❌

Normal view

Received — 27 May 2026 ⏭

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiahao Huo · Wenjie Qu · Yibo Yan · Kening Zheng · Jiaheng Zhang · Xuming Hu · Philip S. Yu · Mingxun Zhou
26 May 2026 at 12:00
arXiv:2605.25796v1 Announce Type: cross Abstract: Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark signals by changing sentence order. In this work, we propose SAMark, a self-anchored watermarking framework that removes the dependency on sentence order by establishing a step-independent green region in semantic space. To improve detectability, we introduce a multi-channel hyperbolic scoring mechanism that amplifies watermark signals while suppressing noise from weakly aligned candidates. We further propose a diversity-aware filtering strategy that combines hard filtering with soft regularization, extending beyond simple n-gram repetition filters to address semantic redundancy. Experimental results show that SAMark achieves up to 90.2% TP@FP1% under typical paragraph-level paraphrasing attacks, outperforming the strongest prior baseline by more than 30% on average, while maintaining generation quality competitive with unwatermarked text and breaking the robustness-quality trade-off that limits prior methods.

The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xingyu Lyu · Qianqian Xu · Zhiyong Yang · Peisong Wen · Qingming Huang
26 May 2026 at 12:00
arXiv:2605.20749v2 Announce Type: replace-cross Abstract: Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, yet the underlying reasons for this advantage remain unclear. In this work, we study GLU by analyzing two-layer networks in the neural tangent kernel (NTK) regime. Our analysis reveals that the GLU structure reshapes the NTK spectrum, leading to a smaller condition number and a more compact eigenvalue distribution. Building on this finding, we further analyze the resulting training dynamics and show how the reshaped spectrum leads to faster convergence of GLU models, including a characteristic loss-crossing phenomenon observed between GLU and non-GLU models. Finally, we empirically observe that GLU has limited impact in reducing the generalization gap on various models, including ViT and GPT-2, suggesting that its primary benefit lies in accelerating optimization rather than reducing the generalization gap. The code is available at: https://github.com/Zemdalk/GLU-NTK.
Received — 8 April 2026 ⏭

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kening Zheng · Wei-Chieh Huang · Jiahao Huo · Zhonghao Li · Henry Peng Zou · Yibo Yan · Xin Zou · Jungang Li · Junzhuo Li · Hanrong Zhang · Xuming Hu · Philip S. Yu
7 April 2026 at 12:00
arXiv:2604.03592v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps remain poorly understood. In this work, we conduct a systematic analysis of expert routing patterns in MoE models, revealing a phenomenon we term Language Routing Isolation, in which high- and low-resource languages tend to activate largely disjoint expert sets. Through layer-stratified analysis, we further show that routing patterns exhibit a layer-wise convergence-divergence pattern across model depth. Building on these findings, we propose RISE (Routing Isolation-guided Subnetwork Enhancement), a framework that exploits routing isolation to identify and adapt language-specific expert subnetworks. RISE applies a tripartite selection strategy, using specificity scores to identify language-specific experts in shallow and deep layers and overlap scores to select universal experts in middle layers. By training only the selected subnetwork while freezing all other parameters, RISE substantially improves low-resource language performance while preserving capabilities in other languages. Experiments on 10 languages demonstrate that RISE achieves target-language F1 gains of up to 10.85% with minimal cross-lingual degradation.
Received — 4 April 2026 ⏭

AeroTherm-GPT: A Verification-Centered LLM Framework for Thermal Protection System Engineering Workflows

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chuhan Qiao · Jinglai Zheng · Jie Huang · Buyue Zhao · Fan Li · Haiming Huang
3 April 2026 at 12:00
arXiv:2604.01738v1 Announce Type: new Abstract: Integrating Large Language Models (LLMs) into hypersonic thermal protection system (TPS) design is bottlenecked by cascading constraint violations when generating executable simulation artifacts. General-purpose LLMs, treating generation as single-pass text completion, fail to satisfy the sequential, multi-gate constraints inherent in safety-critical engineering workflows. To address this, we propose AeroTherm-GPT, the first TPS-specialized LLM Agent, instantiated through a Constraint-Closed-Loop Generation (CCLG) framework. CCLG organizes TPS artifact generation as an iterative workflow comprising generation, validation, CDG-guided repair, execution, and audit. The Constraint Dependency Graph (CDG) encodes empirical co-resolution structure among constraint categories, directing repair toward upstream fault candidates based on lifecycle ordering priors and empirical co-resolution probabilities. This upstream-priority mechanism resolves multiple downstream violations per action, achieving a Root-Cause Fix Efficiency of 4.16 versus 1.76 for flat-checklist repair. Evaluated on HyTPS-Bench and validated against external benchmarks, AeroTherm-GPT achieves 88.7% End-to-End Success Rate (95% CI: 87.5-89.9), a gain of +12.5 pp over the matched non-CDG ablation baseline, without catastrophic forgetting on scientific reasoning and code generation tasks.

Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chongjie Ye · Cheng Cao · Chuanyu Pan · Yiming Hao · Yihao Zhi · Yuanming Hu · Xiaoguang Han
3 April 2026 at 12:00
arXiv:2604.02289v1 Announce Type: cross Abstract: Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D imagery, high-quality 3D assets are scarce, making 3D synthesis under-constrained. Existing methods often rely on indirect pipelines that edit in 2D and lift results into 3D via optimization, sacrificing geometric consistency. We present Omni123, a 3D-native foundation model that unifies text-to-2D and text-to-3D generation within a single autoregressive framework. Our key insight is that cross-modal consistency between images and 3D can serve as an implicit structural constraint. By representing text, images, and 3D as discrete tokens in a shared sequence space, the model leverages abundant 2D data as a geometric prior to improve 3D representations. We introduce an interleaved X-to-X training paradigm that coordinates diverse cross-modal tasks over heterogeneous paired datasets without requiring fully aligned text-image-3D triplets. By traversing semantic-visual-geometric cycles (e.g., text to image to 3D to image) within autoregressive sequences, the model jointly enforces semantic alignment, appearance fidelity, and multi-view geometric consistency. Experiments show that Omni123 significantly improves text-guided 3D generation and editing, demonstrating a scalable path toward multimodal 3D world models.

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 ⏭

Androgen activity in the male embryonic hindbrain drives lethal PFA ependymoma

✇Nature - Issue - nature.com science feeds
By: Jiao Zhang · Winnie Ong · Alexandra Rasnitsyn · Ricardo Daniel Gonzalez · Rodrigo Lopez Gutierrez · Polina Balin · Amr Saadeldin · Xiaochong Wu · Maria C. Vladoiu · Vicente Santa-Maria Lopez · Fernando Gonzalez-Salinas · Navneesh Yadav · Dinesh Mohanakrishnan · Kannan Boosi Narayana Rao · Raja Gopal Reddy Mooli · Hinda Najem · Sebastian Pacheco · Kaitlin Kharas · Cory Richman · David Przelicki · Evan Y. Wang · Haipeng Su · Rachel Naomi Curry · Runze Yang · Michelle Masayo Kameda-Smith · Bryn Livingston · David Scott · Zaili Luo · Mingyang Xia · Namal Abeysundara · Anders W. Erickson · Ncedile Mankahla · Lucas ZhongMing Hu · Chu Pan · Raul Suarez · Ning Huang · Yihao Wu · Hao Wang · Tajana Douglas · Jonelle Pallota · Steven Hébert · Karen Ng · Krystin Mantione · Heather Whetstone · Hassaan Maan · Hussein Lakkis · Juyeun Lee · Sadeesh K. Ramakrishnan · Yanxin Pei · Yujie Tang · Frank Y. Lin · Guillermo Aldave · Marco Gallo · Robert M. Friedlander · Faiyaz Notta · Laura K. Donovan · Murali Chintagumpala · Bo Wang · Yun Li · Daniel D. De Carvalho · Zhaolei Zhang · Ying M
25 March 2026 at 08:00

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10264-6

Androgen activity in the male embryonic hindbrain prolongs hindbrain differentiation in male individuals and drives sex differences in the incidence and prognosis of posterior fossa type A (PFA) ependymoma, an aggressive childhood brain tumour.

Dual Antitumor Effects of Solanum incanum L. in Lung and Colonic Adenocarcinomas via TRAIL-Mediated Extrinsic Apoptotic Pathway: A Network Pharmacology and Multi-Omics Investigation

✇Omics In Lung
By: Chih-Ting Lin · Li-Ren Yeh · Jiun-Ting Wu · Chao-Ming Hung · Chang-Yin Lee
21 March 2026 at 18:00

Curr Med Chem. 2026 Mar 17. doi: 10.2174/0109298673415187251212085809. Online ahead of print.

ABSTRACT

BACKGROUND: Solanum incanum L. (S. incanum) is a Traditional Chinese Medicine (TCM) known for its heat-clearing and detoxifying properties. This study evaluates the anti-cancer potential of S. incanum in lung and colorectal adenocarcinoma. Also, we aim to confirm the connection between the lung and the large intestine, as proposed in TCM theory.

METHODS: This study employed network pharmacology analysis, MTT and morphological analysis, Western blotting, and molecular docking to investigate the anti-cancer effects of S. incanum, particularly through its activation of the TRAIL-mediated extrinsic apoptotic pathway.

