❌

Normal view

Received — 10 September 2026 ⏭

DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sean Bin Yang · Hao Miao · Zongyi Xu · Jilin Hu · Xiangmeng Wang · Hua Lu · Bin Yang · Christian S. Jensen
10 September 2026 at 12:00
arXiv:2609.07316v2 Announce Type: replace Abstract: Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation systems. Although existing self-supervised approaches have achieved promising performance, their dependence on deterministic contrastive learning paradigms and handcrafted view augmentation strategies inherently restricts their cross-scenario generalization capabilities. To address these limitations, we present DGCPath, an innovative Distribution-aware Generative Contrastive learning framework for Path representation. This framework establishes a synergistic connection between generative modeling and distributional contrastive learning, enabling the acquisition of robust and transferable feature embeddings. Specifically, our framework incorporates: (1) a diffusion-based view generator that autonomously produces semantically coherent yet diverse trajectory views from Gaussian noise; (2) a variational contrastive mechanism that enforces latent feature alignment at the distribution level, transcending conventional instance-wise consistency; and (3) a novel generative cross-supervision module that reinforces view-level consistency through cross-view reconstruction learning. Comprehensive evaluations on three real-world trajectory datasets demonstrate that DGCPath outperforms state-of-the-art baselines on two distinct downstream tasks, validating its enhanced generalization capability and representation effectiveness.
Received — 27 May 2026 ⏭

GLP1-E2 therapy delays autoimmune diabetes in late-stage prediabetic NOD mice and potentiates low-dose anti-CD3 therapy for enhanced disease protection

✇(Multiomics OR Omics) AND (Pancreatic)
By: Laure Degroote · Jędrzej Chrzanowski · Pierre Lemaitre · Amber Wouters · Stephanie Bourgeois · Annelore Van Mulders · Julie Pierreux · Sophie Coenen · Lien Willems · Gunter Leuckx · Marijke Viaene · Marc Packbier · Jonathan D Douros · Bin Yang · Yves Heremans · Chantal Mathieu · Willem Staels · Conny Gysemans · Nico De Leu
18 May 2026 at 18:00

Diabetologia. 2026 May 18. doi: 10.1007/s00125-026-06750-1. Online ahead of print.

ABSTRACT

AIMS/HYPOTHESIS: Anti-CD3 monoclonal antibody (aCD3) delays progression to stage 3 type 1 diabetes in high-risk individuals by modulating autoimmune activity. Nevertheless, responses remain variable and transient, with therapy providing only indirect beta cell protection. We investigated whether glucagon-like peptide-1-17ß-oestradiol conjugate (GLP1-E2), a beta cell-targeted fusion compound that enhances beta cell survival and function, could potentiate a short low-dose aCD3 course in preventing autoimmune diabetes in NOD mice. We hypothesised that co-targeting immune dysregulation and beta cell fragility would provide complementary and potentially synergistic benefits, resulting in more durable protection than either monotherapy.

METHODS: Female late-stage prediabetic NOD mice were randomised into four groups: untreated controls, aCD3 monotherapy, GLP1-E2 monotherapy and combination therapy. aCD3 was administered intravenously at 2.5 µg/day for 5 consecutive days, while GLP1-E2 was given subcutaneously at 100 nmol kg-1 day-1 for 18 weeks. Mice were monitored longitudinally for diabetes onset. The pancreas was analysed by spatial transcriptomics and immunostaining to assess immune infiltration, beta cell integrity and molecular pathway alterations.

RESULTS: At 30 weeks of age, diabetes incidence was 77% in untreated controls, 66% in mono aCD3-treated mice and 61% in mono GLP1-E2-treated mice. Combination therapy significantly reduced diabetes incidence to 38% (p≤0.001) and delayed disease onset by 6 weeks, with sustained protection persisting for 5 weeks after treatment cessation. GLP1-E2 monotherapy reduced islet immune cell infiltration to a similar extent as aCD3 mono- and combination therapy, without affecting peripheral lymphocyte counts. Spatial transcriptomics showed increased gene responses linked to beta cell stress (Hspa5, Eif2ak3, Xbp1, Ddit3), dedifferentiation (Cd81), 'disallowed' genes (Oat, Igfbp4), antigen presentation (H2-K1, H2-Q6, H2-Ab1, H2-Eb1) and inflammation (Cxcl10, Cxcl9, Ccl5) during disease progression. These processes were attenuated by mono- and combination therapy, with aCD3 mostly restoring beta cell identity and GLP1-E2 reducing beta cell stress and immunogenicity. Staining for CD81 and TUNEL in 17-week-old treated mice revealed levels comparable to 12-week-old normoglycaemic NOD mice, while being increased in 17-week-old untreated mice. This reduced beta cell dedifferentiation and death was associated with improved beta cell protection and better preservation of beta cell mass at 26.5 weeks compared with new-onset (diabetic) mice.

CONCLUSIONS/INTERPRETATION: Low-dose aCD3 or GLP1-E2 monotherapy delayed diabetes onset and preserved beta cell mass in female NOD mice, while the combination provided substantially superior protection. Simultaneously targeting immune dysregulation and beta cell vulnerability highlights the potential of combination therapy to enhance and prolong immunotherapeutic efficacy in type 1 diabetes.

