Searcharxiv⌕ Search

arXiv subjects

Zilong Wang

Publications and source records attributed to Zilong Wang.

At least 19 recordsLinked to original sources
arXiv2026

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated. Existing benchmarks focus on general web or desktop tasks and underrepresent medical software, which requires domain knowledge, exhibits markedly different UI design from mainstream applications, lacks public testing environments, and demands safety validation beyond task completion. We introduce MedCUA-Bench, an interactive benchmark for clinical computer-use agents. It covers 18 clinical scenarios across 10 medical domains, reconstructed from real product manuals and open-source medical systems to capture authentic clinical interfaces while avoiding licensing and privacy constraints. Each task ships with paired intent- and step-level goals to disentangle clinical reasoning from UI execution, and is evaluated by a deterministic checker over task completion and five clinical safety dimensions. Across 23 agents, the best closed-source model reaches 54.2% strict success, while all models remain below 9% on the real OpenEMR. Open-source agents average only 2.5%, with the best reaching 16.2%. MedCUA-Bench exposes the gap between current agents and reliable clinical software use, providing a reproducible testbed for future research.

cs.AI↗
arXiv2026

Evolutionary characterization of whole-genome doubling across human cancers

Whole-genome doubling (WGD) is common across human cancers and is associated with tumour progression and adverse clinical outcomes. However, how genome-doubled tumours evolve across diverse cancer types remains poorly understood. Here we characterize WGD-associated tumour evolution by integrating genomic analyses of 41,332 tumours from 12 cancer types with evolutionary timing and multi-omic data. Several canonical driver mutations generally preceded WGD when both occurred, as did the onset of homologous recombination deficiency-associated mutagenesis. Notably, post-WGD chromosome-arm losses showed substantially weaker cancer-type dependence than pre-WGD losses, with 61-75% less variance explained by cancer type. Beyond chromosomal evolution, WGD+ tumours showed reduced interferon-response and HLA antigen-presentation programmes linked to epigenetic remodelling, without disproportionate enrichment of genetic immune-escape alterations. Our findings highlight WGD as a recurrent evolutionary transition associated with altered chromosomal evolution and epigenetically linked immune adaptation across cancers.

q-bio.GN↗
arXiv2026

Inkitiate: Initiating and Steering Agent Assistance through Ink in a Spatial Workspace

Handwriting and sketching help people develop ideas around information. As this work unfolds, users may seek assistance with finding, understanding, and organizing materials. We investigate how ink can initiate and steer agent assistance in this process. An eight-participant formative study explored desired assistance and interaction expectations, informing three connected activities: bringing materials in, thinking with materials, and shaping the space. We present Inkitiate, a spatial workspace for ink-based agent assistance in knowledge work. Through ink, users retrieve external materials, build on accumulated content and results, and reorganize the canvas, while inspecting and guiding agent actions. In a study with eighteen participants, users reported favorable usability and low perceived workload, and used retained ink and materials to develop further ink queries. An ink-query vocabulary and cases reveal how users combine linguistic and graphical expressions to direct agents. These findings inform ink-based agent interaction design for expressive requests and continued work with materials.

cs.HC↗
arXiv2026

Evaluating Harmful Memorization in LLM Code Generation

Assessing memorization in LLM code generation is challenging because code reuse is not inherently harmful. Correct programs often share APIs, templates, and algorithmic idioms, so code similarity alone may reflect benign reuse rather than problematic memorization. We focus on the harmful case: a model fails to adapt when task semantics change and instead produces code that remains highly similar to the original solution. We propose \emph{code rewriting}, an automated semantic perturbation pipeline that constructs superficially similar but semantically different variants of existing coding tasks by modifying a core logic element of the reference solution and regenerating the corresponding prompt. To summarize this behavior, we introduce the \emph{Harmful Memorization Index} (HMI), an operational diagnostic that combines similarity to the original solution with performance degradation on rewritten tasks. We use harmful memorization as an operational behavioral term for this specific failure mode; HMI does not establish whether an original task or solution appeared in a model's training data. HMI is intended to complement standard accuracy metrics by capturing brittleness under small semantic changes. Across MBPP+ and BigCodeBench, we find that: (1) HMI does not monotonically increase with model scale and often decreases on simpler tasks; (2) high-HMI failures are concentrated in specific logic-edit types, especially constraint changes and data transformations; (3) supervised fine-tuning improves original-task accuracy but can substantially increase HMI on held-out tasks; and (4) across the evaluated post-training settings, PPO yields a more favorable accuracy--HMI trade-off than SFT.

cs.AI↗
arXiv2026

Working Through Representation: Malleable Workspaces for Human-Agent Knowledge Work

