❌

Normal view

Received — 18 November 2025 ⏭ Favourites

Rethinking Bias in Generative Data Augmentation for Medical AI: a Frequency Recalibration Method

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chi Liu · Jincheng Liu · Congcong Zhu · Minghao Wang · Sheng Shen · Jia Gu · Tianqing Zhu · Wanlei Zhou
18 November 2025 at 13:00
arXiv:2511.12301v1 Announce Type: cross Abstract: Developing Medical AI relies on large datasets and easily suffers from data scarcity. Generative data augmentation (GDA) using AI generative models offers a solution to synthesize realistic medical images. However, the bias in GDA is often underestimated in medical domains, with concerns about the risk of introducing detrimental features generated by AI and harming downstream tasks. This paper identifies the frequency misalignment between real and synthesized images as one of the key factors underlying unreliable GDA and proposes the Frequency Recalibration (FreRec) method to reduce the frequency distributional discrepancy and thus improve GDA. FreRec involves (1) Statistical High-frequency Replacement (SHR) to roughly align high-frequency components and (2) Reconstructive High-frequency Mapping (RHM) to enhance image quality and reconstruct high-frequency details. Extensive experiments were conducted in various medical datasets, including brain MRIs, chest X-rays, and fundus images. The results show that FreRec significantly improves downstream medical image classification performance compared to uncalibrated AI-synthesized samples. FreRec is a standalone post-processing step that is compatible with any generative model and can integrate seamlessly with common medical GDA pipelines.
Received — 14 November 2025 ⏭ Favourites

Stereo-seq V2: Spatial mapping of total RNA on FFPE sections with high resolution

✇Cell
By: Yu Zhao · Young Li · Ying He · Junqi Wu · Yi Liu · Xinxing Li · Zhaoxun Li · Qiaomei Yuan · Jialuo Li · Xinya Zhang · Xiaole Hu · Guifang Wu · Ying Qiu · Jie Yuan · Xin Huang · Mengru Xu · Mei Yang · Jing Guo · Tingting Cao · Qiuling Chen · Dandan Li · Jiajun Zhang · Xiaoxi Zhou · Xia Jiang · Fan Zhu · Xuan Dong · Rong Xiang · Hailin Pan · Lei Han · Ziqing Deng · Haohao Deng · Yan Zhang · Maoyuan Liu · Qin Wu · Gaoyang Wang · Jie Zhai · Weihong Tan · Xiawei Liu · Zehao Wang · Shanshan Li · Tianbi Duan · Longqi Liu · Ao Chen · Haiying Liu · Chang Chen · Sha Liao · Xun Xu
28 August 2025 at 08:00
Stereo-seq V2 facilitates single-cell-resolution spatial RNA mapping in FFPE samples through random primer capture, uncovering ncRNAs, host-pathogen transcriptome profiling, and spatial immune repertoires in situ.
Received — 11 November 2025 ⏭ Favourites

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chao Zhang · Yuhao Wang · Derong Xu · Haoxin Zhang · Yuanjie Lyu · Yuhao Chen · Shuochen Liu · Tong Xu · Xiangyu Zhao · Yan Gao · Yao Hu · Enhong Chen
10 November 2025 at 13:00
arXiv:2511.05385v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning processes. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, TeaRAG improves the average Exact Match by 4% and 2% while reducing output tokens by 61% and 59% on Llama3-8B-Instruct and Qwen2.5-14B-Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG.

Know What You Don't Know: Uncertainty Calibration of Process Reward Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Young-Jin Park · Kristjan Greenewald · Kaveh Alim · Hao Wang · Navid Azizan
10 November 2025 at 13:00
arXiv:2506.09338v2 Announce Type: replace-cross Abstract: Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated. Specifically, they tend to overestimate the success probability that a partial reasoning step will lead to a correct final answer, particularly when smaller LLMs are used to complete the reasoning trajectory. To address this, we present a calibration approach -- performed via quantile regression -- that adjusts PRM outputs to better align with true success probabilities. Leveraging these calibrated success estimates and their associated confidence bounds, we introduce an \emph{instance-adaptive scaling} (IAS) framework that dynamically adjusts the compute budget based on the estimated likelihood that a partial reasoning trajectory will yield a correct final answer. Unlike conventional methods that allocate a fixed number of reasoning trajectories per query, this approach adapts to each instance and reasoning step when using our calibrated PRMs. Experiments on mathematical reasoning benchmarks show that (i) our PRM calibration method achieves small calibration error, outperforming the baseline methods, (ii) calibration is crucial for enabling effective IAS, and (iii) the proposed IAS strategy reduces inference costs while maintaining final answer accuracy, utilizing less compute on more confident problems as desired.
Received — 28 October 2025 ⏭ Favourites

A full life cycle biological clock based on routine clinical data and its impact in health and diseases

✇Nature Medicine
By: Kai Wang · Fei Liu · Wei Wu · Changxi Hu · Xian Shen · Meihao Wang · Gen Li · Fanxin Zeng · Li Liu · Io Nam Wong · Sian Liu · Zixing Zou · Bingzhou Li · Jinghang Li · Xiaoying Huang · Shengwei Jin · Zhuomin Li · Hui Xu · Gang Chen · Xiaodong Chen · Ying Zhu · Ping Li · Zhe Feng · Winston Wang · Linling Cheng · Mingqi Yang · Qiang Hou · Wenyang Lu · Yiwen Sun · Kun Li · Tian Zhong · Zhuo Sun · Yun Yin · Alexandre Loupy · Eric Oermann · Xiangmei Chen · Kang Zhang · Manson Fok · Taiwa Hou · Lei Guo · Miaosang Xu · Dan Yao · Chengjing Wang · Pingzhen Yang · Caiwen Ou · Xueqiang Wang · Aimin Wu
27 October 2025 at 08:00

