arXiv subjects

Ziyu Shen

Publications and source records attributed to Ziyu Shen.

17 recordsLinked to original sources

arXiv2026

Prefix-Adaptive Block Diffusion for Efficient Document Recognition

Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing. However, existing BDMs bind denoising and cache commitment to fixed block boundaries: parallelism shrinks during intra-block denoising, while generated tokens cannot be cached until the whole block is completed. Moreover, intra-block bidirectional denoising conflicts with inter-block autoregression, creating inconsistent information flow that can challenge structure-sensitive recognition. We propose the Prefix-Adaptive Block Diffusion Model (PA-BDM), which replaces intra-block bidirectional denoising with causal denoising from prefix to suffix and treats the block size as a maximum candidate range rather than a fixed commitment unit. PA-BDM uses Confidence-gated Structural Loss (CSL) to build low-entropy prefixes before extending training to longer continuations. During inference, Progressive Prefix Commitment (PPC) then dynamically commits the longest reliable prefix into the KV cache and resets the next candidate range from the updated prefix, restoring a large parallel decoding space at each step. Experiments show that the 3B PA-BDM achieves higher recognition scores on several benchmarks and improves inference throughput by 71.6\% over the 2.5B MinerU-Diffusion.

cs.CV↗

arXiv2026

State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models

Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model (VLM)-based parsing approaches rely on globally compressed visual tokens, where fine-grained details are entangled within a single representation and repeatedly accessed during decoding. However, we observe that the visual evidence for each prediction is typically localized and conditioned on the current decoding state, whereas such representations must be accessed in full at every decoding step, resulting in inefficient computation. To address this mismatch, we formulate perception as state-conditioned visual evidence retrieval (SCVER) during autoregressive decoding. The model operates on a compact global representation for coarse structure and retrieves a small set of relevant high-resolution regions conditioned on the current token state. This coarse-to-fine design enables on-demand access to fine-grained visual cues, relieving globally shared representations from encoding all fine-grained details. We further find that learning such state-conditioned retrieval in VLMs is challenging and unstable. To stabilize this process, we introduce a Spatially-Guided Learning Objective (SGLO) to guide the retrieval process. Experiments on document parsing benchmarks show that SCVER improves robustness under reduced input resolution and achieves a better accuracy-efficiency trade-off, demonstrating the effectiveness of on-demand visual evidence retrieval for fine-grained perception.

cs.CV↗

arXiv2026

Formulation of testing gravitational redshift based on Laser Time link between China Space Station and a ground station

This paper presents a high-precision gravitational redshift test using the China Space Station (CSS) Laser Time Transfer (CLT) system. We develop a comprehensive observation equation based on a c^{-3} order relativistic model for space-ground clock comparison. While the CSS optical clock system is currently in the orbital debugging phase, our simulation using actual CSS orbit data achieves a gravitational redshift verification precision of (1.8 \pm 47)*10^{-7} -- approximately one order of magnitude improvement over previous experiments. Our work represents the first application of laser-based time transfer for gravitational redshift verification at such precision, and the first use of the CSS CLT link for testing this fundamental aspect of General Relativity. Unlike microwave-based methods, our laser approach avoids ionospheric effects and first-order Doppler shifts. Residual analysis identifies tropospheric delay variations and atmospheric turbulence as the primary remaining uncertainty contributors. The achieved precision enables gravitational potential difference measurements with 0.1 m^2/s^2 precision -- offering new capabilities for both fundamental physics investigations and geodetic applications including intercontinental height transfer. This work establishes a new benchmark for high-precision tests of relativistic physics and demonstrates the transformative potential of space-based optical time transfer.

