FigAgent: Towards Automatic Method Illustration Figure Generation for AI Scientific Papers

By: Zhuoling Li · Jiarui Zhang · Jason Kuen · Jiuxiang Gu · Hossein Rahmani · Jun Liu

1 April 2026 at 12:00

arXiv:2603.29590v1 Announce Type: cross Abstract: Method illustration figures (MIFs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. In this paper, we identify three key characteristics that substantially influence MIF generation quality, i.e., \emph{compositional complexity}, \emph{component similarity}, and \emph{design dynamics}. To handle these characteristics, we take inspiration from human authors' drawing practices and propose \textbf{FigAgent}, a novel multi-agent framework for automatically generating high-quality MIFs. Through multi-agent collaboration, our FigAgent distills drawing experiences across similar components of MIFs and encapsulates them into reusable tools that can be invoked during MIF generation, while evolving these tools to adapt to dynamic design requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIFs with complex structures. Extensive experiments show the efficacy of our method. Project is available \href{https://zhuolingli.github.io/FigAgent-page-project/}{here}.

Mechanisms Underlying Drought Adaptability in Duolang Sheep Based on Metabolomic and Transcriptomic Analyses

Omics In Lung

By: Bingjie Jiang · Bin Chen · Yaling Yang · Yong Chen · Wujun Liu

27 March 2026 at 18:00

Biology (Basel). 2026 Mar 12;15(6):461. doi: 10.3390/biology15060461.

ABSTRACT

This study investigates the mechanisms underlying drought adaptability in Duolang sheep, a local breed from two distinct habitats in Xinjiang-an arid southern region and a grassland northern region-aiming to identify key factors driving differential environmental adaptation. Integrated multi-omics analyses were performed, including serum biochemical assays, untargeted metabolomics of perirenal and tail fat tissues, and transcriptomic profiling of lung, liver, and kidney samples. Our results revealed notable differences: (1) serum levels of GSH-Px, IL-2, and IgG were significantly higher in the southern group (p < 0.01); (2) metabolomic analysis identified key differential metabolites, including EPA (involved in unsaturated fatty acid biosynthesis), choline (glycerophospholipid metabolism), L-serine and glutathione (cofactor biosynthesis), and taurine (sulfur metabolism); and (3) transcriptomic analysis revealed significant differential expression of genes such as FGF21 (thermogenesis), CD14 and DUSP2 (MAPK signaling pathway), GOT1 (arginine biosynthesis), and AVPR2 (vasopressin-regulated water reabsorption). Integrative correlation analysis further indicated that glutathione, EPA, GOT1, and CD14 are involved in energy and lipid metabolism, while taurine, AVPR2, and DUSP2 contribute to oxidative stress resistance and immune regulation. These molecular and metabolic adjustments collectively enhance drought adaptability in southern Xinjiang Duolang sheep. In conclusion, adaptation to arid environments requires enhanced antioxidant capacity and immune function, with metabolites such as EPA supporting lipid metabolism and genes such as FGF21 regulating fatty acid oxidation to limit triglyceride accumulation.

PMID:41892221 | PMC:PMC13023672 | DOI:10.3390/biology15060461

ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography

cs.AI, q-bio.NC updates on arXiv.org

By: Jing Xu · Weiqiang Wang · Cunjian Chen · Jun Liu · Qiuhong Ke

25 March 2026 at 12:00

arXiv:2603.22316v1 Announce Type: cross Abstract: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation quality, but they remain difficult to deploy in interactive scenarios due to bidirectional attention dependencies. As the number of dancers and the sequence length increase, the attention computation required for aligning music conditions with motion sequences grows quadratically, leading to reduced efficiency and increased risk of motion collisions. Effectively modeling dense spatial-temporal interactions is therefore essential, yet existing methods often struggle to capture such complexity, resulting in limited scalability and unstable multi-dancer coordination. To address these challenges, we propose ST-GDance++, a scalable framework that decouples spatial and temporal dependencies to enable efficient and collision-aware group choreography generation. For spatial modeling, we introduce lightweight distance-aware graph convolutions to capture inter-dancer relationships while reducing computational overhead. For temporal modeling, we design a diffusion noise scheduling strategy together with an efficient temporal-aligned attention mask, enabling stream-based generation for long motion sequences and improving scalability in long-duration scenarios. Experiments on the AIOZ-GDance dataset show that ST-GDance++ achieves competitive generation quality with significantly reduced latency compared to existing methods.

