arXiv subjects

Yi Guo

Publications and source records attributed to Yi Guo.

At least 19 recordsLinked to original sources

arXiv2026

Prosumer Synchronisation Risk: Impacts of Time-Varying Tariffs on Distribution Network Expansion

The rapid deployment of distributed energy resources, including heat pumps, electric vehicles, photovoltaics, and battery storage, is reshaping the operation of low-voltage networks. While distribution system operators often aim to develop time-varying tariffs to incentivise network-friendly behaviour and defer reinforcements, they risk triggering prosumer synchronisation. As prosumers follow price signals, their behaviour may synchronise, avoiding existing load peaks while creating undesirable peaks at other times. This paper quantifies the impact on low-voltage network reinforcement needs when shifting from flat tariffs to two time-varying tariffs: Time-of-Use and Real-Time Pricing. Applying a mixed-integer linear model across 471 low-voltage reference networks in Switzerland, we evaluate expansion requirements under projections of distributed energy resource deployment for 2050. In the model, prosumers operate their distributed energy resources in accordance with their subscribed electricity tariff to minimise costs, and the distribution system operator subsequently optimises reinforcements. Our results demonstrate that while adopting time-varying tariffs can reduce reinforcement investment costs by more than 50%, high adoption rates can reverse this declining trend. Specifically, once prosumer adoption exceeds the optimal thresholds of 50% for Time-of-Use and 40% for Real-Time Pricing, reinforcement needs increase by 39% and 134%, respectively, for an additional 20% of tariff adoption.

eess.SY↗

arXiv2026

CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation

Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignment breaks down under domain shift, where artifacts and unseen protocols produce confident errors. Existing post-hoc methods adapt the correction at test time, conditioning on predictive entropy, the logit pattern, or augmentation response, but each proxy is read from the terminal prediction, the very quantity that shift corrupts. This motivates reliability evidence beyond the terminal prediction, which categorical diffusion provides in two ways. First, a generative shape prior keeps a capacity-limited reference intact when appearance is corrupted, so its disagreement with the primary segmentor highlights primary-model errors. Second, every reverse step yields a class distribution, separating persistent disagreement from transient discrepancy. Aggregated over the trajectory, this disagreement correlates with Dice at 0.788, against 0.521 for a matched discriminative control. We therefore propose CARD (Calibration via Agreement in Reverse Diffusion), which maps the temporal aggregate of this disagreement to a temperature field applied per pixel across all classes, so that confidence changes while the segmentation does not. Across cardiac, prostate and brain MRI shifts, CARD lowers calibration error in 45 of 49 comparisons against the strongest baseline in each setting.

cs.CV↗

arXiv2026

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousands of them. Which skill to read has thus become a decision the policy itself makes in the middle of an episode, yet no existing signal trains it. We show that the default remedy, outcome-rewarded RL over the candidate slate, cannot teach it, for a structural reason we identify and name selector credit starvation: under a broadcast, sequence-level advantage, the few tokens that name the chosen skill carry a vanishing share of the loss, and the credit they inherit is increasingly wrong-signed as trajectories lengthen. A correct choice is punished whenever the execution after it fails, even though the choice itself is among the most valuable decisions in the trajectory. Auditing a completed run's own training artifacts confirms all three properties, each worsening monotonically with horizon. SkillGate removes the failure by construction: it partitions the token support into two disjoint credit channels, outcome credit reaching only execution tokens, and a separate action-local advantage reaching exactly the skill-naming tokens, positive only when a trajectory's single read is the correct one. On five agentic benchmarks under a 16-candidate slate, SkillGate lifts a 9B policy from 40.8% to 53.2% trial success, well ahead of the identical budget spent on outcome reward alone, while cutting exposure to misleading candidates by two thirds and reading fewer skills.

cs.AI↗

arXiv2026

Win-Ratio Regression for Prioritized Composite Outcomes in Observational Studies: Doubly Robust and Efficient Estimation with Future-Score Correction