gr-qc↗

arXiv2026

WisPaper: Your AI Scholar Search Engine

We present \textsc{WisPaper}, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The system addresses two fundamental challenges. (1)~\textit{Semantic search limitations}: existing academic search engines match keywords but cannot verify whether papers truly address complex research questions; and (2)~\textit{Workflow fragmentation}: researchers must manually stitch together separate tools for discovery, organization, and monitoring. \textsc{WisPaper} tackles these through three integrated modules. \textbf{Scholar Search} combines rapid keyword retrieval with \textit{Deep Search}, in which an agentic model, \textsc{WisModel}, validates candidate papers against user queries through structured reasoning. Discovered papers flow seamlessly into \textbf{Library} with one click, where systematic organization progressively builds a user profile that sharpens the recommendations of \textbf{AI Feeds}, which continuously surfaces relevant new publications and in turn guides subsequent exploration, closing the loop from discovery to long-term awareness. On TaxoBench, \textsc{WisPaper} achieves 22.26\% recall, surpassing the O3 baseline (20.92\%). Furthermore, \textsc{WisModel} attains 93.70\% validation accuracy, effectively mitigating retrieval hallucinations.

cs.IR↗

arXiv2025

LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP

Timely identification and accurate risk stratification of cardiovascular disease (CVD) remain essential for reducing global mortality. While existing prediction models primarily leverage structured data, unstructured clinical notes contain valuable early indicators. This study introduces a novel LLM-augmented clinical NLP pipeline that employs domain-adapted large language models for symptom extraction, contextual reasoning, and correlation from free-text reports. Our approach integrates cardiovascular-specific fine-tuning, prompt-based inference, and entity-aware reasoning. Evaluations on MIMIC-III and CARDIO-NLP datasets demonstrate improved performance in precision, recall, F1-score, and AUROC, with high clinical relevance (kappa = 0.82) assessed by cardiologists. Challenges such as contextual hallucination, which occurs when plausible information contracts with provided source, and temporal ambiguity, which is related with models struggling with chronological ordering of events are addressed using prompt engineering and hybrid rule-based verification. This work underscores the potential of LLMs in clinical decision support systems (CDSS), advancing early warning systems and enhancing the translation of patient narratives into actionable risk assessments.

cs.CL↗

arXiv2025

DocFusion: A Unified Framework for Document Parsing Tasks

Document parsing is essential for analyzing complex document structures and extracting fine-grained information, supporting numerous downstream applications. However, existing methods often require integrating multiple independent models to handle various parsing tasks, leading to high complexity and maintenance overhead. To address this, we propose DocFusion, a lightweight generative model with only 0.28B parameters. It unifies task representations and achieves collaborative training through an improved objective function. Experiments reveal and leverage the mutually beneficial interaction among recognition tasks, and integrating recognition data significantly enhances detection performance. The final results demonstrate that DocFusion achieves state-of-the-art (SOTA) performance across four key tasks.

cs.CL↗

arXiv2025

RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT

Semi-supervised learning has become a compelling approach for 3D tooth segmentation from CBCT scans, where labeled data is minimal. However, existing methods still face two persistent challenges: limited corrective supervision in structurally ambiguous or mislabeled regions during supervised training and performance degradation caused by unreliable pseudo-labels on unlabeled data. To address these problems, we propose Region-Aware Instructive Learning (RAIL), a dual-group dual-student, semi-supervised framework. Each group contains two student models guided by a shared teacher network. By alternating training between the two groups, RAIL promotes intergroup knowledge transfer and collaborative region-aware instruction while reducing overfitting to the characteristics of any single model. Specifically, RAIL introduces two instructive mechanisms. Disagreement-Focused Supervision (DFS) Controller improves supervised learning by instructing predictions only within areas where student outputs diverge from both ground truth and the best student, thereby concentrating supervision on structurally ambiguous or mislabeled areas. In the unsupervised phase, Confidence-Aware Learning (CAL) Modulator reinforces agreement in regions with high model certainty while reducing the effect of low-confidence predictions during training. This helps prevent our model from learning unstable patterns and improves the overall reliability of pseudo-labels. Extensive experiments on four CBCT tooth segmentation datasets show that RAIL surpasses state-of-the-art methods under limited annotation. Our code will be available at https://github.com/Tournesol-Saturday/RAIL.

