arXiv subjects

Zhiyuan Chen

Publications and source records attributed to Zhiyuan Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

SciEval: A Benchmark for Automatic Evaluation of K-12 Science Instructional Materials

The need to evaluate instructional materials for K-12 science education has become increasingly important, as more educators use generative AI to create instructional materials. However, the review of instructional materials is time-consuming, expertise-intensive, and difficult to scale, motivating interest in automated evaluation approaches. While large language models (LLMs) have shown strong performance on general evaluation tasks, their performance and reliability on instructional materials remain unclear. To address this gap, we formulate Automatic Instructional Materials Evaluation (AIME) as a generative AI task that predicts scores and evidence using the rubric designed by the educator. We create a benchmark dataset and develop baseline models for AIME. First, we curate the first AIME dataset, SciEval, consisting of instructional materials annotated with pedagogy-aligned evaluation scores and evidence-based rationales. Expert annotations achieve high inter-rater reliability, resulting in a dataset of 273 lesson-level instructional materials evaluated across 13 criteria (N=3549) using the EQuIP rubric. Second, we test mainstream LLMs (GPT, Gemini, Llama, and Qwen) on SciEval and find that none achieve strong performance. Then we fine-tune Qwen3 on SciEval. Results on a held-out test set show that domain-aligned fine-tuning can achieve up to 11 percent performance gains, highlighting the importance of domain-specific fine-tuning for AIME and facilitating the use of LLMs in other educational tasks.

cs.AI↗

arXiv2026

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models

The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alignment with human values. While extensive research has addressed moral evaluation in LLMs, text-centric assessments cannot adequately capture the complex contextual nuances and ambiguities introduced by visual modalities. To bridge this gap, we introduce MM-MoralBench, a multimodal moral evaluation benchmark grounded in Moral Foundations Theory. We construct unique multimodal scenarios by combining synthesized visual contexts with character dialogues to simulate real-world dilemmas where visual and linguistic information interact dynamically. Our benchmark assesses models across six moral foundations through moral judgment, classification, and response tasks. Extensive evaluations of over 20 LVLMs reveal that models exhibit pronounced moral alignment bias, diverging significantly from human consensus. Furthermore, our analysis indicates that general scaling or structural improvements yield diminishing returns in moral alignment, and thinking paradigm may trigger overthinking-induced failures in moral contexts, highlighting the necessity for targeted moral alignment strategies. Our benchmark is publicly available.

cs.CV↗

arXiv2026

Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction

Accurate prediction of RNA secondary structure underpins transcriptome annotation, mechanistic analysis of non-coding RNAs, and RNA therapeutic design. Recent gains from deep learning and RNA foundation models are difficult to interpret because current benchmarks may overestimate generalization across RNA families. We present the Comprehensive Hierarchical Annotation of Non-coding RNA Groups (CHANRG), a benchmark of 170{,}083 structurally non-redundant RNAs curated from more than 10 million sequences in Rfam~15.0 using structure-aware deduplication, genome-aware split design and multiscale structural evaluation. Across 29 predictors, foundation-model methods achieved the highest held-out accuracy but lost most of that advantage out of distribution, whereas structured decoders and direct neural predictors remained markedly more robust. This gap persisted after controlling for sequence length and reflected both loss of structural coverage and incorrect higher-order wiring. Together, CHANRG and a padding-free, symmetry-aware evaluation stack provide a stricter and batch-invariant framework for developing RNA structure predictors with demonstrable out-of-distribution robustness.

q-bio.BM↗

arXiv2026

ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts

Document Image Machine Translation (DIMT) seeks to translate text embedded in document images from one language to another by jointly modeling both textual content and page layout, bridging optical character recognition (OCR) and natural language processing (NLP). The DIMT 2025 Challenge advances research on end-to-end document image translation, a rapidly evolving area within multimodal document understanding. The competition features two tracks, OCR-free and OCR-based, each with two subtasks for small (less than 1B parameters) and large (greater than 1B parameters) models. Participants submit a single unified DIMT system, with the option to incorporate provided OCR transcripts. Running from December 10, 2024 to April 20, 2025, the competition attracted 69 teams and 27 valid submissions in total. Track 1 had 34 teams and 13 valid submissions, while Track 2 had 35 teams and 14 valid submissions. In this report, we present the challenge motivation, dataset construction, task definitions, evaluation protocol, and a summary of results. Our analysis shows that large-model approaches establish a promising new paradigm for translating complex-layout document images and highlight substantial opportunities for future research.

cs.CV↗

arXiv2026

Context and Diversity Matter: The Emergence of In-Context Learning in World Models

