account of the CosyVoice lineage, from CosyVoice through CosyVoice 2 and CosyVoice 3 to Qwen-Audio-3.0-TTS: progress came from repeatedly relocating the system's dominant bottleneck. Across the lineage, a stable decomposition separates an autoregressive language model that plans speech from a flow-matching model that renders acoustics. What changes is the contract between them. CosyVoice establishes supervised semantic tokens as a content-aligned interface; CosyVoice 2 makes that interface causally available for streaming and removes the utterance-level speaker embedding from the language model; CosyVoice 3 improves the learnability and coverage of the interface through multitask supervision, scaling, and differentiable reward optimization; and Qwen-Audio-3.0-TTS reduces token rate, conditions its renderer on continuous language-model hidden states instead of token embeddings, and progressively aligns the coupled system. We formalize this history through four interface dimensions---representation, ownership, availability, and gradient reach---and separate within-paper evidence from cross-paper comparison. The resulting synthesis connects discrete autoregressive, continuous non-autoregressive, hybrid, and continuous autoregressive speech-generation paradigms, and yields practical principles for diagnosing and training modular speech generators.

eess.AS↗

PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet reliably leveraging preference signals remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we introduce PACIFIC (Preference Alignment for Choices Inference via Five-factor Identity Characterization), a personality-driven preference alignment framework that uses Big-Five (OCEAN) traits as a principled "latent" signal for organizing and reasoning over user preference history. To systematically evaluate this framework, we construct a psychometrics-based dataset containing 1,200 preference-query pairs spanning diverse domains (e.g., travel, movies, and education), with comprehensive coverage of high and low Big-Five trait directions. Extensive experiments show that trait-aligned preferences substantially improve personalized QA: given clean, trait-aligned context, LLMs reach near-ceiling accuracy (up to 99%), confirming that reasoning capability is not the bottleneck. The challenge is that real histories are mixed-trait and unlabeled. We show the true bottleneck is retrieval: a persona-aware contrastive retriever (PiRAG) raises label-free accuracy from 30% to 43% over standard semantic retrieval, without any trait annotations at inference.

cs.CL↗

Self-supervised reconstruction of transients in data from space-borne gravitational-wave detectors

Space-based gravitational-wave (GW) data may contain transient signals whose waveform morphologies are not known in advance. Extracting these signals is important for characterizing new sources and mitigating instrumental anomalies. However, existing deep neural network (DNN)-based extraction approaches rely on clean training targets and waveform-class-specific examples, which may limit their applicability when the transient morphology is not specified in advance. This work develops a Noise2Noise (N2N)-inspired self-supervised framework that learns from noisy observations without clean training targets and requires no transient-specific waveform templates at inference. A single model trained on noisy massive black-hole binary (MBHB) observations provides high-overlap MBHB recovery and recovers the dominant morphologies of instrumental glitches and other GW transient signals such as cosmic string bursts in source-confused test data. Beyond waveform recovery, when independent information identifies a candidate transient as instrumental, its extracted waveform can be subtracted from the data without an anomaly-specific template. In a simulated continuous data stream, this procedure substantially suppresses the injected-anomaly power within the glitch-dominated frequency band. These results support the use of self-supervised extraction for initial waveform estimation of candidate transients with unknown morphologies, enabling subsequent characterization and, where appropriate, conditional subtraction of instrumental anomalies.

gr-qc↗

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation across many model invocations. Because cost and latency accumulate over the full episode, their practical value depends not only on peak capability but also on how efficiently that capability is delivered. Yet many steps in everyday work emphasize state tracking, coordination, recovery, and follow-through rather than frontier-scale reasoning. We present Occamy-1.0, a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint. We construct execution-grounded data and environments, capture replayable long-horizon trajectories across multiple harnesses, and use staged post-training to develop and consolidate complementary execution capabilities. Across a broad suite of co-work benchmarks, Occamy-1.0 is consistently among the strongest comparably sized models and remains competitive with substantially larger frontier systems on several tasks. Under our stated evaluation and pricing protocol, its aggregate performance across four representative benchmarks places it at the low-cost knee of the observed cost--performance Pareto frontier. Supporting evaluations in tool calling, coding, and instruction following further show that this specialization preserves broad agentic capability. We release the model weights and a subset of the training data to support research on practical co-work agents and agentic post-training.