Nature Medicine, Published online: 27 October 2025; doi:10.1038/s41591-025-04006-w

The biological clock model LifeClock predicts biological age across all life stages from routine clinical data, revealing distinct pediatric and adult disease risk patterns.
Received — 24 October 2025 ⏭ Favourites

FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenhao Wang · Kehe Ye · Xinyu Zhou · Tianxing Chen · Cao Min · Qiaoming Zhu · Xiaokang Yang · Yongjian Shen · Yang Yang · Maoqing Yao · Yao Mu
24 October 2025 at 12:00
arXiv:2510.20774v1 Announce Type: cross Abstract: Large-scale and diverse datasets are vital for training robust robotic manipulation policies, yet existing data collection methods struggle to balance scale, diversity, and quality. Simulation offers scalability but suffers from sim-to-real gaps, while teleoperation yields high-quality demonstrations with limited diversity and high labor cost. We introduce FieldGen, a field-guided data generation framework that enables scalable, diverse, and high-quality real-world data collection with minimal human supervision. FieldGen decomposes manipulation into two stages: a pre-manipulation phase, allowing trajectory diversity, and a fine manipulation phase requiring expert precision. Human demonstrations capture key contact and pose information, after which an attraction field automatically generates diverse trajectories converging to successful configurations. This decoupled design combines scalable trajectory diversity with precise supervision. Moreover, FieldGen-Reward augments generated data with reward annotations to further enhance policy learning. Experiments demonstrate that policies trained with FieldGen achieve higher success rates and improved stability compared to teleoperation-based baselines, while significantly reducing human effort in long-term real-world data collection. Webpage is available at https://fieldgen.github.io/.
Received — 1 September 2025 ⏭ Favourites

Stereo-seq V2: Spatial mapping of total RNA on FFPE sections with high resolution

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yu Zhao · Young Li · Ying He · Junqi Wu · Yi Liu · Xinxing Li · Zhaoxun Li · Qiaomei Yuan · Jialuo Li · Xinya Zhang · Xiaole Hu · Guifang Wu · Ying Qiu · Jie Yuan · Xin Huang · Mengru Xu · Mei Yang · Jing Guo · Tingting Cao · Qiuling Chen · Dandan Li · Jiajun Zhang · Xiaoxi Zhou · Xia Jiang · Fan Zhu · Xuan Dong · Rong Xiang · Hailin Pan · Lei Han · Ziqing Deng · Haohao Deng · Yan Zhang · Maoyuan Liu · Qin Wu · Gaoyang Wang · Jie Zhai · Weihong Tan · Xiawei Liu · Zehao Wang · Shanshan Li · Tianbi Duan · Longqi Liu · Ao Chen · Haiying Liu · Chang Chen · Sha Liao · Xun Xu
29 August 2025 at 18:00

Cell. 2025 Aug 22:S0092-8674(25)00922-5. doi: 10.1016/j.cell.2025.08.008. Online ahead of print.

ABSTRACT

Performing total RNA profiling on formalin-fixed, paraffin-embedded (FFPE) samples, the predominant sample conservation method in clinical practice, remains challenging for current spatial transcriptomics techniques. Here, we introduce Stereo-seq V2, which employs random primers to capture and sequence RNAs in situ on FFPE sections and provides single-cell resolution. The random-priming-based strategy offers unbiased transcript capturing and uniform gene body coverage, which increase the sensitivity to marker genes, the efficiency of non-polyadenylation (poly(A)) RNA profiling, and immune repertoire coverage. We demonstrated the robust performance of Stereo-seq V2 on clinical FFPE samples using triple-negative breast cancer (TNBC) sections and identified tumor-specific alternative splicing events. In a Mycobacterium tuberculosis (Mtb)-infected mouse model, we monitored gene expression dynamics of host and pathogen transcriptomes simultaneously by utilizing Stereo-seq V2. We also assembled immune repertoires and identified Mtb-specific BCR clones, which could also be observed in human tuberculous lung samples. These results highlight Stereo-seq V2's potential in biomedical research and personalized medicine.

PMID:40882628 | DOI:10.1016/j.cell.2025.08.008

Received — 25 August 2025 ⏭ Favourites
Received — 6 April 2025 ⏭ Favourites

Treatment of advanced-stage non-small cell lung cancer: Current progress and a glimpse into the future (Review)

✇Omics In Lung
By: Zeming Wang · Guoying Cai · Junquan Zhu · Juchao Wang · Yufeng Zhang
31 March 2025 at 18:00

Mol Clin Oncol. 2025 Mar 12;22(5):42. doi: 10.3892/mco.2025.2837. eCollection 2025 May.

ABSTRACT

Before the twentieth century, patients with advanced lung cancer had limited treatment options and chemotherapy was the primary form of treatment, with an overall survival often <0.5 years. However, with advances in society and medical technology, the treatment approaches for advanced non-small cell lung cancer (NSCLC) have markedly changed. Traditional chemotherapy has been gradually replaced by targeted therapy and immunotherapy, leading to the emergence of various new therapeutic options that offer patients more personalized and precise care. This raises the question of what the future holds for the treatment of NSCLC. This review provides a comprehensive analysis of the latest breakthroughs in targeted therapies, immunotherapies, and drugs for antibody-drug conjugates (ADCs), highlights advances in multimodal combination therapy strategies, and explores the causes of resistance and the challenges that exist in overcoming it. In particular, this review provides unique insights into key directions for future research in NSCLC, such as personalised treatment strategies and biomarker exploration based on multi-omics data, aiming to provide new inspiration for clinical decision-making and research.

PMID:40160297 | PMC:PMC11948471 | DOI:10.3892/mco.2025.2837

There are no more articles
❌