Generalizing Dynamics Modeling More Easily from Representation Perspective

cs.AI, q-bio.NC updates on arXiv.org

By: Yiming Wang · Zhengnan Zhang · Genghe Zhang · Jiawen Dan · Changchun Li · Chenlong Hu · Chris Nugent · Jun Liu · Ximing Li · Bo Yang

25 March 2026 at 12:00

arXiv:2603.22655v1 Announce Type: cross Abstract: Learning system dynamics from observations is a critical problem in many applications over various real-world complex systems, e.g., climate, ecology, and fluid systems. Recently, neural dynamics modeling method have become a prevalent solution that embeds the object's observations into a latent space before learning dynamics using neural methods such as neural Ordinary Differential Equations (ODE). Existing dynamics modeling methods induce a specific model for each observation of different complex systems, resulting in poor generalization across systems. Inspired by the great success of pre-trained models, we conduct a generalized Pre-trained Dynamics EncoDER (PDEDER) which can embed the original state observations into a latent space where the dynamics can be captured more easily. To conduct the generalized PDEDER, we pre-train any Pre-trained Language Model (PLM) by minimizing the Lyapunov exponent objective, which constrains the chaotic behavior of governing dynamics learned in the latent space. By penalizing the divergence of embedded observations, our PDEDER promotes locally stable and well-structured latent dynamics, thereby facilitating more effective dynamics modeling than in the original observation space. In addition, we incorporate reconstruction and forecasting objectives to mitigate the risk of obtaining an over-smoothed latent space. Specifically, we collect 152 sets of real-world and synthetic observations from 23 complex systems as pre-training corpora and employ them to pre-train PDEDER. Given any future dynamic observation, we can fine-tune PDEDER with any specific dynamics modeling method. We evaluate PDEDER on 12 dynamic systems by short/long-term forecasting under both in-domain and cross-domain settings, and the empirical results indicate the effectiveness and generalizability of PDEDER.

Protein phosphatase 2A methylation state impacts α-synucleinopathy in mouse models

Cell Death Discovery nature.com science feeds

By: Santhosh Maddila · Kambiz Hassanzadeh · Jun Liu · Jie Zhang · Faheem Ullah · Russell E. Nichols · M. Maral Mouradian

24 March 2026 at 08:00

Cell Death Discovery, Published online: 24 March 2026; doi:10.1038/s41420-026-03045-7

Protein phosphatase 2A methylation state impacts α-synucleinopathy in mouse models

Screening of Hepatocellular Carcinoma in Hepatic Cirrhosis Patients by a Novel Blood-Based Multi-Omics Test

Omics in Hepatocellular

By: Lei Chen · Jun Liu · Mengcheng Long · Pinghai Hu

23 March 2026 at 18:00

Technol Cancer Res Treat. 2026 Jan-Dec;25:15330338261435022. doi: 10.1177/15330338261435022. Epub 2026 Mar 23.

ABSTRACT

IntroductionHepatocellular carcinoma (HCC) screening in patients with hepatic cirrhosis (HC) relies on ultrasound and alpha-fetoprotein (US + AFP), which has limitations in sensitivity, particularly for early-stage HCC detection. This study aims to evaluate the performance of a novel multi-omics blood test, HCCscreen, with its individual components (methylation, AFP, Des-γ-Carboxy Prothrombin (DCP), mutations) and the standard US + AFP for HCC screening in a hepatic cirrhotic population.MethodsA total of 5078 patients with known high-risk for HCC were recruited. A prospective screening study was conducted on 650 patients with hepatic cirrhosis identified by ultrasound. Blood samples were collected from all patients before the confirmation of diagnosis by imaging and/or pathological examinations. The performance of HCCscreen, individual markers and US + AFP were calculated and compared. Statistics was performed with Graphpad Prism 5.0.ResultsHCCscreen exhibited a sensitivity of 86.3% at a specificity of 81.3%, with a positive predictive value (PPV) of 28.2% and a negative predictive value (NPV) of 98.6%. The positive likelihood ratio (LR+) was 4.61 and the negative LR (LR-) was 0.17. The positive detection rate (PDR) for all markers increased with more advanced HCC stages, whether Barcelona Clinic Liver Cancer (BCLC) or clinical staging. Among the single-omics, methylation showed the highest PDR, followed by AFP, DCP and mutations. HCCscreen demonstrated superior overall performance with an AUC of 0.87, outperforming individual markers like methylation (AUC = 0.76), AFP (AUC = 0.83), and DCP (AUC = 0.77). Crucially, HCCscreen's PDR was significantly higher than US + AFP in early-stage HCC (BCLC-0 and clinical stage I). Furthermore, while AFP's PDR varied significantly by sex, HCCscreen's performance remained consistent across all demographics. Correlation analysis revealed a significant association only between the HCCscreen score and the methylation score.ConclusionsThe multi-omics approach of HCCscreen significantly enhances early HCC detection in patients with hepatic cirrhosis compared to both its individual components and the current standard of US + AFP. Its robust and consistent performance across patient demographics underscores its potential as a superior tool for population-wide early HCC screening.