cs.CV↗

arXiv2025

Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction

Recently developed pre-trained text-and-layout models (PTLMs) have shown remarkable success in multiple information extraction tasks on visually-rich documents (VrDs). However, despite achieving extremely high performance on benchmarks, their real-world performance falls short of expectations. Owing to this issue, we investigate the prevailing evaluation pipeline to reveal that: (1) The inadequate annotations within benchmark datasets introduce spurious correlations between task inputs and labels, which would lead to overly-optimistic estimation of model performance. (2) The evaluation solely relies on the performance on benchmarks and is insufficient to comprehensively explore the capabilities of methods in real-world scenarios. These problems impede the prevailing evaluation pipeline from reflecting the real-world performance of methods, misleading the design choices of method optimization. In this work, we introduce EC-FUNSD, an entity-centric dataset crafted for benchmarking information extraction from visually-rich documents. This dataset contains diverse layouts and high-quality annotations. Additionally, this dataset disentangles the falsely-coupled segment and entity annotations that arises from the block-level annotation of FUNSD. Using the proposed dataset, we evaluate the real-world information extraction capabilities of PTLMs from multiple aspects, including their absolute performance, as well as generalization, robustness and fairness. The results indicate that prevalent PTLMs do not perform as well as anticipated in real-world information extraction scenarios. We hope that our study can inspire reflection on the directions of PTLM development.

cs.CL↗

arXiv2024

Policy Learning for Balancing Short-Term and Long-Term Rewards

Empirical researchers and decision-makers spanning various domains frequently seek profound insights into the long-term impacts of interventions. While the significance of long-term outcomes is undeniable, an overemphasis on them may inadvertently overshadow short-term gains. Motivated by this, this paper formalizes a new framework for learning the optimal policy that effectively balances both long-term and short-term rewards, where some long-term outcomes are allowed to be missing. In particular, we first present the identifiability of both rewards under mild assumptions. Next, we deduce the semiparametric efficiency bounds, along with the consistency and asymptotic normality of their estimators. We also reveal that short-term outcomes, if associated, contribute to improving the estimator of the long-term reward. Based on the proposed estimators, we develop a principled policy learning approach and further derive the convergence rates of regret and estimation errors associated with the learned policy. Extensive experiments are conducted to validate the effectiveness of the proposed method, demonstrating its practical applicability.

cs.LG↗

arXiv2022

Testing gravitational redshift based on microwave frequency links onboard China Space Station

In 2022 China Space Station (CSS) will be equipped with atomic clocks and optical clocks with stabilities of $2 \times 10^{-16}$ and $8 \times 10^{-18}$, respectively, which provides an excellent opportunity to test gravitational redshift (GR) with higher accuracy than previous results. Based on high-precise frequency links between CSS and a ground station, we formulated a model and provided simulation experiments to test GR. Simulation results suggest that this method could test the GR at the accuracy level of $(0.27 \pm 2.15) \times10^{-7}$, more than two orders in magnitude higher than the result of the experiment of a hydrogen clock on board a flying rocket more than 40 years ago.

astro-ph.IM↗

arXiv2022

Determining the gravity potential with the CVSTT technique using two hydrogen clocks

According to general relativity theory (GRT), by comparing the frequencies between two precise clocks at two different stations, the gravity potential (geopotential) difference between the two stations can be determined due to the gravity frequency shift effect. Here, we provide experimental results of geopotential difference determination based on frequency comparisons between two remote hydrogen atomic clocks, with the help of common-view satellite time transfer (CVSTT) technique. For the first time we apply the ensemble empirical mode decomposition (EEMD) technique to the CVSTT observations for effectively determining the geopotential-related signals. Based on the net frequency shift between the two clocks in two different periods, the geopotential difference between stations of the Beijing 203 Institute Laboratory (BIL) and Luojiashan Time--Frequency Station (LTS) is determined. Comparisons show that the orthometric height (OH) of LTS determined by the clock comparison is deviated from that determined by the Earth gravity model EGM2008 by (38.5$\pm$45.7)~m. The results are consistent with the frequency stabilities of the hydrogen clocks (at the level of $10^{-15}$~day$^{-1}$) used in the experiment. Using more precise atomic or optical clocks, the CVSTT method for geopotential determination could be applied effectively and extensively in geodesy in the future.