Generative AI supports knowledge work, yet conversational histories may not capture the evolving organization that guides subsequent action. We introduce the Malleable Workspace, a conceptual model of how humans and agents form and revise a Work Representation and use its organization to advance work within a wider Work Environment. We developed it iteratively through conceptual analysis, comparison of 58 papers, and the construction and three-month longitudinal study of MalleableSpace with seven experienced agent users. Systems varied in what they represented as units and relations. System-assembled context was common; more systems supported local incorporation of agent outputs than reorganization, and fewer supported consequential agent-driven changes beyond the representation. The field study showed how representational roles and organization developed in use. These observations refined the model's account of how representation-grounded action depends on and can change the Work Environment. We contribute a conceptual and analytic foundation for representation-centered human--agent design.

cs.HC↗
arXiv2026

A plug-in estimator of the non-iterative conditional expectation g-formula using long short-term memory models

The non-iterative conditional expectation (NICE) plug-in estimator of the g-formula can be used to estimate the causal effects of sustained treatment strategies, even in the presence of treatment-confounder feedback, under the assumptions of exchangeability, positivity, and consistency. In practical applications, parametric models are commonly used to estimate the joint distribution of confounders, treatments, and outcomes over time. As an alternative to parametric models, long short-term memory (LSTM) models, designed to capture both short-term patterns and long-range dependencies in sequential data, may better accommodate complex temporal dependencies among time-varying confounders, treatments, and outcomes. However, the validity of statistical inferences of a plug-in estimator based on LSTM models has not yet been investigated. Here, we provide proof of principle that, under a complex data generation mechanism that resembles data from a cohort of persons with HIV and sufficiently large sample sizes, an LSTM-based NICE g-formula plug-in estimator results in less bias than parametric estimators while achieving near-nominal coverage for 95\% confidence intervals. This work is intended to spur the development of a theoretical framework that encompasses deep learning plug-in estimators for causal inference based on high-dimensional longitudinal data.

stat.ME↗
arXiv2026

Recursive Organization Improvement: A Modeling Specification for Human--Agent Organizations

Stronger AI agents do not automatically produce better organizations: teams must also learn which work arrangements to retain and when to reconsider them, while those arrangements determine what evidence the team can learn from. We propose a modeling specification for recursive organization improvement and evaluate it through an executable checker, a public-record mapping, and two simulation studies. The specification connects actor-visible histories, organizational memory, decision rights, and the evidence used to retain changes. Study 1 crosses six decision rules, three memory conditions, and three task environments under fixed resource ceilings. In a stationary environment, cumulative evidence raises balanced evaluation's net value per task from 0.452 to 0.480, while selection regret falls from 0.029 to 0.002. After a workflow-ranking reversal, retained evidence delays adaptation. In post hoc acquisition-matched controls, the remaining contribution of program replacement depended on the memory rule: small and uncertain under an eight-round window, positive under cumulative memory after a reversal, and negative under reset evidence. Study 2 models human-agent review with shared errors, copying, and decision rights. It identifies a two-actor case in which public records conceal whether agreement comes from shared errors or copying, and shows how dependence changes the preferred placement of human judgment under a fixed budget. Paid observation can lower decision error while costing more than the deployment gain. Assessments of organizational improvement should track the evidence acquired and retained, using acquisition-matched comparisons to isolate the contribution of evaluator revision.

cs.MA↗
arXiv2026

ScaleMPA: Rethinking Scalable RRT* Acceleration With a Grid-Native Representation

Real-time motion planning remains challenging in large and high-dimensional environments. Prior acceleration of RRT* follows tree-centric state organization, which reduces per-query cost but preserves superlinear end-to-end complexity and limits parallelism through structural dependencies. This paper presents ScaleMPA, a motion-planning accelerator that rethinks RRT* with a grid-native representation. By replacing hierarchical traversal with direct grid-based access, ScaleMPA reduces the planner critical path and exposes fine-grained parallelism. To make this reformulation practical under sparse high-dimensional planning, ScaleMPA further proposes a multi-resolution grid search engine and a hash-grid memory system. Implemented in 28 nm CMOS, ScaleMPA achieves millisecond-level planning latency and delivers 4.7$\times$--44.4$\times$ speedup over state-of-the-art motion-planning accelerators.

cs.RO↗
arXiv2026

VoroUDF: Meshing Unsigned Distance Fields with Voronoi Optimization

We present VoroUDF, an algorithm for reconstructing high-quality triangle meshes from Unsigned Distance Fields (UDFs). Our algorithm supports non-manifold geometry, sharp features, and open boundaries, without relying on error-prone inside/outside estimation, restrictive look-up tables nor topologically noisy optimization. Unlike fixed-grid approaches, our Voronoi-based formulation optimizes a set of movable seeds that travel freely along the iso-surface, jointly minimizing a tangent-plane fitting energy, driven by a fixed set of surface samples queried once from the UDF and its gradient, and a repulsion energy that keeps the seeds evenly distributed. It achieves significantly improved topological consistency and geometric fidelity compared to existing methods, while producing lightweight meshes suitable for downstream real-time and interactive applications.

