❌

Reading view

↗️

Postoperative circulating tumor DNA in stage II colon cancer: biological rationale, clinical evidence, and unresolved challenges

✇MRD
By: Erhua Yang · Xuefeng Wang · Jiajing Zhang · Dejiang Zhao · Zhimeng Yang · Xue Li · Guirong He · Tianhua Guo · Ruotian Wang · Baohong Yuan

Front Oncol. 2026 Sep 11;16:1908802. doi: 10.3389/fonc.2026.1908802. eCollection 2026.

ABSTRACT

BACKGROUND: Stage II colon cancer is clinically heterogeneous. Current clinicopathologic risk factors cannot accurately identify patients with residual disease after curative resection. Circulating tumor DNA (ctDNA) has emerged as a promising biomarker for the detection of minimal residual disease (MRD), defined as microscopic residual tumor burden that remains after curative-intent treatment and is not detectable by conventional imaging, and for postoperative risk stratification.

METHODS: This narrative review summarizes the biological basis, analytical approaches, and clinical evidence regarding ctDNA in stage II colon cancer. We particularly emphasize prospective studies and randomized controlled trials.

RESULTS: Postoperative ctDNA positivity is strongly associated with increased recurrence risk and provides superior prognostic stratification compared with conventional clinicopathologic factors. Prospective studies have demonstrated that ctDNA-positive patients experience substantially higher recurrence rates, with the GALAXY study reporting a hazard ratio of 11.99 (95% CI: 8.83-16.27) for disease-free survival among patients with postoperative molecular residual disease. The DYNAMIC trial demonstrated that ctDNA-guided management reduces adjuvant chemotherapy use without compromising recurrence-free survival. However, current evidence suggests an important asymmetry in clinical utility. ctDNA negativity may support treatment de-escalation. In contrast, ctDNA positivity has not yet reliably identified patients who benefit from treatment escalation.

CONCLUSIONS: ctDNA constitutes a robust prognostic biomarker in stage II colon cancer and supports risk-adapted postoperative management. However, its predictive value for guiding treatment escalation remains unproven. Integration with clinicopathologic and molecular features is essential before routine clinical implementation.

PMID:42798930 | PMC:PMC13613144 | DOI:10.3389/fonc.2026.1908802

  •  
  • ↗️
↗️

GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziyang Cheng · Tianshu Tang · Jinxin Lan · Xinze Chen · Yuhan Gong · Zhichao Liu · Changzhong Wu · Yahao Mao · Zongyan Deng · Mingxuan Ma · Huasen Xi · Yilong Liu · Yutong Wu · Xiaofeng Wang · Yang Wang · Yun Ye · Guan Huang · Xiaojie Jin · Zheng Zhu · Jiwen Lu
arXiv:2608.18234v3 Announce Type: replace-cross Abstract: Whole-body motion tracking policies turn a humanoid into a robust control interface: the teleoperator---or an upstream model---only supplies a coarse movement intent, while the low-level policy keeps the robot balanced and physically feasible. Existing trackers deliver this interface only on flat ground: trained in empty scenes, they never learn how contact with terrain and objects reshapes their dynamics, and they attempt to teach the policy to balance under any command by continually enlarging the reference-motion corpus, which stops working once feasible behaviors become environment-dependent. We present GigaBrain-WBC-0.5, the first Behavior World Model (BWM) for humanoid whole-body control. Rather than a purely reactive tracker, we train a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command, so the network that acts also models how the environment shapes what it can do next. An automatic terrain-annotation pipeline recovers full 3D contact geometry from retargeted motion, enabling terrain annotation at the scale of existing motion datasets. The predicted distribution is reused at deployment to detect implausible commands online and retract them onto learned behaviors, so the robot attempts tasks in a "best-effort" manner. The result is a unified policy that takes real-time command, interacts with environment, and stays robust to implausible commands, falls, and disturbances. GigaBrain-WBC-0.5 achieves the highest success rate across all four regimes among three large-scale tracker baselines: 81.3% on terrain interaction (4.3x the strongest baseline), 83.1% under implausible commands, and 99.3% fall recovery (16.8x the strongest baseline). Hardware trials show robust interaction under missing supports and disturbances; the Unitree G1 checkpoint transfers to the Maker L01 robot with simple fine-tuning.
  •  
  • ↗️
↗️