physics.geo-ph↗

arXiv2021

Measuring height difference using two-way satellite time and frequency transfer

According to general relativity theory (GRT), the clock at a position with lower geopotential ticks slower than an identical one at a position with higher geopotential. Here, we provide a geopotential comparison using a non-transportable hydrogen clock and a transportable hydrogen clock for altitude transmission based on the two-way satellite time and frequency transfer (TWSTFT) technique. First, we set one hydrogen clock on the fifth floor and another hydrogen clock on the ground floor, with their height difference of 22.8 m measured by tape, and compared the time difference between these two clocks by TWSTFT for 13 days. Then, we set both clocks on the ground floor and compared the time difference between the two clocks for 7 days for zero-baseline calibration (synchronization). Based on the measured time difference between the two clocks at different floors, we obtained the height difference of $28 \pm 05.4$ m, which coincides well with the tape-measured result. This experiment provides a method of height propagation using precise clocks based on the TWSTFT technique.

physics.geo-ph↗

arXiv2020

Determining geopotential difference via relativistic precise point positioning time comparison: A case study using simulated observations

According to general relativity theory (GRT), the geopotential difference (GD) can be determined by comparing the change in time difference between precise clocks using the precise point positioning (PPP) time transfer technique, referred to as the relativistic PPP time comparison approach. We focused on high-precision time comparison between two precise clocks for determining the GD using the relativistic PPP time transfer,and conducted simulation experiments to validate the approach. In the experiments, we consider three cases to evaluate the performance of the approach using clocks with different stabilities, namely, the frequency stabilities of the clocks equipped at three selected ground stations are respectively (Case 1), (Case 2), and (Case 3) at time period. Conclusions are drawn from the experimental results. First, high-precision clocks can significantly improve the accuracy for PPP time transfer, but the improvement is limited by measurement noises. Compared to Case 1, the long-term stabilities of OPMT-BRUX as well as PTBB-BRUX are improved in Cases 2 and 3. The frequency stabilities of Cases 1-3 are approximately 4.28*10-16, 4.00*10-17, and 3.22*10-17 at 10-day averaging time for OPMT-BRUX, respectively, and for PTBB-BRUX, these values are approximately 3.73*10-16, 8.17*10-17, and 4.64*10-17. Second, the geopotential difference between any two stations can be determined at the decimeter level, with its accuracy being consistent with the stabilities of the time links in Cases 1-3. In Case 3, the determined geopotential differences between OPMT and BRUX deviate from the EIGEN-6C4 model values by -0.64 m2/s2 with an uncertainty of 1.11 m2/s2, whereas the deviation error between PTBB and BRUX is 0.76 m2/s2 with an uncertainty of 1.79 m2/s2. The approach proposed in this study can be also applied to testing GRT.

physics.geo-ph↗

arXiv2020

Formulation to test gravitational redshift based on the tri-frequency combination of ACES frequency links

Atomic Clock Ensemble in Space (ACES) is an ESA mission mainly designed to test gravitational redshift with high-performance atomic clocks in space and on the ground. A crucial part of this experiment lies in its two-way Microwave Link (MWL), which uses the uplink of carrier frequency 13.475 GHz (Ku band) and downlinks of carrier frequencies 14.70333 GHz (Ku band) and 2248 MHz (S band) to transfer time and frequency. The formulation based on the time comparison has been studied for over a decade. However, there are advantages of using frequency comparison instead of time comparison to test gravitational redshift. Hence, we develop a tri-frequency combination (TFC) method based on the measurements of the frequency shifts of three independent MWLs between ACES and a ground station. The potential scientific object requires stabilities of atomic clocks at least $3\times10^{-16}$/day, so we must consider various effects, including the Doppler effect, second-order Doppler effect, atmospheric frequency shift, tidal effects, refraction caused by the atmosphere, and Shapiro effect, with accuracy levels of tens of centimeters. The ACES payload will be launched as previously planned in the middle of 2021, and the formulation proposed in this study will enable testing gravitational redshift at an accuracy level of at least $2\times10^{-6}$, which is more than one order higher than the present accuracy level of $7\times10^{-5}$.