cs.GR↗
arXiv2026

VibeVoice-ASR-Streaming Technical Report

Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate tasks. Recently, end-to-end models such as VibeVoice-ASR have unified the two tasks within a single model. However, existing unified models still mainly support offline recognition, making it difficult to meet the low-latency requirements of real-time voice assistants and agents. To tackle this issue, we present VibeVoice-ASR-Streaming, one of the first LLM-based end-to-end approaches to streaming speaker-attributed ASR. It interleaves fixed-size audio chunks, a small amount of lookahead audio and previous text. This allows the model to produce ''who said what'' as speech arrives, without a separate diarization stage. For transcription accuracy, our 7B model achieves the lowest average WER/CER across five evaluation sets. For speaker attribution, it achieves the best or tied-best on 12 of 13 evaluation settings. We release the 1.5B and 7B model weights together with inference code.

eess.AS↗
arXiv2026

Benchmarking Clinical Decision Pathway Adherence in Large Language Models

Following clinical decision pathways (CDPs) defined by clinical practice guidelines is essential for safe and reliable medical decision-making. However, existing medical large language model (LLM) benchmarks mainly evaluate final-answer accuracy, providing limited evaluation of models' ability to adhere to guidelines. To address this gap, we introduce MEGA-CDP, a benchmark for evaluating whether medical LLMs can generate guideline-adherent CDPs using provided guidelines as references. MEGA-CDP is constructed from 2,274 English and Chinese clinical practice guidelines through a guideline-to-case pipeline, yielding 42,353 clinical cases with explicit reference CDPs. It supports both single-turn vignette and multi-turn interactive settings, and introduces a CDP-oriented evaluation framework for measuring pathway consistency. Experiments on 16 representative LLMs show that reliable clinical decision support remains challenging for current models, demonstrating the need for CDP-oriented evaluation and the value of MEGA-CDP for advancing guideline adherence in medical LLMs.

cs.CL↗
arXiv2026

Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification

Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment. Because deployed LLMs are commonly exposed only through query APIs, ownership verification must often rely on black-box text responses. This setting is difficult: generations are open-ended and can vary across repeated queries, while existing black-box fingerprints rely on signals that are fragile under a final-response interface, including full-text matching, soft behavioral features, or model-specific prompts designed not to transfer. We propose TCF (Targeted Counterfactual Fingerprinting), a black-box LLM fingerprinting framework that converts open-ended generation comparison into constrained-answer targeted counterfactual transfer. TCF restricts each verification query to a finite answer space, reducing the surface-form ambiguity that enters the verification score, and optimizes a prompt perturbation toward a counterfactual target different from the protected model's clean answer on the original prompt. Verification reduces to checking whether the suspect model's parsed final answer matches the recorded target. We introduce the source-model counterfactual margin (SCM), a protected-model-only quantity that certifies the target is unlikely before the perturbation and likely after it; SCM controls target selection, perturbation stopping, and fingerprint filtering. Under explicit derived-preservation and independent-transfer budgets motivated by local behavioral closeness, we derive a target-accuracy gap between derived and independent models. Across four LLM families, TCF achieves an average AUC of 0.9861, improving over TRAP, ProFLingo, and ZeroPrint by 0.07 to 0.19.

cs.CR↗
arXiv2026

SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials

Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains largely unexplored. We introduce SoM-1K, the first large-scale multimodal benchmark dataset dedicated to evaluating foundation models on problems in the strength of materials (SoM). The dataset, which contains 1,065 annotated SoM problems, mirrors real-world engineering tasks by including both textual problem statements and schematic diagrams. Due to the limited capabilities of current foundation models in understanding complicated visual information, we propose a novel prompting strategy called Descriptions of Images (DoI), which provides rigorous expert-generated text descriptions of the visual diagrams as the context. We evaluate eight representative foundation models, including both large language models (LLMs) and vision language models (VLMs). Our results show that current foundation models struggle significantly with these engineering problems, with the best-performing model achieving only 56.6% accuracy. Interestingly, we found that LLMs, when provided with DoI, often outperform VLMs provided with visual diagrams. A detailed error analysis reveals that DoI plays a crucial role in mitigating visual misinterpretation errors, suggesting that accurate text-based descriptions can be more effective than direct image input for current foundation models. This work establishes a rigorous benchmark for engineering AI and highlights a critical need for developing more robust multimodal reasoning capabilities in foundation models, particularly in scientific and engineering contexts.