The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with novel or rare configurations. We investigate in-context learning (ICL) of world models, shifting attention from zero-shot performance to the growth and asymptotic limits of the world model. Our contributions are three-fold: (1) we formalize ICL of a world model and identify two core mechanisms: environment recognition (ER) and environment learning (EL); (2) we derive error upper-bounds for both mechanisms that expose how the mechanisms emerge; and (3) we empirically confirm that distinct ICL mechanisms exist in the world model, and we further investigate how data distribution and model architecture affect ICL in a manner consistent with theory. These findings demonstrate the potential of self-adapting world models and highlight the key factors behind the emergence of EL/ER, most notably the necessity of long context and diverse environments.

cs.LG↗

arXiv2026

Is Your Private Information Logged? An Empirical Study on Android App Logs

With the rapid growth of mobile apps, users' concerns about their privacy have become increasingly prominent. Android app logs serve as crucial computer resources, aiding developers in debugging and monitoring the status of Android apps, while also containing a wealth of software system information. Previous studies have acknowledged privacy leaks in software logs and Android apps as significant issues without providing a comprehensive view of the privacy leaks in Android app logs. In this study, we build a comprehensive dataset of Android app logs and conduct an empirical study to analyze the status and severity of privacy leaks in Android app logs. Our study comprises three aspects: (1) Understanding real-world developers' concerns regarding privacy issues related to software logs; (2) Studying privacy leaks in the Android app logs; (3) Investigating the characteristics of privacy-leaking Android app logs and analyzing the reasons behind them. Our study reveals five different categories of concerns from real-world developers regarding privacy issues related to software logs and the prevalence of privacy leaks in Android app logs, with the majority stemming from developers' unawareness of such leaks. Additionally, our study provides developers with suggestions to safeguard their privacy from being logged.

cs.SE↗

arXiv2026

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge collaboration and real-time interaction. GUI-Owl-1.5 achieves state-of-the-art results on more than 20+ GUI benchmarks on open-source models: (1) on GUI automation tasks, it obtains 56.5 on OSWorld, 71.6 on AndroidWorld, and 48.4 on WebArena; (2) on grounding tasks, it obtains 80.3 on ScreenSpotPro; (3) on tool-calling tasks, it obtains 47.6 on OSWorld-MCP, and 46.8 on MobileWorld; (4) on memory and knowledge tasks, it obtains 75.5 on GUI-Knowledge Bench. GUI-Owl-1.5 incorporates several key innovations: (1) Hybird Data Flywheel: we construct the data pipeline for UI understanding and trajectory generation based on a combination of simulated environments and cloud-based sandbox environments, in order to improve the efficiency and quality of data collection. (2) Unified Enhancement of Agent Capabilities: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and multi-agent adaptation; (3) Multi-platform Environment RL Scaling: We propose a new environment RL algorithm, MRPO, to address the challenges of multi-platform conflicts and the low training efficiency of long-horizon tasks. The GUI-Owl-1.5 models are open-sourced, and an online cloud-sandbox demo is available at https://github.com/X-PLUG/MobileAgent.

cs.AI↗

arXiv2026

Dynamic Matching Under Patience Imbalance

We study a dynamic matching problem on a two-sided platform with unbalanced patience, in which long-lived supply accumulates over time with a unit waiting cost per period, while short-lived demand departs if not matched promptly. High- or low-quality agents arrive sequentially with one supply agent and one demand agent arriving in each period, and matching payoffs are supermodular. In the centralized benchmark, the optimal policy follows a threshold-based rule that rations high-quality supply, preserving it for future high-quality demand. In the decentralized system, where self-interested agents decide whether to match under an exogenously specified payoff allocation proportion, we characterize a welfare-maximizing Markov perfect equilibrium. Unlike outcomes in the centralized benchmark or in full-backlog markets, the equilibrium exhibits distinct matching patterns in which low-type demand may match with high-type supply even when low-type supply is available. Unlike settings in which both sides have long-lived agents and perfect coordination is impossible, the decentralized system can always be perfectly aligned with the centralized optimum by appropriately adjusting the allocation of matching payoffs across agents on both sides. Finally, when the arrival probabilities for H- and L-type arrivals are identical on both sides, we compare social welfare across systems with different patience levels: full backlog on both sides, one-sided backlog, and no backlog. In the centralized setting, social welfare is weakly ordered across systems. However, in the decentralized setting, the social welfare ranking across the three systems depends on the matching payoff allocation rule and the unit waiting cost, and enabling patience can either increase or decrease social welfare.

econ.TH↗

arXiv2026

Design, waterproofing, and mass production of the 3-inch PMT frontend system of JUNO

Over 25,600 3-inch photomultiplier tubes (PMTs) have been instrumented for the central detector of the Jiangmen Underground Neutrino Observatory. Each PMT is equipped with a high-voltage divider and a frontend cable with waterproof sealing. Groups of sixteen PMTs are connected to the underwater frontend readout electronics via specialized multi-channel waterproof connectors. This paper outlines the design and mass production processes for the high-voltage divider, the cable and connector, as well as the waterproof potting of the PMT bases. The results of the acceptance tests of all the integrated PMTs are also presented.

