❌

Normal view

Received — 27 May 2026 ⏭

$M^3-Verse$: A "Spot the Difference" Challenge for Large Multimodal Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kewei Wei · Bocheng Hu · Jie Cao · Xiaohan Chen · Zhengxi Lu · Wubing Xia · Weili Xu · Jiaao Wu · Junchen He · Mingyu Jia · Ciyun Zhao · Ye Sun · Yizhi Li · Zhonghan Zhao · Jian Zhang · Gaoang Wang
26 May 2026 at 12:00
arXiv:2512.18735v2 Announce Type: replace-cross Abstract: Modern Large Multimodal Models (LMMs) have demonstrated extraordinary ability in static image and single-state spatial-temporal understanding. However, their capacity to comprehend the dynamic changes of objects within a shared spatial context between two distinct video observations, remains largely unexplored. This ability to reason about transformations within a consistent environment is particularly crucial for advancements in the field of spatial intelligence. In this paper, we introduce $M^3-Verse$, a Multi-Modal, Multi-State, Multi-Dimensional benchmark, to formally evaluate this capability. It is built upon paired videos that provide multi-perspective observations of an indoor scene before and after a state change. The benchmark contains a total of 270 scenes and 2,932 questions, which are categorized into over 50 subtasks that probe 4 core capabilities. We evaluate 16 state-of-the-art LMMs and observe their limitations in tracking state transitions. To address these challenges, we further propose a simple yet effective baseline that achieves significant performance improvements in multi-state perception. $M^3-Verse$ thus provides a challenging new testbed to catalyze the development of next-generation models with a more holistic understanding of our dynamic visual world. You can get the construction pipeline from https://github.com/Wal-K-aWay/M3-Verse_pipeline and full benchmark data from https://www.modelscope.cn/datasets/WalKaWay/M3-Verse.
Received — 13 April 2026 ⏭

Spatial multi-omics unveils the monoclonal origin, neuroendocrine plasticity, and microenvironment niches in combined small-cell lung cancer

✇Omics In Lung
By: Zhuo Wang · Qing Luo · Jie Wu · Li Lu · Wenjie Ding · Yichun Zhao · Yongfeng Yu · Ruoran Qiu · Ling Zhu · Xinxing Ouyang · Wendi Xuzhang · Shun Lu · Wei Wei · Qihui Shi · Ziming Li
12 April 2026 at 18:00

Cell Rep Med. 2026 Apr 10:102741. doi: 10.1016/j.xcrm.2026.102741. Online ahead of print.

ABSTRACT

Combined small-cell lung cancer (cSCLC) is an aggressive subtype of SCLC with mixed histologic components. Despite heterogeneity and poorer prognosis than de novo SCLC, cSCLC is managed as SCLC because molecular insight into biology, lineage plasticity, and tumor microenvironment (TME) is limited. We perform spatial whole-exome sequencing, spatial transcriptomics, and single-nucleus RNA sequencing across 19 treatment-naive cSCLC tumors. Different histologic components share a monoclonal origin, whereas divergence associates with distinct mutation and copy-number alteration patterns. Our results define spatially exclusive or interspersed tumor domains with distinct TME and immune landscapes; fibroblast-rich boundaries enriched for an aggressive fibroblast subtype may shape TME and treatment responses. We identify lineage plasticity, including adenocarcinoma-to-SCLC transdifferentiation and SCLC-subtype coexistence, and develop cSCLC Detector, a sensitive mutation-based assay improving cSCLC detection in tissue and liquid biopsies. These findings illuminate cSCLC evolution and heterogeneity, underscoring the need for tailored diagnostic and therapeutic strategies for this aggressive subtype.

PMID:41966692 | DOI:10.1016/j.xcrm.2026.102741

Spatial multi-omics unveils the monoclonal origin, neuroendocrine plasticity, and microenvironment niches in combined small-cell lung cancer

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Zhuo Wang · Qing Luo · Jie Wu · Li Lu · Wenjie Ding · Yichun Zhao · Yongfeng Yu · Ruoran Qiu · Ling Zhu · Xinxing Ouyang · Wendi Xuzhang · Shun Lu · Wei Wei · Qihui Shi · Ziming Li
12 April 2026 at 18:00

Cell Rep Med. 2026 Apr 10:102741. doi: 10.1016/j.xcrm.2026.102741. Online ahead of print.