Deep learning combined habitat radiomics analysis of central lymph node metastasis in papillary thyroid carcinoma

✇npj Digital Medicine
By: Tianhan Zhou · Yang Zhou · Zhongkai Ni · Hao Fang · Fan Wu · Yangyang Xie · Xinyang Song · Sihan Sun · Xianfeng Wang · Xiangfeng Lin · Dong Guo · Lihua Hong · Xiaogang Qi · Chang Su · Jie Wang · Yu Chen · Quanbao Zhang · Jinwang Ding · Lei Xu · Hai Huang

npj Digital Medicine, Published online: 12 September 2026; doi:10.1038/s41746-026-03203-2

Deep learning combined habitat radiomics analysis of central lymph node metastasis in papillary thyroid carcinoma
  •  
  • ↗️
↗️

Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yiran Qiao · Feng Wang · Jing Ma
arXiv:2609.09418v1 Announce Type: new Abstract: World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although WAMs are rapidly advancing embodied AI, general-purpose counterparts remain largely unexplored in games. Existing game-oriented approaches often combine action-conditioned world models with external policies and reward functions to realize WAM-like decision-making, yet they operate mainly in 2D visual observation space and do not instantiate persistent 3D geometry. Extending this paradigm to 3D games introduces a distinct challenge. In autonomous driving and robotics, the physical environment exists independently of the model, providing a persistent 3D world in which selected actions can be executed. Games have no such external substrate; the virtual world itself must be instantiated. Most playable games require a persistent and navigable space, while 3D games additionally require explicit geometry that supports movement and interaction. Action-conditioned video rollouts provide visual observations but not this spatial representation. We present \textsc{Valerant}, a training-free framework that transforms a pretrained action-conditioned world model into a WAM for exploring and constructing 3D game maps. By coupling predictive visual rollouts with SLAM-based spatial reconstruction and exploration-driven action selection, \textsc{Valerant} progressively transforms a single image into a persistent 3D game map. This framework extends WAM-based interaction beyond 2D visual simulation and offers a new approach to reducing manual effort in 3D game-map creation.
  •  
  • ↗️
↗️

JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zixiang Chen · Yuheng Lu · Zihao Cheng · Zeming Liu · Jizeng Bai · Ziye Huang · Zhiyin Lin · Zihan Li · Yuhang Guo · Yunhong Wang · Haifeng Wang
arXiv:2609.10451v1 Announce Type: new Abstract: Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of agents' readiness for real-world usage. We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device workflows requiring coordinated interaction across heterogeneous platforms, including Android, Windows, and Ubuntu. Specifically, JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device workflows and dynamically evaluate agent performance within a unified framework. By evaluating agents in virtual environments spanning multiple operating systems, JarvisGUI reveals that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world workflows, exposing a critical capability gap invisible to existing benchmarks.
  •  
  • ↗️
↗️

Comparative Efficacy of Different AI Systems for Polyp Detection by Size During Colonoscopy: Systematic Review and Network Meta-Analysis

