❌

Normal view

Received — 18 September 2026 ⏭
Received — 15 September 2026 ⏭

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

✇cs.AI, q-bio.NC updates on arXiv.org
By: Miguel Zabaleta · Baihan Lin
14 September 2026 at 12:00
arXiv:2609.11559v1 Announce Type: cross Abstract: Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.

Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Model

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sicheng Mao · Baihan Li · Mathieu Fontaine · Anthony Larcher · Roland Badeau
14 September 2026 at 12:00
arXiv:2609.12154v1 Announce Type: cross Abstract: Distant speaker diarization remains challenging due to difficult acoustic environments, varying numbers of speakers and overlapping speech. Model-driven methods are proposed to exploit the speech source features in multi-channel recordings that help diarization. This paper generalizes a neural model that jointly learns to perform blind source separation and diarization over speech mixtures (neural FCASA) with heavy-tailed models. The popular Gaussian distribution has been applied for variance modeling in the original source separation model, which we replace with two families of heavy-tailed models (Leptokurtic Generalized Gaussian distribution and Student's t distribution) to better capture the heavy-tailedness in speech signals. Thanks to the Gaussian scale mixture model, we are able to unify the proposed method and the original one under the same form of learning objective. Our experiments show consistent large improvements in Diarization Error Rate (DER) and Jaccard Error Rate (JER) compared to the baseline on various corpora.

SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-Distillation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunmeng Chen (Chongqing Ant Consumer Finance Co. · Ltd) · Kunyu Wang (Alibaba Cloud Computing Co. · Ltd) · Peihan Li (Chongqing Ant Consumer Finance Co. · Ltd) · Yi Wang (Chongqing Ant Consumer Finance Co. · Ltd) · Shuyin Xia (Chongqing University of Posts and Telecommunications) · Yi Liu (Chongqing Ant Consumer Finance Co. · Ltd) · Xinyong Cheng (Alibaba Cloud Computing Co. · Ltd) · Dehui Wang (Alibaba Cloud Computing Co. · Ltd) · Xiangyong Zhai (Alibaba Cloud Computing Co. · Ltd) · Yanxing Liu (Chongqing Ant Consumer Finance Co. · Ltd) · Song Liu (Chongqing Ant Consumer Finance Co. · Ltd)
14 September 2026 at 12:00
arXiv:2609.12579v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) scores student-generated prefixes with a solution-conditioned self-teacher, yet transfers supervision only through next-token probabilities. We ask whether the aligned final-layer discrepancy offers a useful second channel, and how to test that channel without confusing its geometry with auxiliary strength. SCOPE-OPSD projects the privileged teacher-student residual onto a frozen rank-64 factor estimated from residual covariance and language-model-head Fisher sensitivity. It reuses the forwards already required by OPSD and adds neither rollouts nor inference-time modules. A matched Random control preserves the structured factor's rank and nonzero spectrum and uses per-arm gradient-RMS calibration, isolating the effect of the data-dependent orientation. Across the complete 25/50/75/100-step trajectories for Qwen3-1.7B, 4B, and 8B, Structured is never below Pure OPSD, with strict gains in 11 of the 12 model-checkpoint combinations and an exact tie at 4B step 25. Structured also exceeds matched Random in 10 of the 12 combinations. At step 75 on Qwen3-1.7B, Structured exceeds matched Random by 1.39 Macro Avg@12 points in each of two independent training reruns. A cross-fitted diagnostic also shows 4.40 times greater held-out privileged-gap capture than the matched random orientation. The results support a compact, Fisher-conditioned privileged subspace for short-budget OPSD.