Prioritized pairwise outcomes are useful when clinical events follow a natural hierarchy, but censoring before pair resolution complicates estimation. We develop a win-ratio regression framework for this setting by defining a complete-data target over follow-up and deriving an estimating equation for the observed data. The central idea is future-score correction (FC): when censoring prevents later pairwise comparisons from being observed, the method replaces the remaining score with its conditional expectation given the observed history. This correction recovers pairwise information beyond that provided by inverse censoring weights alone. Additionally, we incorporate treatment weighting and baseline outcome augmentation to address baseline confounding. Together, these components yield double robustness for treatment assignment and censoring. Inference is obtained from U-statistic theory. Under standard regularity conditions, the AIPW-FC estimator is asymptotically normal and efficient when all nuisance functions are correctly specified. Simulations with 30%, 50%, and 65% censoring show that efficiency gains from future-score correction increase with the censoring rate, with relative efficiency reaching 1.50 under 65% censoring and near-nominal coverage for AIPW-FC. An application to OneFlorida electronic health record data illustrates the method for a composite outcome that prioritizes death over hospitalization.

stat.ME↗

arXiv2026

An Agentic Generative Large Language Model for Treatment Planning of Colorectal Cancer

Treatment planning in precision oncology requires synthesizing heterogeneous patient information with rapidly evolving clinical guidelines to ensure guideline-concordant care. While large language models (LLMs) show promise in many diagnostic tasks, their adoption for high-stakes treatment planning is hindered by complex reasoning, adherence to timely clinical guidelines, and safety concerns. In this study, we present GatorOnco, an agentic LLM for colorectal cancer (CRC) treatment planning. GatorOnco is developed using a total of 282 billion tokens of biomedical text, including healthcare system-scale clinical text comprising 166 billion tokens from UF Health. We implemented a domain-adaptation method that integrates pre-training, model merging, a two-stage post-training approach, and agent-based reinforcement learning. An agentic retrieval-augmented generation (RAG) approach dynamically integrates time-sensitive clinical guidelines into the reasoning process. In a blind, randomized clinical evaluation conducted by five UF Health oncologists, GatorOnco significantly outperformed open-source LLMs (P < 0.01) and achieved expert-level performance comparable to UF Health oncologists. Compared with expert oncologists, GatorOnco received significantly higher ratings for readability (4.46 vs. 4.19, P < 0.01) and completeness (3.91 vs. 3.52, P < 0.01), while showing statistically comparable performance in correctness (4.09 vs. 4.11, P = 0.921), currency (4.04 vs. 3.98, P = 0.478), and safety (4.22 vs. 4.22, P = 0.999). These findings demonstrate that integrating agentic reasoning with large-scale domain adaptation can help bridge the gap for generative AI in high-stakes cancer treatment planning.

cs.CL↗

arXiv2026

Bootstrapping Vision-Language Model for Hysteroscopic Surgical Scene Segmentation

Hysteroscopic surgical scene segmentation plays a pivotal role in understanding the hysteroscopic intraoperative environment as well as computer-assisted intervention. However, this task presents unique challenges due to the high morphological similarity among different lesions and the presence of artifacts such as specular reflections, motion blur, and fluid occlusions in surgical videos. In this work, we propose the first vision-language model (VLM)-based hysteroscopic surgical scene segmentation method, which performs pixel-wise localization for fifteen representative categories in hysteroscopic surgical scenes. Our VLM-hyster has a segmentation backbone that utilizes the pretrained image encoder for robust visual feature extraction, coupled with a transformer-based decoder for dense prediction. Moreover, we design category-specific text prompts and incorporate a masked distillation branch to filter out visual features with low correlation to the text prompts, enabling the model to focus more effectively on category-specific image regions and thereby enhancing segmentation performance. We collect a large multicentric hysteroscopic surgical scene dataset, containing 4,020 high-resolution images with detailed mask annotations, for model training and evaluation. Experimental results demonstrate that VLM-hyster substantially outperforms state-of-the-art AI models. Furthermore, extensive assessments by gynecologists, as well as multicentre and prospective validations, demonstrate VLM-hyster's robustness and generalizability. The results suggest that VLM-hyster earns considerable potential in enabling AI-assisted localization of surgical instruments and lesions in hysteroscopic surgeries. Code is available at https://github.com/viscom-tongji/VLM-hyster.