✇Journal of Medical Internet Research
By: Ling Ba · Yaxin Qi · Xinrui Lv · Sipu Wang · Lu Yang · Yufeng Wang · Bangmao Wang · Hailong Cao · Xin Xu
Background: Colorectal cancer remains a leading cause of death despite being largely preventable through polypectomy. AI systems designed to enhance polyp detection during colonoscopy have shown promise, but the extent to which they improve detection of different-sized polyps remains unclear. Objective: This study compared the size-stratified efficacy of AI-assisted colonoscopy vs standard colonoscopy using the Hartung-Knapp-Sidik-Jonkman (HKSJ) method, and generated exploratory rankings while acknowledging all cross-platform comparisons are indirect. Methods: This systematic review and network meta-analysis (NMA) searched PubMed, Embase, Cochrane CENTRAL, and Web of Science from inception to July 25, 2026, supplemented by citation searching. We included randomized controlled trials (RCTs) comparing AI-assisted vs standard colonoscopy in adults (≥18 years of age), reporting mean polyp detection counts stratified by size (≤5 mm, 6-9 mm, and ≥10 mm). Two reviewers screened studies, extracted data, and assessed risk of bias using the Cochrane Risk of Bias 2.0. We conducted frequentist NMA using the HKSJ method with restricted maximum likelihood estimation, calculated 95% prediction intervals (PIs), and assessed heterogeneity using I2 and τ2. Certainty of evidence was rated using the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) framework. Results: A total of 13 RCTs (4156 participants) compared 8 AI systems to standard colonoscopy, forming a network without direct AI comparisons. For diminutive polyps (≤5 mm), AI showed a modest advantage (standardized mean difference [SMD] 0.21, 95% CI 0.07 to 0.35, 95% PI –1.12 to 1.54), but substantial heterogeneity (I2=86.6%) and wide PI crossing the null indicated high uncertainty. EndoScreener showed the most consistent evidence (SMD 0.36, 95% CI 0.18-0.54). For small and large polyps, effects were minimal (SMD 0.02, 95% CI –0.02 to 0.06, 95% PI –0.03 to 0.07; SMD 0.01, 95% CI 0.00-0.02, 95% PI –0.01 to 0.03). GRADE certainty was very low for diminutive polyps and low for small and large polyps. Sensitivity analysis excluding Tianjin YuJin did not materially change findings. Conclusions: AI may modestly enhance diminutive polyp detection, but effects on small and large polyps are minimal, with no platform superiority. Given very low to low certainty, findings are hypothesis-generating. This exploratory NMA provides size-stratified comparisons that can inform future head-to-head trial design. Unlike prior reviews aggregating all polyp sizes, we show the overall AI benefit is driven by diminutive polyp detection, providing a framework for targeted deployment—prioritizing AI for diminutive polyp screening, with limited value for larger lesions. Head-to-head trials are urgently needed. Trial Registration: PROSPERO International Prospective Register of Systematic Reviews CRD420251266932; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251266932
  •  
  • ↗️
↗️

EMCN is associated with vascular-immune crosstalk and represents a potential biomarker in lung adenocarcinoma

✇Omics in Gastric
By: Yan Zhuang · Qingfeng Wang · Kaimin Wei · Fangjuan Wei · Xiaowei Yao · Yongliang Wang

Front Mol Biosci. 2026 Aug 12;13:1752442. doi: 10.3389/fmolb.2026.1752442. eCollection 2026.

ABSTRACT

BACKGROUND: While MUC family genes have been established as prognostic biomarkers in gastric cancer, and GWAS studies link EMCN mutations to chemotherapy-induced myelosuppression in NSCLC, the systematic characterization of EMCN in lung adenocarcinoma (LUAD) remains elusive.

METHODS: This multi-omics strategy combining bulk and single-cell transcriptomics study integrated differential expression analysis, WGCNA, and machine learning algorithms (LASSO/SVM-RFE/Random Forest) to identify EMCN as a diagnostic hub gene, followed by experimental validation using immunohistochemistry Western blot and qRT-PCR.

RESULTS: EMCN (Endomucin) is a sialomucin-like glycoprotein predominantly expressed in vascular endothelial cells. Using bulk transcriptomic datasets and single-cell RNA-seq analysis, we found that EMCN expression was reduced in lung adenocarcinoma (LUAD) compared with non-tumor controls and was primarily localized to the endothelial compartment. Survival analysis using the median expression cutoff showed that high EMCN expression was associated with improved overall survival (Cox HR_high vs. low = 0.73, p = 0.04), indicating that low EMCN expression correlates with poorer prognosis. Machine learning-based feature selection (LASSO, Random Forest, and SVM) further prioritized EMCN among consensus candidate genes, supporting its potential relevance to the vascular-associated tumor microenvironment in LUAD. EMCN expression levels also showed a significant positive correlation with the degree of immune cell infiltration. Gene set enrichment analysis (GSEA) revealed that high EMCN expression in tumor tissues activates negative regulatory pathways associated with angiogenesis. Receiver operating characteristic (ROC) curve analysis highlights EMCN's excellent diagnostic potential for LUAD, with an area under the curve (AUC) of 0.963. In vitro experiments confirm the downregulation of EMCN at both protein and mRNA levels, consistent with our bioinformatics predictions.