cs.AI↗

Accelerating Stochastic Gravitational Wave Backgrounds Parameter Estimation in Pulsar Timing Arrays with Flow Matching

\Acp{PTA} are essential tools for detecting the \ac{SGWB}, but their analysis faces significant computational challenges. Traditional methods like \ac{MCMC} struggle with high-dimensional parameter spaces where noise parameters often dominate, % while existing deep learning approaches fail to model the \ac{HD} correlation or are validated only on synthetic datasets. while existing deep learning approaches have so far been validated on synthetic datasets or require training on the full pulsar set, incurring substantial computational and memory costs. We propose a flow-matching-based \ac{CNF} for efficient \ac{PTA} parameter estimation. Using ten pulsars selected according to published NANOGrav 12.5-year dropout factors and applied to the NANOGrav 15-year residuals, our method produces \ac{SGWB} posteriors consistent with a reference \ac{MCMC} analysis, with Jensen-Shannon divergences below \(10^{-2}\) nat. After amortized training, posterior generation is reduced from approximately 50 hours for the reference \ac{MCMC} pipeline to approximately 4 minutes for \ac{CNF} sampling. The present study demonstrates that flow-matching-based \acp{CNF} can serve as an efficient posterior-sampling accelerator for reduced \ac{PTA} datasets. Rather than providing new astrophysical constraints, the method is intended to complement conventional \ac{MCMC} analyses and to provide a scalable route toward faster inference in future \ac{PTA} applications.

astro-ph.IM↗

Toward Efficient and Accurate EMRI Parameter Estimation: A Machine Learning-Enhanced MCMC Framework

The detection of gravitational waves from extreme-mass-ratio inspirals (EMRIs) in space-based antennas like Taiji and Laser Interferometer Space Antenna promises deep insights into strong-field gravity and black hole physics. However, the complex, highly degenerate, and nonconvex likelihood landscapes characteristic of EMRI parameter spaces pose severe challenges for conventional Markov chain Monte Carlo (MCMC) methods. Under realistic instrumental noise and broad priors, these methods demand impractical computational costs but are prone to becoming trapped in local maxima, leading to biased and unreliable parameter estimates. To address these challenges, we introduce flow-matching MCMC (FM-MCMC), a novel Bayesian framework that integrates continuous normalizing flows (CNFs) with parallel tempering MCMC (PTMCMC). By generating high-likelihood regions via CNFs and refining them through PTMCMC, FM-MCMC enables robust exploration of the nontrivial parameter spaces, achieves orders-of-magnitude improvement in computational efficiency, and, more importantly, ensures statistically unbiased inference. By enabling real-time, unbiased parameter inference, FM-MCMC could unlock the full scientific potential of EMRI observations, and would serve as a scalable pipeline for precision gravitational-wave astronomy.

gr-qc↗

BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences

While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanities and social sciences (HSS), where nuanced quality judgments matter more than objective correctness. This makes preference alignment a natural paradigm for broad HSS tasks. Yet existing methods are either costly or not tailored to broad HSS disciplines. We thus propose BridgeAlign, among the first preference-alignment pipelines for broad HSS disciplines, with three phases: i) Seed Curation: curating HSS seed documents from web corpora via heuristic/LLM-based filtering and text refinement; ii) Preference Data Synthesis: generating preference triplets via persona-based instruction inversion with Q&A consistency checks; iii) Preference Optimization: moving beyond naive human-vs-model heuristics by first grounding preferences in HSS quality rubric, then generating transitional responses via controlled quality degradation to form near-boundary preference pairs for finer-grained quality discrimination. Aligning over 210k synthetic preference samples, BridgeAlign enables Qwen3-8B to achieve the best average across 17 benchmarks against 11 strong baselines; importantly, leading on both human-preference and knowledge-based capabilities at once, with no trade-off between them, as supported by extensive experiments and contextualized by existing theories.

