❌

Normal view

Received β€” 27 May 2026 ⏭

ADMFormer: An Adaptive-Decomposition Transformer with Time-Varying Masked Spatial Attention for Traffic Forecasting

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Ruiwen Gu Β· Qitai Tan Β· Yahao Liu Β· Xiao-Ping Zhang
26 May 2026 at 12:00
arXiv:2605.25543v1 Announce Type: new Abstract: Accurate traffic forecasting is essential for intelligent transportation systems, supporting a wide range of real-world applications. However, it remains challenging due to two key factors:~(1) Traffic series contain heterogeneous temporal patterns, where stable periodic regularities coexist with event-driven fluctuations. Existing methods often treat them within a unified representation, limiting their ability to capture fine-grained temporal dynamics.~(2)Spatial dependencies among nodes are inherently dynamic and sparse, while dense all-pairs attention often introduces redundant interactions and amplifies noise. To address these issues, we propose ADMFormer, an Adaptive-Decomposition Transformer with Time-Varying Masked Spatial Attention. Specifically, ADMFormer first employs a time-node adaptive gating mechanism to decouple traffic signals into dominant regularities and residual fluctuations that vary across time and nodes. A dual-branch temporal module is then designed to separately capture global periodic dependencies and high-frequency irregular variations from these two decomposed components. Furthermore, ADMFormer introduces a time-varying masked spatial attention that sparsifies spatial interactions based on real-time traffic states, thereby effectively preserving dynamic and informative dependencies. Extensive experiments on four real-world datasets demonstrate that ADMFormer achieves state-of-the-art performance.

PHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Ruiwen Gu Β· Yahao Liu Β· Zhenyu Liu Β· Qitai Tan Β· Xiao-Ping Zhang
26 May 2026 at 12:00
arXiv:2605.25554v1 Announce Type: new Abstract: As a core task in intelligent transportation systems, traffic forecasting plays a critical role in urban traffic management. Accurate traffic forecasting relies on modeling complex spatiotemporal dependencies, which is inherently challenging due to spatial heterogeneity in traffic systems.Despite significant progress, most existing methods are still limited to pairwise spatial dependency modeling, making it difficult to capture dynamic high-order interactions among nodes with similar traffic patterns. To address this issue, we propose PHGNet, a novel spatiotemporal forecasting framework based on prototype-guided hypergraph construction. At the core of PHGNet, a prototype learning mechanism is designed to adaptively assign pattern-similar nodes to hyperedges, thereby capturing high-order interactions with time-varying structures. To improve the reliability of dynamic hypergraph construction, we further develop a global-local node representation module to extract time-consistent features. For forecasting, iterative residual refinement and Temporal Query Attention are introduced to improve forecasting accuracy while supporting efficient parallel decoding. Extensive experiments on multiple real-world datasets demonstrate that PHGNet achieves superior predictive performance compared with state-of-the-art methods.

Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Ziyi Ding Β· Xiao-Ping Zhang
26 May 2026 at 12:00
arXiv:2605.25891v1 Announce Type: cross Abstract: We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed linear probe recovers the evidence-supported answer from the model's hidden state (accuracy approximately 0.97), while the spoken Yes/No reverts to the commonsense one (accuracy approximately 0.5). We call this approximately +0.5 gap Causal Tongue-Tie: a wrong Yes/No decomposes into two separable failure modes: no internal signal versus a signal the verbal interface cannot say. The implication cuts both ways for output-only causal benchmarks: a benchmark "correct" need not mean the model has understood, and a benchmark "wrong" need not mean it cannot. Sweeping claims about whether LLMs can do causal reasoning, drawn from a single accuracy number, deserve a second look.

VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yinghao Wu Β· Zhuoyan Luo Β· Yiyao Yu Β· Zhaojian Yu Β· Yujiu Yang Β· Xiao-Ping Zhang
26 May 2026 at 12:00
arXiv:2605.25952v1 Announce Type: cross Abstract: Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information capacity and density of visual tokens. Addressing this limitation, we propose VEN-VL, a visual ensemble MoE framework for effective and efficient perception following the enrich then compact principle. Specifically, we first enrich the information capacity by unifying the visual representations of different perspectives, and then progressively compact it with adaptive routers in specialized visual experts to enhance the information density. Furthermore, we incorporate the reconstruction ability of vanilla structure via explicit visual supervision, facilitating crucial information preservation. Experimental results demonstrate our superiority in complex visual tasks with few information-condensed tokens, which effectively bridges the gap between performance and efficiency.

Multimodal data-driven prediction of postoperative recurrence and survival in hepatocellular carcinoma: a narrative review

βœ‡Omics in Hepatocellular
By: Ping Zhang Β· Xurui Kang Β· Yunzhang Cheng Β· Yun Feng Β· Yilin Wang
22 May 2026 at 18:00

J Gastrointest Oncol. 2026 Apr 30;17(2):96. doi: 10.21037/jgo-2025-aw-848. Epub 2026 Mar 27.

ABSTRACT

BACKGROUND AND OBJECTIVE: Hepatocellular carcinoma (HCC) is characterized by high postoperative recurrence rates and poor long-term survival despite advances in surgical and systemic therapies. Accurate prediction of postoperative recurrence and survival risk is critical for individualized surveillance, adjuvant treatment selection, and precision management. With the rapid development of artificial intelligence (AI) and medical informatics, multimodal data-driven models integrating clinical, imaging, pathological, and omics information have emerged as a promising paradigm. This narrative review aims to systematically summarize recent advances in multimodal prediction models for postoperative recurrence and survival in HCC, compare modeling strategies and fusion approaches, and discuss current challenges and future directions for clinical translation.