PMID:42149241 | DOI:10.1007/s00125-026-06750-1

Received — 2 April 2026 ⏭

ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jindong Tian · Yifei Ding · Ronghui Xu · Hao Miao · Chenjuan Guo · Bin Yang
1 April 2026 at 12:00
arXiv:2510.09734v2 Announce Type: replace-cross Abstract: Weather forecasting is a fundamental task in spatiotemporal data analysis, with broad applications across a wide range of domains. Existing data-driven forecasting methods typically model atmospheric dynamics over a fixed short time interval, e.g., 6 hours, and rely on naive autoregression-based rollout for long-term forecasting, e.g., 5 days. However, this paradigm suffers from two key limitations: (1) it often inadequately models the spatial and multi-scale temporal dependencies inherent in global weather systems, and (2) the rollout strategy struggles to balance error accumulation with the capture of fine-grained atmospheric variations. In this study, we propose ARROW, an Adaptive-Rollout Multi-scale temporal Routing method for Global Weather Forecasting. To contend with the first limitation, we construct a multi-interval forecasting model that forecasts weather across different time intervals. Within the model, the Shared-Private Mixture-of-Experts captures both shared patterns and specific characteristics of atmospheric dynamics across different time scales, while Ring Positional Encoding accurately encodes the circular latitude structure of the Earth when representing spatial information. For the second limitation, we develop an adaptive rollout scheduler based on reinforcement learning, which selects the most suitable time interval to forecast according to the current weather state. Experimental results demonstrate that ARROW achieves state-of-the-art performance in global weather forecasting, establishing a promising paradigm in this field.
Received — 17 March 2026 ⏭

FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xin Xu · Weilong Li · Wei Liu · Wenke Huang · Zhixi Yu · Bin Yang · Xiaoying Liao · Kui Jiang
16 March 2026 at 12:00
arXiv:2603.12912v1 Announce Type: cross Abstract: Federated Domain Generalization for Person Re-Identification (FedDG-ReID) learns domain-invariant representations from decentralized data. While Vision Transformer (ViT) is widely adopted, its global attention often fails to distinguish pedestrians from high similarity backgrounds or diverse viewpoints -- a challenge amplified by cross-client distribution shifts in FedDG-ReID. To address this, we propose Federated Body Distribution Aware Visual Prompt (FedBPrompt), introducing learnable visual prompts to guide Transformer attention toward pedestrian-centric regions. FedBPrompt employs a Body Distribution Aware Visual Prompts Mechanism (BAPM) comprising: Holistic Full Body Prompts to suppress cross-client background noise, and Body Part Alignment Prompts to capture fine-grained details robust to pose and viewpoint variations. To mitigate high communication costs, we design a Prompt-based Fine-Tuning Strategy (PFTS) that freezes the ViT backbone and updates only lightweight prompts, significantly reducing communication overhead while maintaining adaptability. Extensive experiments demonstrate that BAPM effectively enhances feature discrimination and cross-domain generalization, while PFTS achieves notable performance gains within only a few aggregation rounds. Moreover, both BAPM and PFTS can be easily integrated into existing ViT-based FedDG-ReID frameworks, making FedBPrompt a flexible and effective solution for federated person re-identification. The code is available at https://github.com/leavlong/FedBPrompt.
Received — 11 March 2026 ⏭

GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhengyu Li · Xiangfei Qiu · Yuhan Zhu · Xingjian Wu · Jilin Hu · Chenjuan Guo · Bin Yang
10 March 2026 at 12:00
arXiv:2603.08032v1 Announce Type: cross Abstract: Exogenous variables offer valuable supplementary information for predicting future endogenous variables. Forecasting with exogenous variables needs to consider both past-to-future dependencies (i.e., temporal correlations) and the influence of exogenous variables on endogenous variables (i.e., channel correlations). This is pivotal when future exogenous variables are available, because they may directly affect the future endogenous variables. Many methods have been proposed for time series forecasting with exogenous variables, focusing on modeling temporal and channel correlations. However, most of them use a two-step strategy, modeling temporal and channel correlations separately, which limits their ability to capture joint correlations across time and channels. Furthermore, in real-world scenarios, time series are frequently affected by various forms of noises, underscoring the critical importance of robustness in such correlations modeling. To address these limitations, we propose GCGNet, a Graph-Consistent Generative Network for time series forecasting with exogenous variables. Specifically, GCGNet first employs a Variational Generator to produce coarse predictions. A Graph Structure Aligner then further guides it by evaluating the consistency between the generated and true correlations, where the correlations are represented as graphs, and are robust to noises. Finally, a Graph Refiner is proposed to refine the predictions to prevent degeneration and improve accuracy. Extensive experiments on 12 real-world datasets demonstrate that GCGNet outperforms state-of-the-art baselines.
Received — 25 February 2026 ⏭

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xingjian Wu · Xvyuan Liu · Junkai Lu · Siyuan Wang · Xiangfei Qiu · Yang Shu · Jilin Hu · Chenjuan Guo · Bin Yang
24 February 2026 at 13:00
arXiv:2602.14681v2 Announce Type: replace-cross Abstract: LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.
Received — 17 February 2026 ⏭

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xingjian Wu · Xvyuan Liu · Junkai Lu · Siyuan Wang · Yang Shu · Jilin Hu · Chenjuan Guo · Bin Yang
17 February 2026 at 13:00
arXiv:2602.14681v1 Announce Type: cross Abstract: LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.
There are no more articles
❌