ABSTRACT

Combined small-cell lung cancer (cSCLC) is an aggressive subtype of SCLC with mixed histologic components. Despite heterogeneity and poorer prognosis than de novo SCLC, cSCLC is managed as SCLC because molecular insight into biology, lineage plasticity, and tumor microenvironment (TME) is limited. We perform spatial whole-exome sequencing, spatial transcriptomics, and single-nucleus RNA sequencing across 19 treatment-naive cSCLC tumors. Different histologic components share a monoclonal origin, whereas divergence associates with distinct mutation and copy-number alteration patterns. Our results define spatially exclusive or interspersed tumor domains with distinct TME and immune landscapes; fibroblast-rich boundaries enriched for an aggressive fibroblast subtype may shape TME and treatment responses. We identify lineage plasticity, including adenocarcinoma-to-SCLC transdifferentiation and SCLC-subtype coexistence, and develop cSCLC Detector, a sensitive mutation-based assay improving cSCLC detection in tissue and liquid biopsies. These findings illuminate cSCLC evolution and heterogeneity, underscoring the need for tailored diagnostic and therapeutic strategies for this aggressive subtype.

PMID:41966692 | DOI:10.1016/j.xcrm.2026.102741

Received — 8 April 2026 ⏭

Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hang Fan · Haoran Pei · Runze Liang · Weican Liu · Long Cheng · Wei Wei
7 April 2026 at 12:00
arXiv:2604.04145v1 Announce Type: new Abstract: Photovoltaic (PV) power forecasting plays a critical role in power system dispatch and market participation. Because PV generation is highly sensitive to weather conditions and cloud motion, accurate forecasting requires effective modeling of complex spatiotemporal dependencies across multiple information sources. Although recent studies have advanced AI-based forecasting methods, most fail to fuse temporal observations, satellite imagery, and textual weather information in a unified framework. This paper proposes Solar-VLM, a large-language-model-driven framework for multimodal PV power forecasting. First, modality-specific encoders are developed to extract complementary features from heterogeneous inputs. The time-series encoder adopts a patch-based design to capture temporal patterns from multivariate observations at each site. The visual encoder, built upon a Qwen-based vision backbone, extracts cloud-cover information from satellite images. The text encoder distills historical weather characteristics from textual descriptions. Second, to capture spatial dependencies across geographically distributed PV stations, a cross-site feature fusion mechanism is introduced. Specifically, a Graph Learner models inter-station correlations through a graph attention network constructed over a K-nearest-neighbor (KNN) graph, while a cross-site attention module further facilitates adaptive information exchange among sites. Finally, experiments conducted on data from eight PV stations in a northern province of China demonstrate the effectiveness of the proposed framework. Our proposed model is publicly available at https://github.com/rhp413/Solar-VLM.
Received — 4 April 2026 ⏭

MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms

✇cs.AI, q-bio.NC updates on arXiv.org
By: Isabelle Diana May-Xin Ng · Tharindu Cyril Weerasooriya · Haitao Zhu · Wei Wei
3 April 2026 at 12:00
arXiv:2512.04097v2 Announce Type: replace-cross Abstract: In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. Our results show that MultiGA produces high accuracy across multiple benchmarks, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal.

Ferritin aggregation cell engager for CAR T avidity engineering against refractory leukemias

✇Cell
By: Feng Li · Yuxing Hu · Yan Wang · Xiao Zhang · Shaowei Qiu · Xiaoming Hu · Wenjing Wang · Shuang Wang · Peilin Guo · Cui Song · Huaiji Wang · Changhao He · Jie Sun · Di Yu · Shuhua Yi · Jun Wei · Feifan Liu · Caopei Zheng · Jianxiang Wang · Yuhua Li · Guanghui Ma · Wei Wei
9 March 2026 at 08:00
Li et al. developed a ferritin aggregation cell engager that helps CAR T cells better recognize and attack leukemia cells without re-engineering the CAR itself. This versatile platform overcomes antigen modulation and enables combination with chemotherapy.
Received — 26 March 2026 ⏭

Towards intelligent and miniaturized drug delivery devices

✇Nature - Issue - nature.com science feeds
By: Xinwei Wei · John B. Buse · Hongming Chen · Tejal A. Desai · Molly M. Stevens · Giovanni Traverso · Robert Langer · Zhen Gu
25 March 2026 at 08:00

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10221-3

Intelligent and miniaturized drug delivery devices leveraging advances in biotechnology, artificial intelligence, electronics and materials science enable treatments with increased precision and responsiveness, with applications in cancer, diabetes, cardiovascular disease and other diseases.
Received — 17 March 2026 ⏭