CONCLUSION: This first comprehensive study establishes EMCN as a dual-functional regulator of vascular-immune crosstalk in LUAD, providing both a molecular diagnostic tool and therapeutic target for precision oncology.

PMID:42656419 | PMC:PMC13506425 | DOI:10.3389/fmolb.2026.1752442

  •  
  • ↗️
↗️

Divide-and-Conquer Inference for Large-Scale Visual Recognition with Multimodal Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhipeng Ye · Jiaqi Huang · Feng Jiang · Qiufeng Wang · Yikang Duan · Dawei Wang · Xihang Zhou · Qian Qiao
arXiv:2605.24799v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a wide range of vision language tasks. However, when applied to large scale image classification, their performance degrades significantly as the label space expands a phenomenon we define as Performance Collapse in Long Sequence Recognition. Through an information theoretic analysis, we reveal that this collapse stems from a fundamental conflict between the escalating information entropy and the prominent attention dilution and decay within attention mechanisms, which impairs the model's ability to maintain a sufficient signal-to-noise ratio when processing extremely long prompts. To mitigate this, we propose Divide-and-Conquer Inference (DCI), a novel test-time scaling strategy for visual recognition with MLLMs. DCI recursively decomposes complex global classification tasks into multiple simpler, localized subproblems and employs a dynamic pruning mechanism to compress the search space. This method effectively improves the local signal to noise ratio and model accuracy by mitigating the inherent weight dilution issues in long-sequence inference. Moreover, while traditional self-attention incurs a prohibitive quadratic computational complexity, DCI achieves more favorable scaling behavior and substantially accelerates inference in large scale classification scenarios. Extensive experiments on benchmarks such as ImageNet-1K and ImageNet-21K demonstrate that DCI consistently improves classification accuracy. This enables lightweight open-source models to rival or even surpass frontier closed-source giants without any additional training or fine-tuning. As a model-agnostic, plug-and-play paradigm, DCI offers an efficient approach for scaling the inferential precision of MLLMs in large-scale scenarios.
  •  
  • ↗️
↗️

Subspace-Guided Semantic and Topological Invariant Registration for Annotation-Free Ultrasound Plane Quality Control

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chunzheng Zhu · Jianxin Lin · Feng Wang · Cheng Jiang · Guanghua Tan · Zhenyu Zhou · Shengli Li · Kenli Li
arXiv:2605.25396v1 Announce Type: cross Abstract: Reliable quality control (QC) of ultrasound images is essential for both real-time acquisition guidance and retrospective clinical audit, yet existing approaches rely heavily on per-plane annotations, or employ pseudo-labeling prone to systematic bias under spatial deformations inherent in clinical acquisition. We present STRIQ, a registration-driven framework that recasts annotation-free US plane quality control as a subspace-guided consistency measurement problem. Specifically, STRIQ introduces a Latent Registration Aligner (LRA) to establish hierarchical feature space correspondences between query images and variance-driven anchors, which are autonomously distilled from unlabeled data via a variance spectrum criterion to serve as structurally stable prototypes. To further disambiguate anatomical planes and mitigate negative knowledge transfer, we propose an Orthogonal Knowledge Subspace (OKS) module. The OKS decomposes plane-specific representations into mutually orthogonal subspaces, enabling fine-grained expert collaboration while preventing inter-plane interference, ensuring that the quality metric is grounded in principled subspace proximity. Extensive experiments on the in-house US4QA and public CAMUS datasets demonstrate that STRIQ achieves state-of-the-art correlation with clinical quality scores, establishing a new paradigm for annotation-free, real-time reliable ultrasound quality control. Our code is available at https://github.com/zhcz328/STRIQ.
  •  
  • ↗️
↗️

Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chunzheng Zhu · Yijun Wang · Jianxin Lin · Feng Wang · Hongwei Wang · Lei Zhao · Shengli Li · Kenli Li
arXiv:2605.25402v1 Announce Type: cross Abstract: Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the anatomical context for clinical-aligned representation learning. In this work, we propose an anatomy-anchored ultrasound self-supervision framework ANAUS that shifts representation learning from generic visual regions to clinically meaningful anatomical structures. Utilizing a learnable latent prompt engine alongside a one-time domain adaptation on existing public image--mask pairs, we empower the LP-SAM module to achieve annotation-free anatomy delineation at scale. Building upon this anatomical grounding, we propose a dual-policy self-supervised learning paradigm consisting of inter-view semantics-aware anatomy-separating alignment and contextual core-region prediction to enhance representation learning. Specifically, the former enforces feature invariance within identical anatomical regions while promoting discriminability across distinct structures; the latter compels the model to reconstruct corrupted regions, thereby capturing fine-grained structural details. Extensive evaluations on six public datasets demonstrate that \ours{} consistently outstrips current state-of-the-art methods while maintaining the computational efficiency essential for clinical deployment. Code is available at https://github.com/zhcz328/ANAUS.
  •  
  • ↗️
↗️

Advances in Yupingfeng San Research: Multi-Target Mechanisms and Clinical Evidence

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Shiyu Gao · Yanfang Wang · Xiaoya Li · Lin Zheng · Zhaoshuang Zhan · Jiafeng Wang

Drug Des Devel Ther. 2026 May 18;20:603491. doi: 10.2147/DDDT.S603491. eCollection 2026.

ABSTRACT

This review systematically summarizes the chemical composition, mechanisms of action, and recent progress in research and clinical applications of Yupingfeng San (YPFS) in various diseases. Research indicates that YPFS contains abundant active constituents-such as flavonoids, coumarins, and terpenoids, and demonstrates diverse biological activities,including immune modulation, anti-inflammatory, antiviral, antibacterial, and antitumor activities. Recent pharmacological and network pharmacology studies have elucidated that YPFS regulates key signaling pathways - such as PI3K-Akt, NF-κB, TLR4/MyD88, and JAK-STAT - through multi-target and multi-pathway mechanisms. These effects contribute to its therapeutic role in allergic rhinitis (AR), asthma, atopic dermatitis (AD), liver cancer, lung cancer, and other conditions. Although limited clinical trials and meta-analyses suggest that YPFS, when combined with conventional therapies, can improve treatment efficacy, relieve symptoms, and demonstrate good safety and tolerability, current research is constrained by low evidence quality and the absence of standardized quality control measures. Future research should prioritize large-scale, multi-center clinical trials and integrate multi-omics approaches to identify the main active components and mechanisms of action.

PMID:42182585 | PMC:PMC13196821 | DOI:10.2147/DDDT.S603491

  •  
  • ↗️
↗️

Advances in Yupingfeng San Research: Multi-Target Mechanisms and Clinical Evidence

✇Omics In Lung
By: Shiyu Gao · Yanfang Wang · Xiaoya Li · Lin Zheng · Zhaoshuang Zhan · Jiafeng Wang

Drug Des Devel Ther. 2026 May 18;20:603491. doi: 10.2147/DDDT.S603491. eCollection 2026.

ABSTRACT

This review systematically summarizes the chemical composition, mechanisms of action, and recent progress in research and clinical applications of Yupingfeng San (YPFS) in various diseases. Research indicates that YPFS contains abundant active constituents-such as flavonoids, coumarins, and terpenoids, and demonstrates diverse biological activities,including immune modulation, anti-inflammatory, antiviral, antibacterial, and antitumor activities. Recent pharmacological and network pharmacology studies have elucidated that YPFS regulates key signaling pathways - such as PI3K-Akt, NF-κB, TLR4/MyD88, and JAK-STAT - through multi-target and multi-pathway mechanisms. These effects contribute to its therapeutic role in allergic rhinitis (AR), asthma, atopic dermatitis (AD), liver cancer, lung cancer, and other conditions. Although limited clinical trials and meta-analyses suggest that YPFS, when combined with conventional therapies, can improve treatment efficacy, relieve symptoms, and demonstrate good safety and tolerability, current research is constrained by low evidence quality and the absence of standardized quality control measures. Future research should prioritize large-scale, multi-center clinical trials and integrate multi-omics approaches to identify the main active components and mechanisms of action.