Hepatic Usp2 orchestrates de novo lipogenesis through G3bp2 stabilization and β-catenin activation

✇Cell Death Discovery nature.com science feeds
By: Wei Wang · Hui Wang · Yihan Liu · Siyuan Cui · Chuanxi Tang · Mengxue Wang · Chunyan Mu · Jingyu Li · Xianlong Ye · Xinmiao Liang · Shenglong Zhu
14 September 2026 at 08:00

Cell Death Discovery, Published online: 14 September 2026; doi:10.1038/s41420-026-03333-2

Hepatic Usp2 orchestrates de novo lipogenesis through G3bp2 stabilization and β-catenin activation

Multi-Omics-Enabled Precision Strategies for Overcoming CAR-T Therapy Limitations in Gastrointestinal Malignancies

✇Omics in Gastric
By: Ke Su · Zunyuan Tan · Han Li · Kai You · Susu Xiao · Haiqing Chen · Danyang Li · Xin Liu · Xinrui Du · Jiaxin Hu · Kun He · Yantian Xu · Jian Chen · Yunwei Han
10 September 2026 at 18:00

Biofactors. 2026 Sep-Oct;52(5):e70150. doi: 10.1002/biof.70150.

ABSTRACT

Gastrointestinal malignancies, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic ductal adenocarcinoma, remain major causes of cancer-related morbidity and mortality worldwide. Although chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized the treatment of hematologic malignancies, its efficacy in gastrointestinal solid tumors remains limited by antigen heterogeneity, insufficient trafficking and infiltration, immunosuppressive tumor microenvironments, on-target off-tumor toxicity, and adaptive resistance. In this review, we summarize the current landscape of CAR-T therapy in gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic cancer, with a focus on representative target antigens and emerging biomarker strategies. We further discuss two major categories of biomarkers: target antigen-related biomarkers and conventional dynamic biomarkers, including serum tumor markers, cytokine changes, CAR-T expansion kinetics, and antigen-loss monitoring. In addition, we highlight how single-cell ribonucleic acid sequencing and spatial transcriptomics provide complementary insights into cellular states, immune exhaustion, stromal barriers, and spatially restricted immune exclusion. By integrating these multi-omics approaches with biomarker-guided patient stratification and next-generation CAR-T engineering, gastrointestinal solid tumor CAR-T therapy may evolve from empirical optimization toward mechanism-driven and precision-guided clinical translation.

PMID:42717494 | PMC:PMC13558850 | DOI:10.1002/biof.70150

Received — 13 September 2026 ⏭

Multi-Omics-Enabled Precision Strategies for Overcoming CAR-T Therapy Limitations in Gastrointestinal Malignancies

✇Omics in Hepatocellular
By: Ke Su · Zunyuan Tan · Han Li · Kai You · Susu Xiao · Haiqing Chen · Danyang Li · Xin Liu · Xinrui Du · Jiaxin Hu · Kun He · Yantian Xu · Jian Chen · Yunwei Han
10 September 2026 at 18:00

Biofactors. 2026 Sep-Oct;52(5):e70150. doi: 10.1002/biof.70150.

ABSTRACT

Gastrointestinal malignancies, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic ductal adenocarcinoma, remain major causes of cancer-related morbidity and mortality worldwide. Although chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized the treatment of hematologic malignancies, its efficacy in gastrointestinal solid tumors remains limited by antigen heterogeneity, insufficient trafficking and infiltration, immunosuppressive tumor microenvironments, on-target off-tumor toxicity, and adaptive resistance. In this review, we summarize the current landscape of CAR-T therapy in gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic cancer, with a focus on representative target antigens and emerging biomarker strategies. We further discuss two major categories of biomarkers: target antigen-related biomarkers and conventional dynamic biomarkers, including serum tumor markers, cytokine changes, CAR-T expansion kinetics, and antigen-loss monitoring. In addition, we highlight how single-cell ribonucleic acid sequencing and spatial transcriptomics provide complementary insights into cellular states, immune exhaustion, stromal barriers, and spatially restricted immune exclusion. By integrating these multi-omics approaches with biomarker-guided patient stratification and next-generation CAR-T engineering, gastrointestinal solid tumor CAR-T therapy may evolve from empirical optimization toward mechanism-driven and precision-guided clinical translation.