METHODS: A narrative literature review was conducted by searching PubMed, Web of Science, and Google Scholar for studies published between 2020 and 2025. Articles focusing on postoperative recurrence or survival prediction in HCC using single-modal or multimodal data were included. Relevant studies were identified using keywords related to HCC, multimodal data, AI, machine learning, deep learning, recurrence, and prognosis.

KEY CONTENT AND FINDINGS: This review summarizes commonly used data modalities, including clinical variables, medical imaging, pathological features, and multi-omics data, and outlines their respective strengths and limitations. Conventional statistical models and AI-based approaches, including non-deep learning and deep learning algorithms, are compared. Particular emphasis is placed on multimodal fusion strategies at the feature level and decision level, with discussion of their methodological characteristics and suitable clinical scenarios. Overall, multimodal models consistently demonstrate superior predictive performance compared with single-modality approaches. However, key challenges remain, including data heterogeneity, limited interpretability of complex models, insufficient external validation, and the predominance of static baseline modeling.

CONCLUSIONS: Multimodal data-driven prediction models represent a promising strategy for improving postoperative risk stratification and personalized management in HCC. While current evidence highlights their potential advantages over traditional prognostic tools, broader clinical adoption is hindered by methodological limitations and a lack of standardized frameworks. Future research should focus on longitudinal multimodal modeling, multi-center prospective validation, and enhanced model interpretability to facilitate integration into clinical workflows and inform precision oncology-oriented decision-making.

PMID:42169935 | PMC:PMC13187996 | DOI:10.21037/jgo-2025-aw-848

Integrating clinical and multiomics evidence based on disease module theory: deciphering the comorbidity network of psoriasis vulgaris via the Ising model for mechanistic insights

βœ‡Pulmonary nodule
By: Dongwen Shi Β· Yuan Luo Β· Ping Zhang Β· Bin Liang Β· Mengmeng Wang Β· Hong Cai Β· Xiaowen Pang
30 April 2026 at 18:00

Front Immunol. 2026 Apr 14;17:1744789. doi: 10.3389/fimmu.2026.1744789. eCollection 2026.

ABSTRACT

Psoriasis vulgaris (PV), a chronic immune-mediated inflammatory dermatosis, is associated with a significant burden of systemic comorbidities. Traditional comorbidity research methods struggle to reveal its complex interconnectedness. Based on large-scale retrospective cohort data, we constructed a PV comorbidity network using the Ising model from statistical physics. Weighted network centrality analysis was used to identify core and hub nodes and elucidate shared molecular mechanisms at the multiomics level (nontargeted proteomics and lipid peroxidation metabolomics). Finally, the impact of IL-17A inhibition (IL-17Ai) on PV and atherosclerosis (assessed by carotid Doppler color ultrasound) was evaluated using a prospective intervention study. The Ising model identified atherosclerosis- coronary heart disease (CHD) as the core comorbidity (degree centrality >10), with pulmonary nodules, hypertension, and fatty liver serving as key hub nodes (betweenness centrality >60). Multiomics analysis revealed a core molecular mechanism in PV, involving immune inflammation, oxidative stress, lipid metabolism disorder, and coagulation abnormalities, where the oxidative stress molecule GPX3 acts as a critical hub. Following IL-17Ai intervention, both skin lesions and early atherosclerosis markers significantly improved, accompanied by downregulation of the proinflammatory peripheral blood factor S100A9 and upregulation of anti-inflammatory lipid peroxidation metabolites (e.g., 17(R)-RVD1). This study systematically revealed the modular hierarchical structure of PV comorbidities at the network topology and molecular mechanism levels, confirming the central role of the IL-17 signaling pathway in driving the comorbidity network. This conclusion was further clinically validated by IL-17Ai intervention outcomes. This research provides theoretical and clinical evidence for early identification, prioritized management, and "one drug, multiple targets" therapeutic strategies for treating PV comorbidities.

PMID:42058202 | PMC:PMC13121148 | DOI:10.3389/fimmu.2026.1744789

Received β€” 8 April 2026 ⏭

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Zhiping Zhang Β· Yi Evie Zhang Β· Freda Shi Β· Tianshi Li
7 April 2026 at 12:00
arXiv:2510.04465v2 Announce Type: replace-cross Abstract: LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and the effectiveness of personalization. Yet the expanded design space of agent autonomy also presents opportunities to shape these effects, which remain underexplored. We conducted a $3\times3$ between-subjects experiment ($N=450$) to study how agent autonomy level influences personalization's effects on users' privacy concerns, trust, and willingness to use, as well as the underlying psychological processes. We find that risk-contingent autonomy, where the agent delegates control to users upon detecting potential privacy leakage, through improving users' perceived control, attenuates personalization's adverse effects by reducing the increase in privacy concerns and the decrease in trust. Our results suggest that designing $\textbf{agent's autonomy}$ that supports $\textbf{human autonomy}$ (both in terms of perceived control and oversight effectiveness) helps users benefit from personalization without being deterred by growing privacy concerns, contributing to the development of trustworthy LLM agents.
There are no more articles
❌