physics.ins-det↗

arXiv2026

A Survey of Multimodal Hallucination Evaluation and Detection

Multi-modal Large Language Models (MLLMs) have emerged as a powerful paradigm for integrating visual and textual information, supporting a wide range of multi-modal tasks. However, these models often suffer from hallucination, producing content that appears plausible but contradicts the input content or established world knowledge. This survey offers an in-depth review of hallucination evaluation benchmarks and detection methods across Image-to-Text (I2T) and Text-to-image (T2I) generation tasks. Specifically, we first propose a taxonomy of hallucination based on faithfulness and factuality, incorporating the common types of hallucinations observed in practice. Then we provide an overview of existing hallucination evaluation benchmarks for both T2I and I2T tasks, highlighting their construction process, evaluation objectives, and employed metrics. Furthermore, we summarize recent advances in hallucination detection methods, which aims to identify hallucinated content at the instance level and serve as a practical complement of benchmark-based evaluation. Finally, we highlight key limitations in current benchmarks and detection methods, and outline potential directions for future research.

cs.CV↗

arXiv2026

RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference

Real-time recommender systems execute multi-stage cascades (retrieval, pre-processing, fine-grained ranking) under strict tail-latency SLOs, leaving only tens of milliseconds for ranking. Generative recommendation (GR) models can improve quality by consuming long user-behavior sequences, but in production their online sequence length is tightly capped by the ranking-stage P99 budget. We observe that the majority of GR tokens encode user behaviors that are independent of the item candidates, suggesting an opportunity to pre-infer a user-behavior prefix once and reuse it during ranking rather than recomputing it on the critical path. Realizing this idea at industrial scale is non-trivial: the prefix cache must survive across multiple pipeline stages before the final ranking instance is determined, the user population implies cache footprints far beyond a single device, and indiscriminate pre-inference would overload shared resources under high QPS. We present RelayGR, a production system that enables in-HBM relay-race inference for GR. RelayGR selectively pre-infers long-term user prefixes, keeps their KV caches resident in HBM over the request lifecycle, and ensures the subsequent ranking can consume them without remote fetches. RelayGR combines three techniques: 1) a sequence-aware trigger that admits only at-risk requests under a bounded cache footprint and pre-inference load, 2) an affinity-aware router that co-locates cache production and consumption by routing both the auxiliary pre-infer signal and the ranking request to the same instance, and 3) a memory-aware expander that uses server-local DRAM to capture short-term cross-request reuse while avoiding redundant reloads. We implement RelayGR on Huawei Ascend NPUs and evaluate it with real queries. Under a fixed P99 SLO, RelayGR supports up to 1.5$\times$ longer sequences and improves SLO-compliant throughput by up to 3.6$\times$.

cs.DC↗

arXiv2025

HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery

The rapid advancement of large language models (LLMs) and multimodal foundation models has sparked growing interest in their potential for scientific research. However, scientific intelligence encompasses a broad spectrum of abilities ranging from understanding fundamental knowledge to conducting creative discovery, and existing benchmarks remain fragmented. Most focus on narrow tasks and fail to reflect the hierarchical and multi-disciplinary nature of real scientific inquiry. We introduce \textbf{HiSciBench}, a hierarchical benchmark designed to evaluate foundation models across five levels that mirror the complete scientific workflow: \textit{Scientific Literacy} (L1), \textit{Literature Parsing} (L2), \textit{Literature-based Question Answering} (L3), \textit{Literature Review Generation} (L4), and \textit{Scientific Discovery} (L5). HiSciBench contains 8,735 carefully curated instances spanning six major scientific disciplines, including mathematics, physics, chemistry, biology, geography, and astronomy, and supports multimodal inputs including text, equations, figures, and tables, as well as cross-lingual evaluation. Unlike prior benchmarks that assess isolated abilities, HiSciBench provides an integrated, dependency-aware framework that enables detailed diagnosis of model capabilities across different stages of scientific reasoning. Comprehensive evaluations of leading models, including GPT-5, DeepSeek-R1, and several multimodal systems, reveal substantial performance gaps: while models achieve up to 69\% accuracy on basic literacy tasks, performance declines sharply to 25\% on discovery-level challenges. HiSciBench establishes a new standard for evaluating scientific Intelligence and offers actionable insights for developing models that are not only more capable but also more reliable. The benchmark will be publicly released to facilitate future research.