RESULTS: This study identified 15 active compounds in S. incanum, with glycosylated alkaloids such as α-solanine and solasonine highlighted as key bioactive compounds. KEGG and GO analyses revealed that S. incanum influences apoptosis-related pathways, particularly the extrinsic apoptotic pathway, regulating mediators such as CASP3, CASP8, and various TNF- related receptors. The anticancer potential was assessed through cellular studies using A549 and HT29 cell lines, with MTT cell viability assays showing that α-solanine induces apoptosis, with IC50 values between 20 and 30 μM. Western blot analysis demonstrated that S. incanum activates apoptosis via the TRAIL-mediated extrinsic apoptotic pathway, promoting CASP8, CASP3, and PARP1 cleavage in a dose-dependent manner, affecting DNA synthesis. Molecular docking further identified α-solanine and solasonine as compounds that bind to critical proteins in the TRAIL-related apoptotic pathway, confirming their roles in promoting apoptosis.

DISCUSSION: The shared activation of the TRAIL-mediated apoptotic pathway in both lung and colorectal adenocarcinoma models suggests a common molecular mechanism. These findings provide experimental evidence linking traditional ethnopharmacological concepts with apoptosis-related anti-cancer activity.

CONCLUSIONS: This study emphasizes that the main compound of S. incanum, α-solanine, supports the ethnopharmacological concept of "Exterior-interior Pairing of the Lung and Large Intestine", thereby demonstrating that both lung and colorectal adenocarcinomas share a common anticancer pathway through a TRAIL-related apoptotic mechanism.

PMID:41863159 | DOI:10.2174/0109298673415187251212085809

Received — 17 March 2026 ⏭

ELLA: Generative AI-Powered Social Robots for Early Language Development at Home

✇cs.AI, q-bio.NC updates on arXiv.org
By: Victor Nikhil Antony · Shiye Cao · Shuning Wang · Chien-Ming Huang
16 March 2026 at 12:00
arXiv:2603.12508v1 Announce Type: cross Abstract: Early language development shapes children's later literacy and learning, yet many families have limited access to scalable, high-quality support at home. Recent advances in generative AI make it possible for social robots to move beyond scripted interactions and engage children in adaptive, conversational activities, but it remains unclear how to design such systems for pre-schoolers and how children engage with them over time in the home. We present ELLA (Early Language Learning Agent), an autonomous, generative AI-powered social robot that supports early language development through interactive storytelling, parent-selected language targets, and scaffolded dialogue. Using a multi-phased, human-centered process, we interviewed parents (n=7) and educators (n=5) and iteratively refined ELLA through twelve in-home design workshops. We then deployed ELLA with ten children for eight days. We report design insights from in-home workshops, characterize children's engagement and behaviors during deployment, and distill design implications for generative AI-powered social robots supporting early language learning at home.
Received — 14 March 2026 ⏭

Latilactobacillus curvatus IM01 Alleviates Allergic Airway Inflammation Through Microbial and Metabolic Crosstalk Along the Gut-Lung Axis

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yujia He · Jing Liu · Tao Yang · Yuanming Huang · Liqiong Song · Zhihong Ren
14 March 2026 at 18:00

Nutrients. 2026 Mar 4;18(5):834. doi: 10.3390/nu18050834.

ABSTRACT

Background: Gut microbiota dysbiosis is critically implicated in the pathogenesis of allergic airway inflammation (AAI) via the gut-lung axis. While Latilactobacillus curvatus is a promising probiotic candidate, its specific immunomodulatory mechanisms in respiratory diseases remain poorly understood. Objective: In this study, we investigated the protective effects and underlying mechanisms of L. curvatus IM01 in an ovalbumin (OVA)-induced murine AAI model using an integrated multi-omics approach. Results: Our results demonstrated that oral administration of L. curvatus IM01 significantly attenuated airway inflammation, suppressed Th2-type immune responses, and reduced serum IgE levels. Crucially, our multi-omics integration revealed a coherent gut-lung axis narrative driven by microbial and metabolic crosstalk. Specifically, 16S rRNA sequencing indicated that L. curvatus IM01 was closely linked to structural shifts in the gut microbial community, notably characterized by an enrichment trend for beneficial genera such as Odoribacter and Lactobacillus. This microbial restructuring was closely associated with a modulated cecal metabolic profile, as untargeted metabolomics exhibited a clear trend toward the restoration of key systemically active immunoregulatory metabolites, including indolelactic acid (ILA) and choline, which have been previously linked to the alleviation of AAI symptoms. Further linking this metabolic shift to respiratory immune tolerance, lung transcriptomic analysis showed that the treatment is strongly associated with the promotion of the differentiation of CD4+ T cells into Foxp3+ regulatory T cells (Tregs). Conclusions: Collectively, these findings suggest a novel potential pathway by which L. curvatus IM01 modulates the gut-lung axis through coordinated microbial and metabolic interventions, highlighting its potential as a therapeutic functional food ingredient for AAI.