cs.CL↗

A unified reconstruction algorithm for reduced-frame structured illumination microscopy

Reduced-frame structured illumination microscopy (SIM) is attractive for live-cell imaging because it can improve temporal throughput and reduce photobleaching, but incomplete phase sampling makes reconstruction unstable and computationally demanding. Here we present URA-SIM, a unified reduced-acquisition framework that turns fixed reduced-frame measurements into pipeline- compatible raw stacks through model-consistent phase-domain completion. Instead of solving a large object-level inverse problem or replacing established SIM reconstruction, URA-SIM estimates the missing phase content on the low-dimensional phase-harmonic manifold required by the target modality and then delegates order separation and image formation to classical reconstruction pipeline. This design combines three practical advantages: fidelity from the SIM forward structure, lightweight online computation, and direct compatibility with existing reconstruction workflows. For 2D-SIM, URA-SIM uses the first-harmonic phase structure of three-phase SIM to estimate a shared zero-order field and complete missing phase samples by direction-wise harmonic fitting. On calibration and biological 2D-SIM data, reduced-frame reconstructions preserve resolvable structures and remain competitive on COS7 mitochondria comparison data. In live-cell COS7 mitochondria imaging, URA-SIM reconstructs each time point from five acquired raw frames and resolves mitochondrial cristae across different temporal sampling regimes. Experiments on 3D-SIM and nonlinear SIM further show that the same design principle can be transferred when the phase model and reconstruction-pipeline interface are adapted to the target modality. These results support URA-SIM as a transparent, model-consistent and computationally lightweight route from fixed reduced-frame acquisition to classical SIM reconstruction workflows.

physics.optics↗

HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs

High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds on closed tasks, yet the humanities and social sciences (HSS) are overlooked, and their open-ended nature makes synthesis challenging. Moving beyond prior capability-centric, fragmented attempts, we adopt a subject-centric paradigm, define the first HSS domain system covering 14 mainstream fields, and introduce HSS-Synth, the first data synthesis pipeline for HSS. HSS-Synth comprises: (1) constructing seed documents from web corpora via multi-step filtering and text refinement evaluated by a judge; (2) specifying "requirements + persona" to backtranslate seed documents into diverse yet faithful instructions with a strict Q&A alignment check; and (3) breaking LLM response limits via teacher-forced Answering that feeds seed documents during response generation to anchor semantics, reduce hallucinations, and preserve tone and integrity. HSS-Synth yields 237k high-quality, diverse instruction-tuning samples that outperform 14 leading baselines on 16 benchmarks. The fine-tuned Qwen3-8B-Base sets a new SOTA and approaches the official Qwen3-8B, improving both human preference and knowledge capabilities without performance seesaws. Extensive experiments demonstrate HSS-Synth's robustness and transferability. Our code is publicly available at https://github.com/pengr/HSS-Synth.

cs.CL↗

Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm

In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, audio quality, controllability, multilingual coverage, efficiency, and robustness. It combines a 12.5~Hz low-frame-rate speech tokenizer for reduced inference latency with a five-stage progressive training paradigm for coordinated language model (LM) and flow-matching model (FM) optimization. The model provides production-level control through free-style natural-language instructions and fine-grained inline tags, while supporting 16 languages, 20 Chinese dialect regions, one-pass long-form synthesis up to 3 minutes, and robust generation from noisy, reverberant, or unclear reference speech. Across SEED-TTS-Eval, CV3-Eval, instruction-following, long-form, and acoustic-robustness evaluations, Qwen-Audio-3.0-TTS achieves state-of-the-art performance on many reported dimensions or the strongest aggregate results. It also ranks first on the independent Artificial Analysis Text-to-Speech Leaderboard. These results establish Qwen-Audio-3.0-TTS as a strong foundation for production-level speech synthesis.

eess.AS↗