PMID:42717494 | PMC:PMC13558850 | DOI:10.1002/biof.70150

Fibronectin 1 mediated histone lactylation promotes malignant progression of GIST regulated by m<sup>6</sup>A modification

✇Cell Death Discovery nature.com science feeds
By: Ge Zhang · Jiehan Li · Yuhan Yin · Wunan Mi · Hao Liu · Zhao Sun · Jiahao Liu · Yizheng Zhang · Meimei Jiang · Nannan Liu · Guiyun Jia · Yingjie Zhang · Yang Fu
11 September 2026 at 08:00

Cell Death Discovery, Published online: 11 September 2026; doi:10.1038/s41420-026-03338-x

Fibronectin 1 mediated histone lactylation promotes malignant progression of GIST regulated by m6A modification

Multi-Omics-Enabled Precision Strategies for Overcoming CAR-T Therapy Limitations in Gastrointestinal Malignancies

✇(Multiomics OR Omics) AND (Pancreatic)
By: Ke Su · Zunyuan Tan · Han Li · Kai You · Susu Xiao · Haiqing Chen · Danyang Li · Xin Liu · Xinrui Du · Jiaxin Hu · Kun He · Yantian Xu · Jian Chen · Yunwei Han
10 September 2026 at 18:00

Biofactors. 2026 Sep-Oct;52(5):e70150. doi: 10.1002/biof.70150.

ABSTRACT

Gastrointestinal malignancies, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic ductal adenocarcinoma, remain major causes of cancer-related morbidity and mortality worldwide. Although chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized the treatment of hematologic malignancies, its efficacy in gastrointestinal solid tumors remains limited by antigen heterogeneity, insufficient trafficking and infiltration, immunosuppressive tumor microenvironments, on-target off-tumor toxicity, and adaptive resistance. In this review, we summarize the current landscape of CAR-T therapy in gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic cancer, with a focus on representative target antigens and emerging biomarker strategies. We further discuss two major categories of biomarkers: target antigen-related biomarkers and conventional dynamic biomarkers, including serum tumor markers, cytokine changes, CAR-T expansion kinetics, and antigen-loss monitoring. In addition, we highlight how single-cell ribonucleic acid sequencing and spatial transcriptomics provide complementary insights into cellular states, immune exhaustion, stromal barriers, and spatially restricted immune exclusion. By integrating these multi-omics approaches with biomarker-guided patient stratification and next-generation CAR-T engineering, gastrointestinal solid tumor CAR-T therapy may evolve from empirical optimization toward mechanism-driven and precision-guided clinical translation.

PMID:42717494 | PMC:PMC13558850 | DOI:10.1002/biof.70150

Received — 10 September 2026 ⏭

BRD4 Inhibition Mitigates Acute and Chronic Corneal Injury Following Topical Nitrogen Mustard Exposure

✇Molecular Therapy
By: Zhongqiao Lu · Shuizhen Shi · Fan Xia · Adwaid Manu Krishna Chandran · Jonathan Lin · Daniela J. Iniguez · Massoud Motamedi · Hua Liu · Wenbo Zhang
2 September 2026 at 08:00
Lu and colleagues identify BRD4 as a central epigenetic driver of vesicant-induced corneal injury. Using reproducible mouse and rabbit models, they show that short-term topical BRD4 inhibition suppresses acute inflammation and provides durable protection of corneal clarity, stromal organization, endothelial integrity, and neovascularization, supporting translational therapy for chemical eye injuries.

MITF-SCD1 Lipid Metabolic Axis Prevents Ouabain-Induced Spiral Ganglion Neuron Ferroptosis and Hearing Loss

✇Molecular Therapy
By: Xue Wang · Fang Chen · Ziji Zhang · Man Zhang · Man Wang · Lei Chen · Anqi Suo · Xugang Zhuang · Tenghan Ling · Renjie Chai · Haibo Wang · Bo Chu · Lei Xu · Wenwen Liu
31 August 2026 at 08:00
Ouabain triggers cochlear spiral ganglion neuron (SGN) ferroptosis and hearing loss via SCD1 downregulation. MITF directly activates Scd1 transcription, and the MITF–SCD1 axis mitigates SGN ferroptosis and hearing impairment in ototoxic ouabain and cisplatin models, revealing a lipid metabolic vulnerability and therapeutic target for sensorineural hearing loss.

JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zixiang Chen · Yuheng Lu · Zihao Cheng · Zeming Liu · Jizeng Bai · Ziye Huang · Zhiyin Lin · Zihan Li · Yuhang Guo · Yunhong Wang · Haifeng Wang
10 September 2026 at 12:00
arXiv:2609.10451v1 Announce Type: new Abstract: Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of agents' readiness for real-world usage. We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device workflows requiring coordinated interaction across heterogeneous platforms, including Android, Windows, and Ubuntu. Specifically, JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device workflows and dynamically evaluate agent performance within a unified framework. By evaluating agents in virtual environments spanning multiple operating systems, JarvisGUI reveals that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world workflows, exposing a critical capability gap invisible to existing benchmarks.

FrogNano: Training a 4B Coding Agent via Online Task Synthesis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Minseon Kim · Zhengyan Shi · Emiliano Penaloza · Christopher Cui · Roger Creus Castanyer · Maryam Hashemzadeh · Isadora White · Jonathan Light · Jeonghye Kim · Matheus Pereira · Darya Moldavskaya · Chinmay Singh · Fabio Vera · Baolin Peng · Xingdi Yuan · Marc-Alexandre C\^ot\'e · Alessandro Sordoni
10 September 2026 at 12:00
arXiv:2609.07925v2 Announce Type: replace Abstract: We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks. A key ingredient for improving performance is an online task synthesis pipeline that creates tasks calibrated to the frontier of learnability for the current checkpoint. This report provides evidence that competitive small coding agents can be trained with synthetic tasks alone, without traditional distillation from larger models, and that generating tasks at the learnability frontier of the current agent is important. We report details on the training methodology, evaluations across diverse environments, and in-depth analyses, serving as a foundation for our ongoing exploration of lightweight yet capable coding agents that can run on minimal hardware.
  • ✇cs.AI, q-bio.NC updates on arXiv.org
  • The Biggest Risk of Embodied AI is Governance Lag Shaoshan Liu
    arXiv:2604.21938v2 Announce Type: replace-cross Abstract: Embodied AI is widely discussed as a job-displacement problem. The deeper risk, however, is governance lag: the time and capability gap between a measurable change in technology deployment and an institutional response able to address its consequences. Building on the established pacing problem and the Collingridge dilemma, this article argues that embodied AI intensifies that gap through scalable models and platforms, task-level reorgan
     
  • 🏷️
  • ↗️

The Biggest Risk of Embodied AI is Governance Lag

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shaoshan Liu
10 September 2026 at 12:00
arXiv:2604.21938v2 Announce Type: replace-cross Abstract: Embodied AI is widely discussed as a job-displacement problem. The deeper risk, however, is governance lag: the time and capability gap between a measurable change in technology deployment and an institutional response able to address its consequences. Building on the established pacing problem and the Collingridge dilemma, this article argues that embodied AI intensifies that gap through scalable models and platforms, task-level reorganization, and the separation of upstream technological control from downstream social impact. We distinguish three mutually reinforcing forms of lag, observational, institutional, and distributive, and propose a compliance architecture based on deployment visibility, stack-level accountability, trigger-based adjustment, and automatic distributional response. The central policy challenge is not automation alone, but whether governance systems can become observable, responsive, and adaptive before disruption becomes entrenched.

Integrated single-cell multi-omics characterization reveals lipid-associated macrophage-mediated immunosuppression in neoadjuvant immunotherapy of hepatocellular carcinoma

✇Omics in Hepatocellular
By: Shengxuan Peng · Chang Liu · Junyu Long · Jincheng Tian · Han Li · Donghai Lu · Qihang Cao · Daolin Zhang · Qiao He · Jisen Jia · Yuxuan Wang · Zhaoru Dong · Haitao Zhao · Lei Zhao · Dongxu Wang · Tao Li
1 September 2026 at 18:00

Nat Commun. 2026 Jul 31;17(1):9381. doi: 10.1038/s41467-026-75949-y.