PMID:41830004 | PMC:PMC12987261 | DOI:10.3390/nu18050834

Latilactobacillus curvatus IM01 Alleviates Allergic Airway Inflammation Through Microbial and Metabolic Crosstalk Along the Gut-Lung Axis

✇Omics In Lung
By: Yujia He · Jing Liu · Tao Yang · Yuanming Huang · Liqiong Song · Zhihong Ren
14 March 2026 at 18:00

Nutrients. 2026 Mar 4;18(5):834. doi: 10.3390/nu18050834.

ABSTRACT

Background: Gut microbiota dysbiosis is critically implicated in the pathogenesis of allergic airway inflammation (AAI) via the gut-lung axis. While Latilactobacillus curvatus is a promising probiotic candidate, its specific immunomodulatory mechanisms in respiratory diseases remain poorly understood. Objective: In this study, we investigated the protective effects and underlying mechanisms of L. curvatus IM01 in an ovalbumin (OVA)-induced murine AAI model using an integrated multi-omics approach. Results: Our results demonstrated that oral administration of L. curvatus IM01 significantly attenuated airway inflammation, suppressed Th2-type immune responses, and reduced serum IgE levels. Crucially, our multi-omics integration revealed a coherent gut-lung axis narrative driven by microbial and metabolic crosstalk. Specifically, 16S rRNA sequencing indicated that L. curvatus IM01 was closely linked to structural shifts in the gut microbial community, notably characterized by an enrichment trend for beneficial genera such as Odoribacter and Lactobacillus. This microbial restructuring was closely associated with a modulated cecal metabolic profile, as untargeted metabolomics exhibited a clear trend toward the restoration of key systemically active immunoregulatory metabolites, including indolelactic acid (ILA) and choline, which have been previously linked to the alleviation of AAI symptoms. Further linking this metabolic shift to respiratory immune tolerance, lung transcriptomic analysis showed that the treatment is strongly associated with the promotion of the differentiation of CD4+ T cells into Foxp3+ regulatory T cells (Tregs). Conclusions: Collectively, these findings suggest a novel potential pathway by which L. curvatus IM01 modulates the gut-lung axis through coordinated microbial and metabolic interventions, highlighting its potential as a therapeutic functional food ingredient for AAI.

PMID:41830004 | PMC:PMC12987261 | DOI:10.3390/nu18050834

Harnessing pyroptosis in breast cancer therapy: immunological mechanisms and emerging biomaterial strategies

✇Cell Death Discovery nature.com science feeds
By: Richmond Kwame Frimpong Asiedu · Mahamadou Souley Abdou · Rongbin Wei · Zhongdang Xiao · Bing Li · Ming Hu
12 March 2026 at 08:00

Cell Death Discovery, Published online: 12 March 2026; doi:10.1038/s41420-026-02996-1

Harnessing pyroptosis in breast cancer therapy: immunological mechanisms and emerging biomaterial strategies
Received — 25 February 2026 ⏭

Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haojun Shi · Suyu Ye · Katherine M. Guerrerio · Jianzhi Shen · Yifan Yin · Daniel Khashabi · Chien-Ming Huang · Tianmin Shu
24 February 2026 at 13:00
arXiv:2602.19304v1 Announce Type: cross Abstract: Successful cooperation among decentralized agents requires each agent to quickly adapt its plan to the behavior of other agents. In scenarios where agents cannot confidently predict one another's intentions and plans, language communication can be crucial for ensuring safety. In this work, we focus on path-level cooperation in which agents must adapt their paths to one another in order to avoid collisions or perform physical collaboration such as joint carrying. In particular, we propose a safe and interpretable multimodal path planning method, CaPE (Code as Path Editor), which generates and updates path plans for an agent based on the environment and language communication from other agents. CaPE leverages a vision-language model (VLM) to synthesize a path editing program verified by a model-based planner, grounding communication to path plan updates in a safe and interpretable way. We evaluate our approach in diverse simulated and real-world scenarios, including multi-robot and human-robot cooperation in autonomous driving, household, and joint carrying tasks. Experimental results demonstrate that CaPE can be integrated into different robotic systems as a plug-and-play module, greatly enhancing a robot's ability to align its plan to language communication from other robots or humans. We also show that the combination of the VLM-based path editing program synthesis and model-based planning safety enables robots to achieve open-ended cooperation while maintaining safety and interpretability.
There are no more articles
❌