cs.CV↗

arXiv2026

Complexity and Stability of Neural Activity Across Aging and Neurodegenerative Disease

Objective: EEG signals fluctuate continuously even within a fixed cognitive state, but an important question is whether the brain still reuses similar activity patterns to represent information over time. Methods: To address this, we model EEG as distributions of windowed activity patterns and quantify their temporal stability using Wasserstein distance, while intrinsic dimensionality captures representational complexity. Results: Across multi-task, lifespan, and clinical EEG datasets, we find that neural representations show constrained, condition-specific stability rather than unconstrained drift. Higher intrinsic dimensionality is consistently associated with lower stability, suggesting that richer representational spaces are less reproducible over time. Both measures exhibit reproducible spatial organization, with posterior regions showing higher dimensionality and lower stability than frontal regions. Healthy aging is characterized by increased dimensionality and reduced stability, whereas mild cognitive impairment and Alzheimer's disease show a joint collapse of both. Conclusions: These findings provide a distribution-level framework for understanding neural stability across cognition, aging, and disease. Significance: This framework offers a principled approach to quantifying neural representational stability, with potential utility as a sensitive biomarker for tracking cognitive aging and neurodegeneration in clinical settings.

q-bio.NC↗

arXiv2026

Distributed coordination for transmission-distribution systems with nonlinear flexibility aggregation

High shares of distributed energy resources (DERs) transform distribution systems into active participants in integrated transmission and distribution (ITD) operations. Linear models enable scalable distribution-level flexibility aggregation but can misclassify AC feasible operating points, whereas direct nonlinear aggregation becomes costly, especially in multiperiod ITD coordination. This paper reformulates transmission-distribution coordination within a hierarchical optimization framework and introduces a non-iterative predictor-corrector aggregation method. By leveraging path-following techniques from real-time optimal control, the approach achieves tractable computation with guaranteed error bounds. Across 24 radial distribution-network cases and seven meshed variants, including the real KIT Campus North grid, the proposed method yields substantially lower sampled false- and lost-flexibility rates than linear surrogates and a convex relaxation. On two 24-period ITD testcases, the formulation reduces end-to-end wall-clock time by factors of 6 relative to the corresponding centralized formulation, primarily through dimensionality reduction.

eess.SY↗

arXiv2026

Observation of metastable chiral domain walls in a topological magnet

The interplay between topology and correlation can give rise to exotic collective excitations. The integer and fractional quantum anomalous Hall (QAH) magnets recently discovered in two-dimensional (2D) flatband systems are predicted to host spin excitations distinct from those in conventional magnets. Experimentally, nevertheless, these new excitations remain largely unexplored. Here we investigate spin-valley excitations in a twisted MoTe2 moir\'e superlattice using resonant ultrafast pump-probe spectroscopy. We observe a metastable spin-valley excitation in the QAH magnet below T ~ 3.7 K that survives reverse magnetic field several times larger than the saturation field. The behavior of this excitation is sharply distinct from ordinary domain walls and magnons, indicating a new type of spin-valley textures unique to topological magnets. We propose that these textures are chiral domain walls with an in-plane winding of the pseudospin order parameter along the domain wall. Their metastability arises from the interplay between the topological winding in real space and the quantum geometry of the parent bands in momentum space through a universal mechanism. These chiral domain walls govern the nonequilibrium dynamics of QAH magnets and may play a central role in their stability. Our study highlights intrinsic quantum geometry effects on spin excitations in topological magnets; and provides key insights into the fundamental mechanism limiting stability of topological protection.