PMID:42182585 | PMC:PMC13196821 | DOI:10.2147/DDDT.S603491

  •  
  • ↗️
↗️

Targeted Therapy-Induced Interstitial Lung Disease in NSCLC: Mechanisms, Clinical Signatures, and a Precision Medicine Roadmap

✇Omics In Lung
By: Jia-Feng Wang · Lei-Lei Jiang · Meng-Chuan Wang · Yang-Ling Li

Drug Des Devel Ther. 2026 Apr 8;20:600434. doi: 10.2147/DDDT.S600434. eCollection 2026.

ABSTRACT

Molecularly targeted therapies have transformed the therapeutic landscape of non-small cell lung cancer (NSCLC), establishing precision oncology as the foundation of modern disease management. However, these advances are increasingly complicated by drug-induced interstitial lung disease (DILD), a potentially life-threatening adverse event that can disrupt treatment continuity and compromise clinical benefit. In this review, we provide a comprehensive evaluation of interstitial lung disease associated with targeted agents in NSCLC, including oncogene-directed tyrosine kinase inhibitors, antibody-drug conjugates (ADCs), and angiogenesis inhibitors. We summarize reported differences in ILD incidence, onset timing, clinical manifestations, and radiographic characteristics across targeted agents, with particular emphasis on high-risk populations and the elevated ILD incidence observed with deruxtecan-based ADCs. We further summarize current mechanistic evidence suggesting that DILD may arise from multiple overlapping processes, including immune-mediated inflammatory activation, direct epithelial cytotoxicity, off-target kinase inhibition, and payload-dependent bystander injury. Finally, we discuss current challenges and future directions for improving pulmonary safety, including real-world datasets, multi-omics approaches, and emerging AI-assisted tools for earlier detection and risk stratification. Importantly, the current evidence base remains limited by the predominance of retrospective studies, case reports, and incomplete mechanistic validation. These insights may help guide safer and more sustained implementation of targeted therapies in NSCLC.

PMID:41978697 | PMC:PMC13070417 | DOI:10.2147/DDDT.S600434

  •  
  • ↗️
↗️

Automated Conjecture Resolution with Formal Verification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haocheng Ju · Guoxiong Gao · Jiedong Jiang · Bin Wu · Zeming Sun · Leheng Chen · Yutong Wang · Yuefeng Wang · Zichen Wang · Wanyi He · Peihao Wu · Liang Xiao · Ruochuan Liu · Bryan Dai · Bin Dong
arXiv:2604.03789v1 Announce Type: cross Abstract: Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capable performance on research-level problems. However, reliably solving and verifying such problems remains challenging due to the inherent ambiguity of natural language reasoning. In this paper, we propose an automated framework for tackling research-level mathematical problems that integrates natural language reasoning with formal verification, enabling end-to-end problem solving with minimal human intervention. Our framework consists of two components: an informal reasoning agent, Rethlas, and a formal verification agent, Archon. Rethlas mimics the workflow of human mathematicians by combining reasoning primitives with our theorem search engine, Matlas, to explore solution strategies and construct candidate proofs. Archon, equipped with our formal theorem search engine LeanSearch, translates informal arguments into formalized Lean 4 projects through structured task decomposition, iterative refinement, and automated proof synthesis, ensuring machine-checkable correctness. Using this framework, we automatically resolve an open problem in commutative algebra and formally verify the resulting proof in Lean 4 with essentially no human involvement. Our experiments demonstrate that strong theorem retrieval tools enable the discovery and application of cross-domain mathematical techniques, while the formal agent is capable of autonomously filling nontrivial gaps in informal arguments. More broadly, our work illustrates a promising paradigm for mathematical research in which informal and formal reasoning systems, equipped with theorem retrieval tools, operate in tandem to produce verifiable results, substantially reduce human effort, and offer a concrete instantiation of human-AI collaborative mathematical research.
  •  
  • ↗️
↗️

