❌

Normal view

Received β€” 2 April 2026 ⏭

The neonatal lung microbiome: a dynamic determinant of respiratory health, disease, and novel therapeutics

βœ‡Omics In Lung
By: Wanwei Zheng Β· Yan Liang Β· Jiayao Li
1 April 2026 at 18:00

Front Pediatr. 2026 Mar 16;14:1770578. doi: 10.3389/fped.2026.1770578. eCollection 2026.

ABSTRACT

The neonatal lung, once considered sterile, is now recognized to harbor a dynamic and complex microbiome that plays a critical role in respiratory health and disease. This review synthesizes current evidence on the composition, development, and functional impact of the lung microbiome in neonates, with a focus on its involvement in key respiratory disorders such as bronchopulmonary dysplasia, respiratory syncytial virus infection, neonatal acute respiratory distress syndrome, cystic fibrosis, and asthma predisposition. We place particular emphasis on the bidirectional communication along the gut-lung axis as a central mechanism, wherein intestinal microbiota and their metabolites modulate pulmonary immunity and inflammation. Emerging multi-omics studies that integrate microbial data with host metabolomic and immune profiles are highlighted for their role in deciphering disease-specific dysbiotic signatures and mechanistic pathways. Critically, this review advances the discussion beyond association by evaluating the translational potential of the microbiome as both a diagnostic biomarker and a therapeutic target. We provide a critical appraisal of innovative microbiome-targeted strategies-including probiotics, postbiotics, phage therapy, and bacterial lysates-and discuss the unique challenges and future directions for translating these approaches into safe, effective clinical interventions for vulnerable neonates. By bridging foundational science with clinical implications, this work aims to inform the development of novel, ecology-informed therapeutics to prevent and mitigate neonatal respiratory diseases.

PMID:41918694 | PMC:PMC13033698 | DOI:10.3389/fped.2026.1770578

The neonatal lung microbiome: a dynamic determinant of respiratory health, disease, and novel therapeutics

βœ‡(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Wanwei Zheng Β· Yan Liang Β· Jiayao Li
1 April 2026 at 18:00

Front Pediatr. 2026 Mar 16;14:1770578. doi: 10.3389/fped.2026.1770578. eCollection 2026.

ABSTRACT

The neonatal lung, once considered sterile, is now recognized to harbor a dynamic and complex microbiome that plays a critical role in respiratory health and disease. This review synthesizes current evidence on the composition, development, and functional impact of the lung microbiome in neonates, with a focus on its involvement in key respiratory disorders such as bronchopulmonary dysplasia, respiratory syncytial virus infection, neonatal acute respiratory distress syndrome, cystic fibrosis, and asthma predisposition. We place particular emphasis on the bidirectional communication along the gut-lung axis as a central mechanism, wherein intestinal microbiota and their metabolites modulate pulmonary immunity and inflammation. Emerging multi-omics studies that integrate microbial data with host metabolomic and immune profiles are highlighted for their role in deciphering disease-specific dysbiotic signatures and mechanistic pathways. Critically, this review advances the discussion beyond association by evaluating the translational potential of the microbiome as both a diagnostic biomarker and a therapeutic target. We provide a critical appraisal of innovative microbiome-targeted strategies-including probiotics, postbiotics, phage therapy, and bacterial lysates-and discuss the unique challenges and future directions for translating these approaches into safe, effective clinical interventions for vulnerable neonates. By bridging foundational science with clinical implications, this work aims to inform the development of novel, ecology-informed therapeutics to prevent and mitigate neonatal respiratory diseases.