ABSTRACT

Hepatocellular carcinoma (HCC) is a cancer with high incidence and mortality rate. Although immune checkpoint inhibitors (ICIs) improved survival outcomes for HCC patients, limited objective response rate highlights the urgency of investigating determinants of immunotherapy. Here, we explore HCC resistance mechanisms following neoadjuvant αPD-1 immunotherapy by constructing a comprehensive multi-modal single-cell transcriptomic atlas consisting of 14 HCC patients treated with αPD-1 from our cohort (ClinicalTrials.gov ID: NCT06571396) and 60 external HCC cases with heterogeneous treatment backgrounds. Supervised by clinical outcomes of our cohort, we identify positive and negative regulators of immunotherapy within the tumor immune microenvironment (TIME), especially lipid-associated macrophages (LAM) with increased lipid metabolic state in non-responders and characterized by C1QA, FABP1, and APOA1 expression. We further show the presence, exogenous inducements and immunosuppressive functions of LAM, along with regulation strategies of its lipid-associated condition, including lycopene and chiglitazar. Furthermore, we construct interaction networks of immune regulators across responders and non-responders, showing distinct ligand-receptor landscapes with intervention targets. We reveal the TIME components including immunosuppressive LAMs that influence immunotherapy outcomes, thus providing evidence and insights for exploring immune landscape and therapeutic strategies for HCC immunotherapy. ClinicalTrials.gov ID: NCT06571396.

PMID:42680737 | PMC:PMC13534469 | DOI:10.1038/s41467-026-75949-y

Received — 27 May 2026 ⏭

TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuhang Zhang · Keyan Ding · Peilin Chen · Han Liu · Can Lin · Ruixi Chen · Shiqi Wang · Qi Song
26 May 2026 at 12:00
arXiv:2605.24489v1 Announce Type: new Abstract: Enzyme-reaction retrieval is a fundamental problem in computational biology, underpinning enzyme characterization, reaction mechanism elucidation, and the rational design of metabolic pathways and biocatalysts. As a bidirectional task, it entails both enzyme-to-reaction and reaction-to-enzyme mapping. However, existing approaches suffer from poor generalization across tasks and distributions, with performance highly sensitive to dataset splits and substantial asymmetry between retrieval directions. To address these challenges, we present TIGER, a Text-Informed Generalized Enzyme-Reaction Retrieval framework that leverages protein-to-text generation models to distill textual semantic knowledge from enzyme sequences, providing a generalized representation that bridges enzymes and biochemical reactions. To ensure the quality and reliability of textual semantics, we design a Dynamic Gating Network that adaptively fuses text-derived knowledge with sequence features, enabling more consistent and informative enzyme representations, while a Structure-Shared Feature Projector aligns enzyme and reaction representations within a unified latent space. Extensive experiments demonstrate that, under bidirectional retrieval supervision, TIGER significantly outperforms state-of-the-art baselines across diverse distributions and exhibits strong robustness and transferability across tasks.

Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuntao Wang · Jianle Ba · Han Liu · Yanghe Pan · Jintao Wei · Zhou Su · Tom H. Luan · Linkang Du
26 May 2026 at 12:00
arXiv:2605.25435v1 Announce Type: new Abstract: The rapid evolution of large language model (LLM)-driven autonomous agents has given rise to OpenClaw, a new class of open-source agent frameworks that operate as continuously running, skill-augmented systems with persistent memory, multi-channel interaction, and high degrees of autonomy. Such capabilities enable OpenClaw agents to autonomously execute complex, multi-step tasks and interact seamlessly with external applications, but simultaneously introduce a substantially enlarged attack surface. In particular, the combination of high-privilege operations and persistent memory exposes OpenClaw agents to various emerging threats, including skill poisoning, cognitive manipulation, multi-agent cascading failures, and supply-chain vulnerabilities. In this survey, we present a comprehensive study of the security landscape of OpenClaw agents. We first examine the general architecture and key characteristics that distinguish OpenClaw agents from traditional AI agent systems. We categorize existing security and privacy threats into a layered framework and analyze how vulnerabilities arise during agent reasoning, action execution, and external interaction. Representative defense mechanisms are also reviewed to draw the current defense landscape. Finally, several unresolved issues related to the reliability and trustworthiness of OpenClaw ecosystems are discussed.