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yang Zhou · Xiaofeng Wang · Hao Shao · Letian Wang · Guosheng Zhao · Jiangnan Shao · Jiagang Zhu · Tingdong Yu · Zheng Zhu · Guan Huang · Steven L. Waslander
arXiv:2604.01765v1 Announce Type: cross Abstract: Recently, world-action models (WAM) have emerged to bridge vision-language-action (VLA) models and world models, unifying their reasoning and instruction-following capabilities and spatio-temporal world modeling. However, existing WAM approaches often focus on modeling 2D appearance or latent representations, with limited geometric grounding-an essential element for embodied systems operating in the physical world. We present DriveDreamer-Policy, a unified driving world-action model that integrates depth generation, future video generation, and motion planning within a single modular architecture. The model employs a large language model to process language instructions, multi-view images, and actions, followed by three lightweight generators that produce depth, future video, and actions. By learning a geometry-aware world representation and using it to guide both future prediction and planning within a unified framework, the proposed model produces more coherent imagined futures and more informed driving actions, while maintaining modularity and controllable latency. Experiments on the Navsim v1 and v2 benchmarks demonstrate that DriveDreamer-Policy achieves strong performance on both closed-loop planning and world generation tasks. In particular, our model reaches 89.2 PDMS on Navsim v1 and 88.7 EPDMS on Navsim v2, outperforming existing world-model-based approaches while producing higher-quality future video and depth predictions. Ablation studies further show that explicit depth learning provides complementary benefits to video imagination and improves planning robustness.
  •  
  • ↗️
↗️

Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model

✇cs.AI, q-bio.NC updates on arXiv.org
By: Siyuan Du · Siyi Li · Shuwei Bai · Ang Li · Haolin Li · Mingqing Xiao · Yang Pan · Dongsheng Li · Weidi Xie · Yanfeng Wang · Ya Zhang · Chencheng Zhang · Jiangchao Yao
arXiv:2603.29176v1 Announce Type: new Abstract: Parkinson's disease (PD) affects over ten million people worldwide. Although temporal interference (TI) and deep brain stimulation (DBS) are promising therapies, inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost. Previous explorations either resort to limited statistical biomarkers that are insufficient to characterize variability, or employ AI-driven methods which is prone to overfitting and opacity. We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI. Critically, a generative virtual brain foundation model, pretrained on a collective dataset (2707 subjects, 5621 sessions) to capture universal disorder patterns, was finetuned on PD cohorts receiving TI (n=51) or DBS (n=55) to yield individualized virtual brains with high fidelity to empirical functional connectivity (r=0.935). By constructing counterfactual estimations between pathological and healthy neural states within these personalized models, we predicted clinical responses (TI: AUPR=0.853; DBS: AUPR=0.915), substantially outperforming baselines. External and prospective validations (n=14, n=11) highlight the feasibility of clinical translation. Moreover, our framework provides state-dependent regional patterns linked to response, offering hypothesis-generating mechanistic insights.
  •  
  • ↗️
↗️

UniCA: Unified Covariate Adaptation for Time Series Foundation Model

✇cs.AI, q-bio.NC updates on arXiv.org
By: Lu Han · Yu Liu · Lan Li · Qiwen Deng · Jian Jiang · Yinbo Sun · Zhe Yu · Binfeng Wang · Xingyu Lu · Lintao Ma · Han-Jia Ye · De-Chuan Zhan
arXiv:2506.22039v2 Announce Type: replace-cross Abstract: Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their ability to handle general forecasting tasks involving diverse and often heterogeneous covariates -- such as categorical variables and multimodal data (e.g., images, text) -- which are typically task-specific and difficult to leverage during pretraining. To address this gap, we propose Unified Covariate Adaptation (UniCA), a framework to bridge TSFMs with general covariate-aware forecasting. UniCA first performs covariate homogenization to transform heterogeneous covariates into high-level homogeneous series representations and then fuses them via a unified attention-based fusion mechanism. UniCA is compatible and universal for adaptation with both homogeneous and heterogeneous covariates, incorporating extra covariate information while preserving the generalization ability of TSFMs.Extensive experiments on multiple unimodal and multimodal covariate-aware forecasting benchmarks demonstrate the superiority of UniCA, highlighting the promise of covariate-aware TSFM adaptation in real-world forecasting scenarios.Code: https://github.com/hanlu-nju/UniCA.
  •  
  • ↗️
↗️