cond-mat.mes-hall↗

arXiv2026

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

Agents built around large language models continually accumulate interaction trajectories during deployment, yet their behavior typically remains fixed. Beyond updating model weights, these trajectories can improve the agent harness that constructs context, mediates tools, validates actions, and recovers execution. We introduce Harness-R1, the first method, to our knowledge, that makes failure-conditioned, lifecycle-wide editing of an existing executable runtime a learned capability. It post-trains a dedicated harness engineer with online reinforcement learning so that its edits are optimized for the realized task success they produce, rather than proposed by a fixed editor. A separate 9B engineer converts batches of target-agent failures into validated executable patches; fresh same-batch reruns of the frozen target provide outcome rewards, so training updates only the engineer. Cold-start supervised fine-tuning initializes this editing policy, which is then trained online with group-relative policy optimization. Across WebShop, ALFWorld, and DBBench, Harness-R1 raises vanilla Qwen3.5-9B success from 44.3% to 53.6% (+9.3 percentage points). After direct target-agent fine-tuning, a target-specific engineer raises the average further from 59.2% to 64.2% (+5.0 points); because these gains hold both before and after fine-tuning the target, Harness-R1 points toward co-evolving the harness engineer and the target agent.

cs.AI↗

arXiv2026

Studying Competing Events with Federated Cumulative Incidence Curves

Combining electronic health record (EHR) data from multiple institutions is a valuable strategy for conducting post-market safety surveillance of medical products, but privacy concerns limit sharing individual-level data. We develop a novel federated learning (FL) method for multi-site post-market safety surveillance of medical products using competing risks data. We apply this method to study immune-related adverse events (irAEs) following treatment with immune checkpoint inhibitors (ICIs) in patients with auto-immune disease (AID). We provide an algorithm for constructing non-parametric cumulative incidence curves for competing event types, which can be used to compare exposure groups (e.g. treated and untreated) with no sharing of patient-level data across institutions. We incorporate covariate adjustment via inverse propensity weighting, and informative causal comparison using the area under cumulative incidence curves, known as restricted mean time lost. We apply our method to $N=10,281$ cancer patients with no pre-existing endocrine-related AID receiving ICIs across $K=10$ sites from the OneFlorida+ network, comparing patients with a pre-existing non-endocrine AID to those with no pre-existing AID. After covariate adjustment, we found that patients with a pre-existing non-endocrine AID lost 4.8 [95% CI: 4.3,5.2] months of event-free survival time to endocrine irAEs in the first 18 months following treatment, compared to 3.2 [95% CI: 3.1,3.3] months in the group without prior AID. As patients with prior AID were initially excluded from clinical trials of ICIs, our findings provide important new information to clinicians and patients receiving or considering ICI treatment. Our proposed non-parametric federated algorithm is the first to allow investigators to use some of the most crucial non-parametric tools for conducting postmarket safety surveillance across multiple institutions.

stat.ME↗

arXiv2026

Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet

Translating complex biomedical data into patient-friendly narratives is central to modern biomedical informatics. This study presents a comparative analysis of training small language models (SLMs) in specialized biomedical datato-text generation tasks. We explore widely adopted post-training methods including supervised fine-tuning (SFT), direct preference optimization (DPO), odds ratio preference optimization (ORPO), and group relative policy optimization (GRPO) with Qwen-based SLMs on a medicine package leaflets dataset. To assess cross-dataset generalizability, we also curated drug label data from openFDA. We evaluate models using both standard lexical overlap metrics like ROUGE as well as semantic similarity measures. Across our experiments, the results show that (1) the aligned SLMs outperform proprietary models like GPT-5; (2) ORPO outperforms the SFTbaselines; (3) GRPO yields the most robust cross-dataset performance among the alignment methods tested as well as GPT-5.

cs.CL↗

arXiv2026

GenVid2Robot: From Video Generation to Robot Manipulation via Rigid-Geometric Consistency