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenqi Liu · Yunxiao Wang · Shijie Ma · Meng Liu · Qile Su · Tianke Zhang · Haonan Fan · Changyi Liu · Kaiyu Jiang · Jiankang Chen · Kaiyu Tang · Bin Wen · Fan Yang · Tingting Gao · Han Li · Yinwei Wei · Xuemeng Song
16 March 2026 at 12:00
arXiv:2602.07801v3 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.
Received — 14 March 2026 ⏭

Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingbo Yang · Bairu Hou · Wei Wei · Yujia Bao · Shiyu Chang
10 March 2026 at 12:00
arXiv:2603.07915v1 Announce Type: new Abstract: Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable reasoning levels (e.g., high/medium/low), static strategies are often ineffective: using low-effort modes at every step leads to significant performance degradation, while random selection fails to preserve accuracy or provide meaningful cost reduction. However, agents should reserve high reasoning effort for difficult steps like navigating complex website structures, while using lower-effort modes for simpler steps like opening a target URL. In this paper, we propose Ares, a framework for per-step dynamic reasoning effort selection tailored for multi-step agent tasks. Ares employs a lightweight router to predict the lowest appropriate reasoning level for each step based on the interaction history. To train this router, we develop a data generation pipeline that identifies the minimum reasoning effort required for successful step completion. We then fine-tune the router to predict these levels, enabling plug-and-play integration for any LLM agents. We evaluate Ares on a diverse set of agent tasks, including TAU-Bench for tool use agents, BrowseComp-Plus for deep-research agents, and WebArena for web agents. Experimental results show that Ares reduces reasoning token usage by up to 52.7% compared to fixed high-effort reasoning, while introducing minimal degradation in task success rates.
Received — 11 March 2026 ⏭

CRTAM inhibition mitigates toxicity of immune checkpoint inhibitors without antitumor efficacy trade-off

✇Nature Cancer
By: Si-Cong Ma · Zi-Xuan Rong · Zi-Peng Xu · Yan-Pei Zhang · Kui-Mao Zhuang · Hao Sun · Chuan-Hui Cao · Ze-Nan Wu · Hai-Peng Zhang · Qiang Zuo · Jia-Run Lin · Jia-Xin Cheng · Hua-Ting Qu · Duan-Duan Han · Wei Wei · Ke Liu · Xiao-Ting Cai · Ze-Qin Guo · Xue Bai · Li Liu · De-Hua Wu · Zhong-Yi Dong
5 March 2026 at 08:00

Nature Cancer, Published online: 05 March 2026; doi:10.1038/s43018-026-01135-0

Dong and colleagues report that blockade of T cell-expressed cytotoxic and regulatory T cell molecule results in selective mitigation of immune-related toxicities without affecting antitumor efficacy of immune checkpoint inhibitors.
Received — 5 March 2026 ⏭

HumanLM: Simulating Users with State Alignment Beats Response Imitation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shirley Wu · Evelyn Choi · Arpandeep Khatua · Zhanghan Wang · Joy He-Yueya · Tharindu Cyril Weerasooriya · Wei Wei · Diyi Yang · Jure Leskovec · James Zou
5 March 2026 at 13:00
arXiv:2603.03303v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to simulate how specific users respond to a given context, enabling more user-centric applications that rely on user feedback. However, existing user simulators mostly imitate surface-level patterns and language styles, which fail to reflect the underlying states of real users (e.g., beliefs and emotions). To address these limitations, we propose a novel training framework, HumanLM, which builds user simulators that accurately reflect real users. Our key insight is that, in addition to generating responses, the model should generate natural-language latent states that align with ground-truth responses through reinforcement learning. These latent states correspond to a set of psychologically grounded state dimensions that drive how real users respond. HumanLM further synthesizes these aligned latent states into responses that accurately represent real users. For extensive evaluation, we develop Humanual, a comprehensive benchmark for simulating real users based on public data. Humanual consists of six large-scale datasets with 26k users and 216k responses in total, spanning diverse tasks such as generating user responses to daily life issues, political blogs, and chat sessions with LLM assistants. Across datasets, HumanLM significantly outperforms alternative approaches, achieving an average relative improvement of 16.3% in alignment scores from an LLM judge. In a real-time simulation study with 111 participants, HumanLM achieves the highest similarity to real user responses and competitive human-likeness scores.

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenqi Liu · Yunxiao Wang · Shijie Ma · Meng Liu · Qile Su · Tianke Zhang · Haonan Fan · Changyi Liu · Kaiyu Jiang · Jiankang Chen · Kaiyu Tang · Bin Wen · Fan Yang · Tingting Gao · Han Li · Yinwei Wei · Xuemeng Song
4 March 2026 at 13:00
arXiv:2602.07801v2 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.
There are no more articles
❌