Research on the compatibility mechanism of the Tingli Dazao Xiefei Decoction by multi-organ metabolomics strategy

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Rui-Feng Wang · Pei-Pei Yuan · Long Chen · Zhen-Kai Zhang · Bing-Xian Zhang · Lin Chen · Shu-Miao Yuan · Yan-Fang Zhao · Ning Zhou · Xiao-Ke Zheng · Wei-Sheng Feng

J Ethnopharmacol. 2026 Mar 21:121548. doi: 10.1016/j.jep.2026.121548. Online ahead of print.

ABSTRACT

ETHNOPHARMACOLOGICAL RELEVANCE: The Tingli Dazao Xiefei Decoction (TD) is a traditional phlegm-eliminating prescription composed of Descurainia sophia (L.) Webb. ex Prantl (TLZ) and Ziziphus jujuba Mill. (DZ), which can relieve lung, heart and kidney injury in asthma. TLZ acts as the monarch drug in the TD. Based on the research mode of "material basis of traditional Chinese medicinal properties can be divided and combined", we have confirmed that the flavonoid glycosides components /the oligosaccharide components/the fatty oil component (FG/Oli/FO) are effective components of TLZ. However, the compatibility mechanism of the TD, and the contribution of the effective components of TLZ to the efficacy were still unclear.

AIM OF THE STUDY: To clarify the compatibility mechanism of TD, and the contribution of the effective components of TLZ to the efficacy from a comprehensive perspective of lung, heart, and kidney.

METHODS: First, we chose the asthma model corresponding to the efficacy of TD in purging the lungs and relieving asthma, and the rats were divided into the normal (NC) group, model (M) group, dexamethasone (DEX) group, and treatment groups of TD/TLZ/DZ/FO+DZ/Oli+DZ/FG+DZ. Second, metabolomics and network pharmacology were applied to elucidate the comprehensive protective effect of TD/FG+DZ/Oli+DZ/FO+DZ. Third, the multi-omics results were validated using Western blotting, RT-qPCR, flow cytometry, and immunofluorescence.

RESULTS: FO+DZ/Oli+DZ/FG+DZ had different degrees of protective effects against lung/heart/kidney injury in asthma. In metabolomics research, the principal component analysis (PCA) and cluster analysis results showed that the TLZ group was closer to TD group than DZ group, the FO+DZ and Oli+DZ group clustered with TD/NC groups in the lung and kidney, and the FO+DZ and FG+DZ group clustered with TD/NC groups in the heart. Pathway enrichment analysis suggested that the comprehensive protective effect of TLZ and its effective components combined with DZ on lung/heart/kidney may be achieved by regulating the arginine and proline metabolism, alanine, aspartate and glutamate metabolism, and unsaturated fatty acid biosynthesis. Multi-organ metabolomics and network pharmacology revealed consistent biological functions in KEGG pathways. Validation experiment showed that TLZ and its effective components combined with DZ could reverse the abnormal expression of proteins and RNA related to inflammation, airway remodeling, excitotoxicity, and energy-supply, apoptosis at different levels. Furthermore, FO+DZ may reduce asthma damage by inhibiting the FABP4/PPAR-γ/NF-κB signaling pathway.

CONCLUSION: TLZ played the key role in TD, and FO had the best therapeutic effect on each organ; the efficacy of Oli was mainly reflected in reducing lung and kidney damage, and FG was mainly involved in enhancing energy metabolism in the heart. These findings proved that traditional Chinese medicine could exert comprehensive efficacy in a 'multi-components trigger multi-channel' way.

PMID:41871629 | DOI:10.1016/j.jep.2026.121548

  •  
  • ↗️
❌