MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding

3 December 2025 at 13:00

arXiv:2512.02906v1 Announce Type: cross Abstract: Understanding high-resolution images remains a significant challenge for multimodal large language models (MLLMs). Recent study address this issue by dividing the image into smaller crops and computing the semantic similarity between each crop and a query using a pretrained retrieval-augmented generation (RAG) model. The most relevant crops are then selected to localize the target object and suppress irrelevant information. However, such crop-based processing can fragment complete objects across multiple crops, thereby disrupting the computation of semantic similarity. In our experiments, we find that image crops of objects with different sizes are better handled at different resolutions. Based on this observation, we propose Multi-resolution Retrieval-Detection (MRD), a training-free framework for high-resolution image understanding. To address the issue of semantic similarity bias caused by objects being split across different image crops, we propose a multi-resolution semantic fusion method, which integrates semantic similarity maps obtained at different resolutions to produce more accurate semantic information and preserve the integrity of target objects. Furthermore, to achieve direct localization of target objects at a global scale, we introduce an open-vocalbulary object detection (OVD) model that identifies object regions using a sliding-window approach.Experiments on high-resolution image understanding benchmarks using different MLLMs demonstrate the effectiveness of our approach.

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

cs.AI, q-bio.NC updates on arXiv.org

By: Yueqi Song · Ketan Ramaneti · Zaid Sheikh · Ziru Chen · Boyu Gou · Tianbao Xie · Yiheng Xu · Danyang Zhang · Apurva Gandhi · Fan Yang · Joseph Liu · Tianyue Ou · Zhihao Yuan · Frank Xu · Shuyan Zhou · Xingyao Wang · Xiang Yue · Tao Yu · Huan Sun · Yu Su · Graham Neubig

29 October 2025 at 12:00

arXiv:2510.24702v1 Announce Type: cross Abstract: Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying data sources, but that a large variety of data is fragmented across heterogeneous formats, tools, and interfaces. To this end, we introduce the agent data protocol (ADP), a light-weight representation language that serves as an "interlingua" between agent datasets in diverse formats and unified agent training pipelines downstream. The design of ADP is expressive enough to capture a large variety of tasks, including API/tool use, browsing, coding, software engineering, and general agentic workflows, while remaining simple to parse and train on without engineering at a per-dataset level. In experiments, we unified a broad collection of 13 existing agent training datasets into ADP format, and converted the standardized ADP data into training-ready formats for multiple agent frameworks. We performed SFT on these data, and demonstrated an average performance gain of ~20% over corresponding base models, and delivers state-of-the-art or near-SOTA performance on standard coding, browsing, tool use, and research benchmarks, without domain-specific tuning. All code and data are released publicly, in the hope that ADP could help lower the barrier to standardized, scalable, and reproducible agent training.

Integrative multi-omics profiling deciphers tumor microenvironment heterogeneity and immunotherapy vulnerabilities in lung neuroendocrine carcinomas

(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)

By: Zicheng Zhang · Modi Zhai · Siqi Bao · Xujie Sun · Ruanqi Chen · Bingning Wang · Fan Yang · Lin Yang · Meng Zhou

13 June 2025 at 18:00

J Adv Res. 2025 Jun 11:S2090-1232(25)00427-8. doi: 10.1016/j.jare.2025.06.017. Online ahead of print.

ABSTRACT

INTRODUCTION: Lung neuroendocrine carcinomas (Lu-NECs) are rare, highly aggressive lung tumors with poor prognosis and limited therapeutic options. Understanding the tumor immune microenvironment (TIME) is crucial towards personalized therapeutic strategies.

OBJECTIVES: This study aims to systematically characterize the heterogeneity and complexity of the TIME in Lu-NECs by integrating proteomic, transcriptomic, and genomic data.

METHODS: We performed comprehensive immune-proteomic profiling of 76 Lu-NECs across diverse histopathological subtypes to elucidate intra-tumoral TIME heterogeneity at the proteomic level. Validation was conducted in multiple independent cohorts, including 112 Lu-NECs using immunohistochemistry, 147 Lu-NECs, and 17 small cell lung carcinoma samples using transcriptomics. We integrated proteomic, transcriptomic, genomic, and clinical data to assess molecular, immunological, and clinical features, as well as therapeutic vulnerabilities across different immune subtypes.

RESULTS: We delineated the immuno-proteomic landscape of Lu-NECs and identified two major immuno-proteomic clusters with distinct immunological, molecular, and clinical characteristics. IPC1 was characterized by high immune cell infiltration, while IPC2 exhibited sparse immune cell presence. Genomic analysis revealed distinct mutational patterns, with IPC1 showing a higher incidence of APOBEC-associated mutation signatures and IPC2 being enriched for mutations associated with defective DNA mismatch repair and tobacco-related mutagens. Functional analyses indicated that IPC1 was related to immune and oncogenic signaling activity, whereas IPC2 was associated with cancer stemness and proliferation-related features. Furthermore, IPC1 and IPC2 demonstrated histological subtype-specific clinical benefits from postoperative chemotherapy. Finally, we developed a machine learning model (iPROM) to predict Lu-NECs immune classification and improve risk stratification, which was validated across multiple independent cohorts.

CONCLUSIONS: This study advances the understanding of the tumor immune microenvironment in Lu-NECs through multi-omics characterization and highlights potential personalized therapeutic vulnerabilities tailored to the specific immune landscapes of Lu-NECs.

PMID:40513660 | DOI:10.1016/j.jare.2025.06.017

An organoid co-culture model for probing systemic anti-tumor immunity in lung cancer

(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)

By: Kaiyi Li · Chang Liu · Xizhao Sui · Chao Li · Ting Zhang · Tian Zhao · Dong Zhang · Hainan Wu · Yuhan Liu · Shuai Wang · Yingshun Yang · Baobao Lin · Wenyan Wang · Fan Yang · Xiaofang Chen · Peng Liu

13 June 2025 at 18:00

Cell Stem Cell. 2025 Jun 6:S1934-5909(25)00191-2. doi: 10.1016/j.stem.2025.05.011. Online ahead of print.

ABSTRACT

Deciphering interactions between tumor micro- and systemic immune macroenvironments is essential for developing more effective cancer diagnosis and therapeutic strategies. Here, we established a gel-liquid interface (GLI) co-culture model of lung cancer organoids (LCOs) and paired peripheral-blood mononuclear cells (PBMCs), featuring enhanced interactions between immune cells and tumor organoids for optimized simulation of in vivo systemic anti-tumor immunity. By constructing a cohort of lung cancer patients, we demonstrated that the responses of GLI models under αPD1 treatment reflected the immunotherapy outcomes of the corresponding patients precisely. Furthermore, we dissected the various tumor immune processes mediated by PBMC-derived T cells within GLI models through functional multi-omics analyses, along with the characterization of circulating tumor-reactive T cells (GNLY⁺CD44⁺CD9⁺) with effector memory-like phenotypes as a potential indicator of immunotherapy efficacy. Our findings indicate that the GLI co-culture model can be used to develop diagnostic strategies for precision immunotherapies, as well as understanding the underlying mechanisms.

PMID:40513558 | DOI:10.1016/j.stem.2025.05.011

Reading view