Generated videos provide useful visual motion priors for robot manipulation, but their visual plausibility does not imply physical executability. A generated video usually lacks metric geometry, grasp grounding, robot kinematic feasibility, and execution-time feedback, which makes direct trajectory replay unreliable in real-world manipulation. This paper presents GenVid2Robot, a rigid-geometric consistency framework that converts generated video motion into executable real-robot manipulation trajectories. Given an initial RGB-D observation and a task instruction, GenVid2Robot samples task-relevant semantic anchors from the real first frame, tracks these anchors through generated video candidates, and verifies whether the resulting 2D motion can be explained by first-frame RGB-D anchors under a sparse relative $SE(3)$ model. In this way, generated videos are treated as uncertain visual motion hypotheses rather than direct robot demonstrations. Only geometrically consistent motion is transferred to the robot. The accepted relative motion is then applied to the real grasp-time TCP pose selected by mask-constrained grasping, producing a grasp-conditioned execution trajectory that is consistent with both the visual motion prior and the physical grasp configuration. To reduce execution mismatch caused by RGB-D noise, calibration residuals, and small contact-induced displacement, a bounded depth-compensation module corrects local depth-direction errors without assuming full online replanning. Real-robot experiments demonstrate that GenVid2Robot improves the reliability of generated-video-guided manipulation by grounding visual motion priors with sparse metric geometry, grasp constraints, robot feasibility checking, and bounded execution feedback.

cs.RO↗

arXiv2026

An Interpretable Deep Learning Framework for Discovery and Clinical Validation of Deep Radiomic Signatures in Tumor Classification

Imaging signatures are quantitative features extracted from medical images that provide clinically meaningful information for tumor diagnosis, characterization, prognosis, and treatment planning. Although deep learning has shown great potential for imaging signature discovery, its limited interpretability remains a major barrier to clinical adoption. Existing approaches often achieve high predictive performance but provide little biological insight into the identified signatures. We propose a unified framework for interpretable imaging signature discovery by integrating deep learning based segmentation, explainable classification, and radiomic analysis. A robust segmentation model is first used to accurately delineate tumors, followed by a Grad-CAM guided pipeline that identifies diagnostically important regions as candidate imaging signatures. A mutual information based adaptive thresholding strategy enables patient-specific signature extraction. The resulting signatures are validated using a downstream deep learning classification model, while radiomic features extracted from the signature regions are evaluated with traditional machine learning models and interpreted using SHAP to identify the most discriminative biomarkers. The proposed framework is evaluated on the public BUSI breast ultrasound, KiTS renal CT, and BraTS brain tumor datasets, as well as a private UF Health renal CT cohort. Compared with conventional whole-tumor radiomics, the proposed signature-based approach achieves improved discriminative performance while providing greater biological interpretability. By converting deep learning attention into reproducible quantitative imaging biomarkers, this framework offers an interpretable and reproducible solution for non-invasive tumor characterization and imaging biomarker discovery.

eess.IV↗

arXiv2026

CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness

Deep learning models for medical diagnosis frequently exhibit substantial performance disparities across sensitive subgroups (e.g., race, sex), even when average accuracy is high. While generative data augmentation offers a route to mitigate this, existing strategies are suboptimal; they typically address only one or two dependency channels between sensitive attributes and image features. We formalize the medical image formation process via a structural causal model, revealing that sensitive attributes actually influence image content through four distinct pathways-a structural complexity neglected by prior works. Based on this insight, we introduce CIPHER (Causal Intervention Pathways for Healthcare Equity and Robustness), a framework designed to systematically intervene on all four causal paths. To achieve this, CIPHER utilizes a diffusion backbone equipped with classifier-free guidance and null-text inversion. This technical design enables the faithful reconstruction of patient-specific anatomy while allowing for the precise, editable synthesis of counterfactuals required to break sensitive dependency chains. We tested CIPHER using chest X-ray and dermoscopy benchmarks across both standard and shifted data distributions. By employing a multi-pathway intervention strategy, our model reduced worst-group disparities by an average of 35.8% compared to disease-conditioned synthesis baselines, while also improving total diagnostic accuracy