astro-ph.IM↗

arXiv2020

Preliminary experimental results of determining the geopotential difference between two synchronized portable hydrogen clocks at different locations

Here, we provide preliminary experimental results of the geopotential determination based on time elapse comparisons between two remote atomic clocks located at Beijing and Wuhan, respectively. After synchronizing two hydrogen atomic clocks at Beijing 203 Institute Laboratory (BIL) for 20 days as zero-baseline calibration, we transport one clock to Luojiashan Time-Frequency Station (LTS), Wuhan, without stopping its running. Continuous comparisons between the two remote clocks were conducted for 65 days based on the Common View Satellite Time Transfer (CVSTT) technique. The ensemble empirical mode decomposition (EEMD) technique is applied to removing the uninteresting periodic signals contaminated in the original CVSTT observations to obtain the residual clocks-offsets series, from which the time elapse between the two remote clocks was determined. Based on the accumulated time elapse between these two clocks the geopotential difference between these two stations was determined. Given the orthometric height (OH) of BIL, the OH of the LTS was determined based on the determined geopotential difference. Comparisons show that the OH of the LTS determined by time elapse comparisons deviates from that determined by Earth gravity model EGM2008 by about 98 m. The results are consistent with the frequency stabilities of the hydrogen atomic clocks (at the level of $10^{-15}$/day) applied in our experiments. In addition, we used 85-days original observations to determine the geopotential difference between two remote stations based on the CVSTT technique. Using more precise atomic or optical clocks, the CVSTT method for geopotential determination could be applied effectively and extensively in geodesy in the future.

physics.geo-ph↗

arXiv2020

Gravity field modeling using space frequency signal transfer technique between satellites

Here we provide an alternative approach to determine the Earth's external gravitational potential field based on low-orbit target satellite (TS), geostationary satellites (GS), and microwave signal links between them. By emitting and receiving frequency signals controlled by precise clocks between TS and GS, we can determine the gravitational potential (GP) at the TS orbit. We set the TS with polar orbits, altitude of around 500 km above ground, and three evenly distributed GSs with equatorial orbits, altitudes of around 35000 km from the Earth's center. In this case, at any time the TS can be observed via frequency signal links by at least one GS. In this way we may determine a potential distribution over the TS-defined sphere (TDS), which is a sphere that best fits the TS' orbits. Then, based on the potential distribution over the TDS, an Earth's external gravitational field can be determined. Simulation results show that the accuracy of the potential filed established based on 30-days observations can achieve decimeter level if optical atomic clocks with instability of $1\times 10^{-17}τ^{-1/2}$ are available. The formulation proposed in this study may enrich the approachs for determining the Earth's external gravity field.

physics.geo-ph↗

arXiv2020

Unification of global height system at centimeter level using precise frequency signal links

The realization of International Height Reference System (IHRS) is one of the major tasks of the International Association of Geodesy (IAG). A main component of the IHRS realization is the global vertical datum unification, which requires the connection of the existing local vertical height reference systems (VHS). However, it is difficult to estimate the offsets between two local height systems by conventional approaches when they are far apart. In this paper, we formulate a framework for connecting two local VHSs using ultra-precise frequency signal transmission links between satellites and ground stations, which is referred to as satellite frequency signal transmission (SFST) approach. The SFST approach can directly determine the geopotential difference between two ground datum stations without location restrictions, and consequently determine the height difference of the two VHSs. Simulation results show that the China's VHS and the US's VHS can be unified at the accuracy of several centimeters, provided that the stability of atomic clocks used on board the satellite and on ground datum stations reach the highest level of current technology, about $4.8\times 10^{-17}/\sqrtτ$ for an averaging time τ (in seconds). The SFST approach is promising to unify the global vertical height datum in centimeter level in future, and it also provide a new way for the IHRS realization.

physics.geo-ph↗