PMID:41869803 | PMC:PMC13009828 | DOI:10.1177/15330338261435022

Screening of Hepatocellular Carcinoma in Hepatic Cirrhosis Patients by a Novel Blood-Based Multi-Omics Test

(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)

By: Lei Chen · Jun Liu · Mengcheng Long · Pinghai Hu

23 March 2026 at 18:00

Technol Cancer Res Treat. 2026 Jan-Dec;25:15330338261435022. doi: 10.1177/15330338261435022. Epub 2026 Mar 23.

ABSTRACT

IntroductionHepatocellular carcinoma (HCC) screening in patients with hepatic cirrhosis (HC) relies on ultrasound and alpha-fetoprotein (US + AFP), which has limitations in sensitivity, particularly for early-stage HCC detection. This study aims to evaluate the performance of a novel multi-omics blood test, HCCscreen, with its individual components (methylation, AFP, Des-γ-Carboxy Prothrombin (DCP), mutations) and the standard US + AFP for HCC screening in a hepatic cirrhotic population.MethodsA total of 5078 patients with known high-risk for HCC were recruited. A prospective screening study was conducted on 650 patients with hepatic cirrhosis identified by ultrasound. Blood samples were collected from all patients before the confirmation of diagnosis by imaging and/or pathological examinations. The performance of HCCscreen, individual markers and US + AFP were calculated and compared. Statistics was performed with Graphpad Prism 5.0.ResultsHCCscreen exhibited a sensitivity of 86.3% at a specificity of 81.3%, with a positive predictive value (PPV) of 28.2% and a negative predictive value (NPV) of 98.6%. The positive likelihood ratio (LR+) was 4.61 and the negative LR (LR-) was 0.17. The positive detection rate (PDR) for all markers increased with more advanced HCC stages, whether Barcelona Clinic Liver Cancer (BCLC) or clinical staging. Among the single-omics, methylation showed the highest PDR, followed by AFP, DCP and mutations. HCCscreen demonstrated superior overall performance with an AUC of 0.87, outperforming individual markers like methylation (AUC = 0.76), AFP (AUC = 0.83), and DCP (AUC = 0.77). Crucially, HCCscreen's PDR was significantly higher than US + AFP in early-stage HCC (BCLC-0 and clinical stage I). Furthermore, while AFP's PDR varied significantly by sex, HCCscreen's performance remained consistent across all demographics. Correlation analysis revealed a significant association only between the HCCscreen score and the methylation score.ConclusionsThe multi-omics approach of HCCscreen significantly enhances early HCC detection in patients with hepatic cirrhosis compared to both its individual components and the current standard of US + AFP. Its robust and consistent performance across patient demographics underscores its potential as a superior tool for population-wide early HCC screening.

PMID:41869803 | PMC:PMC13009828 | DOI:10.1177/15330338261435022

Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning

cs.AI, q-bio.NC updates on arXiv.org

By: Yang Xu · Jun Liu · Shuwei Chen · Chris Nugent · Hailing Guo

16 March 2026 at 12:00

arXiv:2603.12953v1 Announce Type: cross Abstract: Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by construction pipeline integrating the Automated Theorem Generator Delta1 based on the full triangular standard contradiction (FTSC) with LLMs. Delta1 deterministically constructs minimal unsatisfiable clause sets and complete theorems in polynomial time, ensuring both soundness and minimality by construction. The LLM layer verbalizes each theorem and proof trace into coherent natural language explanations and actionable insights. Empirical studies across health care, compliance, and regulatory domains show that Delta1 and LLM enables interpretable, auditable, and domain aligned reasoning. This work advances the convergence of logic, language, and learning, positioning constructive theorem generation as a principled foundation for neuro-symbolic explainable AI.

Multimodal electron microscopy of halide perovskite interfacial dynamics

Nature - Issue - nature.com science feeds

By: Xinjuan Li · Qichun Gu · Wei Huang · Simon M. Fairclough · Richard H. Friend · Samuel D. Stranks · Tianjun Liu · Caterina Ducati

11 March 2026 at 08:00

Nature, Published online: 11 March 2026; doi:10.1038/s41586-026-10238-8

A multimodal in situ electron microscopy approach enables direct visualization of structural and chemical evolution in a working halide perovskite light-emitting diode with nanometre precision.

Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression

cs.AI, q-bio.NC updates on arXiv.org

By: Ye Tian · Aijun Liu

10 March 2026 at 12:00

arXiv:2603.07598v1 Announce Type: new Abstract: Chain-of-thought (CoT) improves reasoning reliability but increases token cost, motivating post-training compression of explicit reasoning traces. However, the shortest sufficient reasoning is not universal: it depends on difficulty, model capacity, and training state, making fixed length targets brittle. In practice, naive RL-based compression can also undesirably shorten the user-facing answer, because a single completion-level learning signal leaks across the think/answer boundary. We propose Difficulty-Scaled Segment-Wise GRPO (DSS-GRPO), which decomposes returns into think and answer components, computes group-relative advantages per segment, and routes them with hard token masks so compression updates act only on think while answer alignment acts only on answer. DSS-GRPO uses prompt-wise within-group shaping and difficulty-aware scaling to encourage concise reasoning without collapsing answer behavior.

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

cs.AI, q-bio.NC updates on arXiv.org

By: Liuyi Xu · Yun Guo · Ming Chen · Zihan Dun · Yining Qian · An-Yang Lu · Shuang Li · Lijun Liu

10 March 2026 at 12:00

arXiv:2603.08321v1 Announce Type: new Abstract: Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a field demanding rigorous interpretability and safety. To address this, we propose CORE-Acu, a neuro-symbolic framework for acupuncture clinical decision support that integrates Structured Chain-of-Thought (S-CoT) with knowledge graph (KG) safety verification. First, we construct the first acupuncture Structured Reasoning Trace dataset and a schema-constrained fine-tuning framework. By enforcing an explicit causal chain from pattern identification to treatment principles, treatment plans, and acupoint selection, we transform implicit Traditional Chinese Medicine (TCM) reasoning into interpretable generation constraints, mitigating the opacity of LLM-based CDS. Furthermore, we construct a TCM safety knowledge graph and establish a ``Generate--Verify--Revise'' closed-loop inference system based on a Symbolic Veto Mechanism, employing deterministic rules to intercept hallucinations and enforce hard safety boundaries. Finally, we introduce the Lexicon-Matched Entity-Reweighted Loss (LMERL), which corrects terminology drift caused by the frequency--importance mismatch in general optimization by adaptively amplifying gradient contributions of high-risk entities during fine-tuning. Experiments on 1,000 held-out cases demonstrate CORE-Acu's superior entity fidelity and reasoning quality. Crucially, CORE-Acu achieved 0/1,000 observed safety violations (95\% CI: 0--0.37\%), whereas GPT-4o exhibited an 8.5\% violation rate under identical rules. These results establish CORE-Acu as a robust neuro-symbolic framework for acupuncture clinical decision support, guaranteeing both reasoning auditability and strict safety compliance.

Foundational World Models Accurately Detect Bimanual Manipulator Failures

cs.AI, q-bio.NC updates on arXiv.org

By: Isaac R. Ward · Michelle Ho · Houjun Liu · Aaron Feldman · Joseph Vincent · Liam Kruse · Sean Cheong · Duncan Eddy · Mykel J. Kochenderfer · Mac Schwager

10 March 2026 at 12:00

arXiv:2603.06987v1 Announce Type: cross Abstract: Deploying visuomotor robots at scale is challenging due to the potential for anomalous failures to degrade performance, cause damage, or endanger human life. Bimanual manipulators are no exception; these robots have vast state spaces comprised of high-dimensional images and proprioceptive signals. Explicitly defining failure modes within such state spaces is infeasible. In this work, we overcome these challenges by training a probabilistic, history informed, world model within the compressed latent space of a pretrained vision foundation model (NVIDIA's Cosmos Tokenizer). The model outputs uncertainty estimates alongside its predictions that serve as non-conformity scores within a conformal prediction framework. We use these scores to develop a runtime monitor, correlating periods of high uncertainty with anomalous failures. To test these methods, we use the simulated Push-T environment and the Bimanual Cable Manipulation dataset, the latter of which we introduce in this work. This new dataset features trajectories with multiple synchronized camera views, proprioceptive signals, and annotated failures from a challenging data center maintenance task. We benchmark our methods against baselines from the anomaly detection and out-of-distribution detection literature, and show that our approach considerably outperforms statistical techniques. Furthermore, we show that our approach requires approximately one twentieth of the trainable parameters as the next-best learning-based approach, yet outperforms it by 3.8% in terms of failure detection rate, paving the way toward safely deploying manipulator robots in real-world environments where reliability is non-negotiable.

Reading view