Harnessing AtomisticSkills for Agentic Atomistic Research

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bowen Deng · Bohan Li · Matthew Cox · Hoje Chun · Juno Nam · Artur Lyssenko · Sathya Edamadaka · Jurgis Ruza · Xiaochen Du · Nofit Segal · Jesus Diaz Sanchez · Mingrou Xie · Ty Perez · Yu Yao · Miguel Steiner · Sauradeep Majumdar · Charles B. Musgrave III · Anirban Chandra · Abhirup Patra · Detlef Hohl · Connor W. Coley · Ju Li · Rafael G\'omez-Bombarelli
26 May 2026 at 12:00
arXiv:2605.24002v1 Announce Type: cross Abstract: Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabilities, scaling monolithic agents to manage the rigor and complexity of atomistic research remains a challenge. Here, we introduce AtomisticSkills, an open-source harness framework that empowers general-purpose AI coding agents to conduct atomistic research across materials science, chemistry, and drug discovery. By hierarchically decomposing scientific workflows into agent skills and tools, AtomisticSkills provides agents with modular, extensible, and plug-and-play research capabilities. The framework integrates more than 100 human-curated multidisciplinary skills, including database access, thermodynamics and kinetics modeling, and diverse simulation engines employing machine learning interatomic potentials (MLIPs) and density functional theory (DFT). We validate its functional coverage against scientific literature and demonstrate robust orchestration capabilities across diverse scientific campaigns: generative design of Li-ion solid-state electrolytes, high-throughput screening of metal-organic frameworks for CO2 capture, autonomous MLIP benchmarking and fine-tuning, multi-stage structure-based virtual screening for drug design, multimodal X-ray diffraction pattern analysis, and screening of Fe-oxide catalysts for oxygen evolution reaction. AtomisticSkills provides a critical agent infrastructure towards building fully autonomous AI scientists.

SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack

✇cs.AI, q-bio.NC updates on arXiv.org
By: Han Liu · Zhi Xu · Xiaotong Zhang · Feng Zhang · Xiaoming Xu · Wei Wang · Fenglong Ma · Hong Yu
26 May 2026 at 12:00
arXiv:2605.24958v1 Announce Type: cross Abstract: Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especially transferable attacks that generate adversarial examples using surrogate models without accessing the victim model. Transferable attacks in the text domain are still under-explored, with only a few studies addressing this challenging issue, often with suboptimal results due to equal treatment of submodels or inaccurate estimation of importance scores. To address these challenges, we propose a simple yet effective paradigm for transfer-based textual adversarial attack, named SEP-Attack. Specifically, we employ the Determinantal Point Process (DPP) to generate diverse surrogate ensemble weights, representing the transferability of submodels. Using these weights, we introduce a new metric to evaluate prediction confidence scores, which in turn are used to calculate word importance scores and generate adversarial candidates. Finally, we quantify the transferability score for each candidate and select the top ones as the final transferable adversarial examples. Experiments conducted on four datasets and two real-world APIs validate the efficacy of SEP-Attack, significantly outperforming state-of-the-art baselines.

MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunqi Gao · Leyuan Liu · Yuhan Li · Changxin Gao · Jingying Chen
26 May 2026 at 12:00
arXiv:2605.25861v2 Announce Type: cross Abstract: 3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation, we propose to address these two tasks within a unified framework, which allows their mutual dependencies to be effectively exploited. Building on this idea, we propose MuNet, a mutualistic network for joint 3D human mesh recovery and 3D clothed human reconstruction from single images. First, we adopt 2-manifold graphs as a unified representation for all 3D models, enabling consistent modeling across 3D human mesh recovery and clothed human reconstruction. Second, we design an end-to-end graph convolutional network that progressively deforms an initial graph into a 3D human mesh and refines it into a detailed 3D clothed human model. Third, we introduce a mutualistic mechanism that allows reciprocal interaction between the two tasks {during training}, where 3D human mesh recovery provides guidance for 3D clothed human reconstruction, and reconstruction feedback refines the 3D human mesh recovery. We extensively evaluate MuNet on six benchmark datasets for 3D human mesh recovery and 3D clothed human reconstruction, including Human3.6M, 3DPW, MPI-INF-3DHP, THuman2.0, CAPE, and RenderPeople. Experimental results demonstrate that MuNet achieves state-of-the-art performance on both tasks across all datasets. The code of MuNet is released for research purposes at https://github.com/starVisionTeam/MuNet.
❌