cs.CV↗

arXiv2026

X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping. While integrating Predictive World Models (PWMs) addresses this gap, existing approaches either incur prohibitive cascaded latency or act as shallow terminal tasks that fail to deeply embed forward-looking reasoning. To endow VLA models with this reasoning capability, we propose X-Mind. Rather than treating PWMs as an external auxiliary module, this framework internalizes them as the Visual Chain-of-Thought (Visual CoT). By enforcing a world rollout prior to action, the model is constrained to imagine future evolution first, yielding a driving policy that is robustly grounded in environmental dynamics and aware of the future consequences its actions will unfold. The challenge here is efficiency, and we tackle it on two fronts. First, we introduce a compact representation of visual thinking: an abstract sketch that fuses a Bird's-Eye-View (BEV) layout with abstract driving priors (e.g., navigation intents and traffic rules). Rather than rolling out dense future frames, the model reasons over this sketch as a mental canvas; aided by a Deep Compression Autoencoder (DC-AE), a 12-frame future rollout is reduced to merely 96 tokens, alleviating the long-context computational bottleneck. Second, to accelerate generation further, we propose a recurrent block diffusion scheme that unrolls the denoising steps across the layers of the large drive model, folding iterative refinement into the backbone's one forward pass. Trained and validated on large-scale real-world data, X-Mind achieves competitive end-to-end driving performance, which makes it a highly practical, low-latency solution that successfully deploys large-scale cognitive reasoning directly onto resource-constrained vehicle platforms.

cs.CV↗

arXiv2026

Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data

Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusions. This lack of spatial grounding limits clinical utility: outputs cannot be audited, and models may hallucinate findings on normal scans. We present BrReMark (Brain Rethink via ROI Marking), a framework that introduces explicit region marking into brain MRI diagnosis. The model first generates hypotheses about potential abnormalities and grounds them through explicit bounding box marking, then verifies conclusions by re-examining the marked evidence. Training combines supervised fine-tuning on structured reasoning trajectories with reinforcement learning using a composite reward over localization accuracy and diagnostic reasoning. Furthermore, we integrate a domain randomization-based pathology synthesis augmentation strategy to improve the model's generalizability to out-of-distribution (OOD) data. On internal benchmark, BrReMark improves mAP50 from 0.74% to 37.54% compared to the base model, while achieving 21.57% Clinical F1 and 45.26% diagnostic accuracy. On NOVA OOD benchmark, it also achieves competitive overall performance with a 45.7% reduction in false positives compared to the state-of-the-art, indicating reduced hallucination on rare pathologies. These findings suggest that explicit hypothesis-verification grounding is a practical path toward trustworthy open-ended brain MRI diagnosis across both in-distribution and OOD settings.

cs.CV↗

arXiv2026

Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives

Information extraction from pathology reports is essential for cancer staging, tumor registry population. Yet key data remains embedded in narrative reports, making manual extraction labor-intensive and error-prone. Traditional supervised Natural Language Processing pipelines address this through fully supervised Named Entity Recognition and Relation Extraction, but require expensive manual annotation and suffer cascading failures when upstream entities are missed. In this study, we developed a zero-shot, agentic workflow, and evaluated five open-source generative Large Language Models (LLMs) to populate 13 College of American Pathologists synoptic fields from lung resection pathology reports. We compared them against a state-of-the-art supervised GatorTron NER-RE baseline using a novel, registry-aligned evaluation framework. The baseline achieved Micro-F1of 0.960, while the best zero-shot model (GPT-OSS-20B) achieved Micro-F1 of 0.893 (recall: 0.949), accurately extracting complex relations like Pathologic Stage without task-specific training. These results suggest that open-source, zero-shot agentic LLMs show great potential as a low-cost solution for extracting lung pathology information.

cs.CL↗