cs.AI↗

arXiv2025

Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification

The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. Although modern biological pre-trained models have achieved great success in analyzing these macromolecules individually, their interconnected nature remains underexplored. This paper follows the guidance of the central dogma to redesign both the data and model pipeline and offers a comprehensive framework, Life-Code, that spans different biological functions. As for data flow, we propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences. As for the model, we design a codon tokenizer and a hybrid long-sequence architecture to encode the interactions between coding and non-coding regions through masked modeling pre-training. To model the translation and folding process with coding sequences, Life-Code learns protein structures of the corresponding amino acids by knowledge distillation from off-the-shelf protein language models. Such designs enable Life-Code to capture complex interactions within genetic sequences, providing a more comprehensive understanding of multi-omics with the central dogma. Extensive experiments show that Life-Code achieves state-of-the-art results on various tasks across three omics, highlighting its potential for advancing multi-omics analysis and interpretation.

cs.LG↗

arXiv2025

High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection

Object detection models demand large-scale annotated datasets, which are costly and labor-intensive to create. This motivated Imaginary Supervised Object Detection (ISOD), where models train on synthetic images and test on real images. However, existing methods face three limitations: (1) synthetic datasets suffer from simplistic prompts, poor image quality, and weak supervision; (2) DETR-based detectors, due to their random query initialization, struggle with slow convergence and overfitting to synthetic patterns, hindering real-world generalization; (3) uniform denoising pressure promotes model overfitting to pseudo-label noise. We propose Cascade HQP-DETR to address these limitations. First, we introduce a high-quality data pipeline using LLaMA-3, Flux, and Grounding DINO to generate the FluxVOC and FluxCOCO datasets, advancing ISOD from weak to full supervision. Second, our High-Quality Proposal guided query encoding initializes object queries with image-specific priors from SAM-generated proposals and RoI-pooled features, accelerating convergence while steering the model to learn transferable features instead of overfitting to synthetic patterns. Third, our cascade denoising algorithm dynamically adjusts training weights through progressively increasing IoU thresholds across decoder layers, guiding the model to learn robust boundaries from reliable visual cues rather than overfitting to noisy labels. Trained for just 12 epochs solely on FluxVOC, Cascade HQP-DETR achieves a SOTA 61.04\% mAP@0.5 on PASCAL VOC 2007, outperforming strong baselines, with its competitive real-data performance confirming the architecture's universal applicability.

cs.CV↗

arXiv2025

Finite generation of higher rank quasi-monomial valuations via the extended Rees algebra

In the algebraic theory of K-stability, one of the most challenging problems is to show the graded algebra associated with certain higher rank quasi-monomial valuations are finitely generated. In the global case of Fano varieties and local case of klt singularities, the finite generation has been proved for quasi-monomial valuations on models of qdlt Fano type. In this paper, we generalize these results using a different argument, by studying the extended Rees algebra via a more algebraic approach. As consequences, our results apply to fibrations of Fano type with singularities worse than qdlt, and graded algebras coming from the multi-section ring of arbitrary divisors.

math.AG↗

arXiv2025

Stable degeneration of families of klt singularities with constant local volume

We prove that for a locally stable family of klt singularities with constant local volume, the ideal sequences of the minimizing valuations for the normalized volume function form a family of ideals with flat cosupport, which induces a degeneration to a locally stable family of K-semistable log Fano cone singularities. Our proof is a family version of the method of C. Xu and Z. Zhuang proving finite generation by Kollár models and multiple degenerations.

math.AG↗

arXiv2025

SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs

Despite rapid advances, Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge, which correspond to faithfulness and factuality hallucinations, respectively. Prior studies primarily evaluate faithfulness hallucination at a rather coarse level (e.g., object-level) and lack fine-grained analysis. Additionally, existing benchmarks often rely on costly manual curation or reused public datasets, raising concerns about scalability and data leakage. To address these limitations, we propose an automated data construction pipeline that produces scalable, controllable, and diverse evaluation data. We also design a hierarchical hallucination induction framework with input perturbations to simulate realistic noisy scenarios. Integrating these designs, we construct SHALE, a Scalable HALlucination Evaluation benchmark designed to assess both faithfulness and factuality hallucinations via a fine-grained hallucination categorization scheme. SHALE comprises over 30K image-instruction pairs spanning 12 representative visual perception aspects for faithfulness and 6 knowledge domains for factuality, considering both clean and noisy scenarios. Extensive experiments on over 20 mainstream LVLMs reveal significant factuality hallucinations and high sensitivity to semantic perturbations.

cs.CV↗

arXiv2025

Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency

Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model's existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR proficiency, inspired by the concept "Bilingual Cognitive Advantage". Specifically, SSR prompts the model to generate OCR text before producing translation text, which allows the model to leverage its strong monolingual OCR ability while learning to translate text across languages. Comprehensive experiments demonstrate the proposed SSR learning helps mitigate catastrophic forgetting, improving the generalization ability of MLLMs on both OCR and DIMT tasks.

cs.CL↗