cs.CL↗
arXiv2026

A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining

At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are prohibitively expensive to deploy at scale, while traditional pipelines of classifiers and extractors remain efficient yet brittle and unable to generalize to new tasks. We introduce Falconer, a collaborative framework that combines the agentic reasoning of LLMs with lightweight proxy models for scalable knowledge mining. In Falconer, LLMs act as planners, decomposing user instructions into executable pipelines, and as annotators, generating supervision to train small proxies. The framework unifies classification and extraction into two atomic operations, get label and get span, enabling a single instruction-following model to replace multiple task-specific components. To evaluate the consistency between proxy models incubated by Falconer and annotations provided by humans and large models, we construct new benchmarks covering both planning and end-to-end execution. Experiments show that Falconer closely matches state-of-the-art LLMs in instruction-following accuracy while reducing inference cost by up to 90% and accelerating large-scale knowledge mining by more than 20x, offering an efficient and scalable foundation for Deep Research.

cs.AI↗
arXiv2026

A report-grounded vision-language foundation model for colonoscopy from 280000 routine reports

Vision-language models remain underused in colonoscopy despite the rich expert descriptions recorded in routine reports. These reports document lesion appearance, size and location but summarise entire procedures rather than caption individual frames, leaving clinical findings only weakly linked to the corresponding images. Here we develop EndoCLIP, a colonoscopy vision-language foundation model trained on 125,756 lesion-level image-text pairs progressively recovered from 280,476 routine colonoscopy records. Across lesion-level image-text retrieval, structured report generation and six multi-centre clinical classification tasks, EndoCLIP outperforms general-purpose and biomedical vision-language encoders in both zero-shot and linear-probe settings. On benign-versus-malignant classification, its linear probe approaches the performance of expert readers in a blinded study involving 12 endoscopists. These results suggest that recovering finding-to-frame correspondence can transform routine documentation into scalable supervision, enabling clinical targets to be specified in language rather than separately annotated for each task.

cs.AI↗
arXiv2026

Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement

Although artificial intelligence (AI) has shown promising performance in several medical tasks, accurate dementia etiology diagnosis with AI remains challenging due to complex overlapping symptoms among diseases. Scaling up the dataset size by combining the cross-center samples may bring a gain in the pursuit of performance, while the inherent data heterogeneity across centers or populations induces the conflict. Conventional multi-task learning paradigms offer a promising framework; however, they fail to consider critical meta information (e.g., site-specific acquisition and modality availability) to combat the heterogeneity. To address this challenge, we propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis, which injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training, enabling explicit modeling of heterogeneity. Besides, a trust-region constrained optimization scheme is designed to regularize the model from spurious correlations during training through a reference model. Across seven independent cohorts, our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline, while maintaining superior out-of-domain generalization under both cross-center and cross-sequence evaluations. Extensive validation also confirms the alignment between model predictions and established biomarkers (amyloid, tau) and clinical severity, highlighting the potential of COME to enable robust and interpretable dementia diagnostics in real-world settings.

cs.LG↗
arXiv2026

Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes, resulting in poor generalization on minority groups. Bias mitigation remains challenging due to two fundamental issues. First, when group labels are unavailable, existing group-unsupervised methods typically infer spurious attributes implicitly from model behavior, making it difficult to identify spurious factors that are semantically aligned with real-world biases. Second, even with pseudo spurious supervision, most existing debiasing methods follow a single-branch design that operates within a single shared feature space, where target and spurious attributes are intrinsically entangled. To address the first challenge, we introduce Confidence-guided Bias Concept Mining (CBCM), which leverages diffusion-disentangled, semantically grounded concept representations to identify reliable spurious attributes without attribute annotations. To address the second challenge, we propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches and explicitly removes spurious information through cross null-space projection while preserving target-relevant semantics. Extensive experiments on four benchmark datasets show that our method achieves state-of-the-art worst group accuracy among group-unsupervised approaches, while tuning at most 0.22% of the model parameters. The source code is available in the supplementary materials.

cs.CV↗
arXiv2026

Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework

Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evolving, and inherently open-ended. Traditional rule engines are brittle and costly to maintain, whereas unconstrained LLM agents lack the reliability and auditability required for financial decisions. We present a production-grade LLM-powered pricing system with a strict decision boundary: LLMs perform structured extraction and bounded policy/path selection, while all numeric pricing, including total-price computation, is executed deterministically. Policies are compiled into interpretable condition trees, enabling open-ended support for new clauses and evolving rules without code changes, while exposing auditable artifacts for human-in-the-loop control. Periodic fine-tuning on logged traces further improves tree induction and path matching. Deployed at a municipal state-owned tourism enterprise across 7 scenic sites and 12 business categories with 1,500+ operators and 1,000+ active policies, the system processed 3,960 orders in six months, reduced the order management team from 15-20 to 3, and cut per-order handling time from 10 minutes to <2 minutes.

cs.CL↗