PMID:41918694 | PMC:PMC13033698 | DOI:10.3389/fped.2026.1770578

Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Siyuan Du Β· Siyi Li Β· Shuwei Bai Β· Ang Li Β· Haolin Li Β· Mingqing Xiao Β· Yang Pan Β· Dongsheng Li Β· Weidi Xie Β· Yanfeng Wang Β· Ya Zhang Β· Chencheng Zhang Β· Jiangchao Yao
1 April 2026 at 12:00
arXiv:2603.29176v1 Announce Type: new Abstract: Parkinson's disease (PD) affects over ten million people worldwide. Although temporal interference (TI) and deep brain stimulation (DBS) are promising therapies, inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost. Previous explorations either resort to limited statistical biomarkers that are insufficient to characterize variability, or employ AI-driven methods which is prone to overfitting and opacity. We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI. Critically, a generative virtual brain foundation model, pretrained on a collective dataset (2707 subjects, 5621 sessions) to capture universal disorder patterns, was finetuned on PD cohorts receiving TI (n=51) or DBS (n=55) to yield individualized virtual brains with high fidelity to empirical functional connectivity (r=0.935). By constructing counterfactual estimations between pathological and healthy neural states within these personalized models, we predicted clinical responses (TI: AUPR=0.853; DBS: AUPR=0.915), substantially outperforming baselines. External and prospective validations (n=14, n=11) highlight the feasibility of clinical translation. Moreover, our framework provides state-dependent regional patterns linked to response, offering hypothesis-generating mechanistic insights.

Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Zhiqian Zhang Β· Xu Zhao Β· Xiaoqing Xu Β· Guangdong Liang Β· Weijia Wang Β· Xiaolei Lv Β· Bo Li Β· Jun Gao
1 April 2026 at 12:00
arXiv:2603.29211v1 Announce Type: new Abstract: In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models still suffer from degraded generalization and catastrophic forgetting because of limited fine-grained visual perception and insufficient modeling of long-tail noise. In this paper, we present Xuanwu VL-2B as a case study of how general multimodal models can be developed into an industrial-grade foundation model for content ecosystems. The model adopts a compact InternViT-300M + MLP + Qwen3 1.7B architecture, balancing fine-grained visual perception, language-semantic alignment, and deployment cost within an approximately 2B-parameter budget. To balance business specialization with the retention of general capabilities, we developed a data iteration and curation mechanism and trained the model through a progressive three-stage pipeline: pre-training, mid-training, and post-training. Ablation studies and offline business evaluations show that Xuanwu VL-2B achieves an average score of 67.90 across seven OpenCompass multimodal metrics (vs. 64.27 for InternVL 3.5 2B), an average recall of 94.38% over seven independent business moderation tasks, and a weighted overall recall of 82.82% on policy-violating text in challenging adversarial OCR scenarios, outperforming Gemini-2.5-Pro (76.72%). These results show that, under a limited parameter budget, Xuanwu VL-2B achieves a practical balance among business alignment, visual perception, general capability retention, and deployment cost.

ASI-Evolve: AI Accelerates AI

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Weixian Xu Β· Tiantian Mi Β· Yixiu Liu Β· Yang Nan Β· Zhimeng Zhou Β· Lyumanshan Ye Β· Lin Zhang Β· Yu Qiao Β· Pengfei Liu
1 April 2026 at 12:00
arXiv:2603.29640v1 Announce Type: new Abstract: Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI research that closes this loop through a learn-design-experiment-analyze cycle. ASI-Evolve augments standard evolutionary agents with two key components: a cognition base that injects accumulated human priors into each round of exploration, and a dedicated analyzer that distills complex experimental outcomes into reusable insights for future iterations. To our knowledge, ASI-Evolve is the first unified framework to demonstrate AI-driven discovery across three central components of AI development: data, architectures, and learning algorithms. In neural architecture design, it discovered 105 SOTA linear attention architectures, with the best discovered model surpassing DeltaNet by +0.97 points, nearly 3x the gain of recent human-designed improvements. In pretraining data curation, the evolved pipeline improves average benchmark performance by +3.96 points, with gains exceeding 18 points on MMLU. In reinforcement learning algorithm design, discovered algorithms outperform GRPO by up to +12.5 points on AMC32, +11.67 points on AIME24, and +5.04 points on OlympiadBench. We further provide initial evidence that this AI-for-AI paradigm can transfer beyond the AI stack through experiments in mathematics and biomedicine. Together, these results suggest that ASI-Evolve represents a promising step toward enabling AI to accelerate AI across the foundational stages of development, offering early evidence for the feasibility of closed-loop AI research.

Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Quanhao Li Β· Wei Jiang
1 April 2026 at 12:00
arXiv:2603.29761v1 Announce Type: new Abstract: A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength. We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state. These impose contradictory data requirements: low-rated games provide the diversity needed for tracking, while high-rated games provide the quality signal for decision learning. Removing low-rated data degrades performance. We formalize this tension as a dual-capability bottleneck, P

Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Han Deng Β· Anqi Zou Β· Hanling Zhang Β· Ben Fei Β· Chengyu Zhang Β· Haobo Wang Β· Xinru Guo Β· Zhenyu Li Β· Xuzhu Wang Β· Peng Yang Β· Fujian Zhang Β· Weiyu Guo Β· Xiaohong Shao Β· Zhaoyang Liu Β· Shixiang Tang Β· Zhihui Wang Β· Wanli Ouyang
1 April 2026 at 12:00
arXiv:2603.29828v1 Announce Type: new Abstract: Scientific discovery increasingly depends on high-throughput characterization, yet automation is hindered by proprietary GUIs and the limited generalizability of existing API-based systems. We present Owl-AuraID, a software-hardware collaborative embodied agent system that adopts a GUI-native paradigm to operate instruments through the same interfaces as human experts. Its skill-centric framework integrates Type-1 (GUI operation) and Type-2 (data analysis) skills into end-to-end workflows, connecting physical sample handling with scientific interpretation. Owl-AuraID demonstrates broad coverage across ten categories of precision instruments and diverse workflows, including multimodal spectral analysis, microscopic imaging, and crystallographic analysis, supporting modalities such as FTIR, NMR, AFM, and TGA. Overall, Owl-AuraID provides a practical, extensible foundation for autonomous laboratories and illustrates a path toward evolving laboratory intelligence through reusable operational and analytical skills. The code are available at https://github.com/OpenOwlab/AuraID.

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: He Yang Β· Dongyi Lv Β· Song Ma Β· Wei Xi Β· Jizhong Zhao
1 April 2026 at 12:00
arXiv:2603.28824v1 Announce Type: cross Abstract: Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable to backdoor attacks, where malicious triggers are injected into the condensation dataset, manipulating model behavior during inference. While prior approaches have made progress in balancing attack success rate and clean test accuracy, they often fall short in preserving stealthiness, especially in concealing the visual artifacts of condensed data or the perturbations introduced during inference. To address this challenge, we introduce Sneakdoor, which enhances stealthiness without compromising attack effectiveness. Sneakdoor exploits the inherent vulnerability of class decision boundaries and incorporates a generative module that constructs input-aware triggers aligned with local feature geometry, thereby minimizing detectability. This joint design enables the attack to remain imperceptible to both human inspection and statistical detection. Extensive experiments across multiple datasets demonstrate that Sneakdoor achieves a compelling balance among attack success rate, clean test accuracy, and stealthiness, substantially improving the invisibility of both the synthetic data and triggered samples while maintaining high attack efficacy. The code is available at https://github.com/XJTU-AI-Lab/SneakDoor.

OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Tianran Liu Β· Shengwen Zhao Β· Mozhgan Pourkeshavarz Β· Weican Li Β· Nicholas Rhinehart
1 April 2026 at 12:00
arXiv:2603.28887v1 Announce Type: cross Abstract: Data-driven autonomous driving simulation has long been constrained by its heavy reliance on pre-recorded driving logs or spatial priors, such as HD maps. This fundamental dependency severely limits scalability, restricting open-ended generation capabilities to the finite scale of existing collected datasets. To break this bottleneck, we present OccSim, the first occupancy world model-driven 3D simulator. OccSim obviates the requirement for continuous logs or HD maps; conditioned only on a single initial frame and a sequence of future ego-actions, it can stably generate over 3,000 continuous frames, enabling the continuous construction of large-scale 3D occupancy maps spanning over 4 kilometers for simulation. This represents an >80x improvement in stable generation length over previous state-of-the-art occupancy world models. OccSim is powered by two modules: W-DiT based static occupancy world model and the Layout Generator. W-DiT handles the ultra-long-horizon generation of static environments by explicitly introducing known rigid transformations in architecture design, while the Layout Generator populates the dynamic foreground with reactive agents based on the synthesized road topology. With these designs, OccSim can synthesize massive, diverse simulation streams. Extensive experiments demonstrate its downstream utility: data collected directly from OccSim can pre-train 4D semantic occupancy forecasting models to achieve up to 67% zero-shot performance on unseen data, outperforming previous asset-based simulator by 11%. When scaling the OccSim dataset to 5x the size, the zero-shot performance increases to about 74%, while the improvement over asset-based simulators expands to 22.1%.

Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Alex Zongo Β· Filippos Fotiadis Β· Ufuk Topcu Β· Peng Wei
1 April 2026 at 12:00
arXiv:2603.28900v1 Announce Type: cross Abstract: We address robust separation assurance for small Unmanned Aircraft Systems (sUAS) under GPS degradation and spoofing via Multi-Agent Reinforcement Learning (MARL). In cooperative surveillance, each aircraft (or agent) broadcasts its GPS-derived position; when such position broadcasts are corrupted, the entire observed air traffic state becomes unreliable. We cast this state observation corruption as a zero-sum game between the agents and an adversary: with probability R, the adversary perturbs the observed state to maximally degrade each agent's safety performance. We derive a closed-form expression for this adversarial perturbation, bypassing adversarial training entirely and enabling linear-time evaluation in the state dimension. We show that this expression approximates the true worst-case adversarial perturbation with second-order accuracy. We further bound the safety performance gap between clean and corrupted observations, showing that it degrades at most linearly with the corruption probability under Kullback-Leibler regularization. Finally, we integrate the closed-form adversarial policy into a MARL policy gradient algorithm to obtain a robust counter-policy for the agents. In a high-density sUAS simulation, we observe near-zero collision rates under corruption levels up to 35%, outperforming a baseline policy trained without adversarial perturbations.

Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Bilgehan Sel Β· Xuanli He Β· Alwin Peng Β· Ming Jin Β· Jerry Wei
1 April 2026 at 12:00
arXiv:2603.29038v1 Announce Type: cross Abstract: Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an adversarial fine-tuning method that bypasses Anthropic's Constitutional Classifiers. Our approach uses curriculum learning combined with GRPO-based hybrid reinforcement learning to teach models a communication protocol that evades LLM-based content classification. Crucially, while prior adversarial fine-tuning approaches report more than 25% capability degradation on reasoning benchmarks, Trojan-Speak incurs less than 5% degradation while achieving 99+% classifier evasion for models with 14B+ parameters. We demonstrate that fine-tuned models can provide detailed responses to expert-level CBRN (Chemical, Biological, Radiological, and Nuclear) queries from Anthropic's Constitutional Classifiers bug-bounty program. Our findings reveal that LLM-based content classifiers alone are insufficient for preventing dangerous information disclosure when adversaries have fine-tuning access, and we show that activation-level probes can substantially improve robustness to such attacks.

On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Zichao Wei
1 April 2026 at 12:00
arXiv:2603.29069v1 Announce Type: cross Abstract: Integer multiplication has long been considered a hard problem for neural networks, with the difficulty widely attributed to the O(n) long-range dependency induced by carry chains. We argue that this diagnosis is wrong: long-range dependency is not an intrinsic property of multiplication, but a mirage produced by the choice of computational spacetime. We formalize the notion of mirage and provide a constructive proof: when two n-bit binary integers are laid out as a 2D outer-product grid, every step of long multiplication collapses into a $3 \times 3$ local neighborhood operation. Under this representation, a neural cellular automaton with only 321 learnable parameters achieves perfect length generalization up to $683\times$ the training range. Five alternative architectures -- including Transformer (6,625 params), Transformer+RoPE, and Mamba -- all fail under the same representation. We further analyze how partial successes locked the community into an incorrect diagnosis, and argue that any task diagnosed as requiring long-range dependency should first be examined for whether the dependency is intrinsic to the task or induced by the computational spacetime.

Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Guan Wang Β· Shuyin Xia Β· Lei Qian Β· Guoyin Wang Β· Yi Liu Β· Yi Wang Β· Wei Wang
1 April 2026 at 12:00
arXiv:2603.29148v1 Announce Type: cross Abstract: Graph Convolutional Network (GCN) is a model that can effectively handle graph data tasks and has been successfully applied. However, for large-scale graph datasets, GCN still faces the challenge of high computational overhead, especially when the number of convolutional layers in the graph is large. Currently, there are many advanced methods that use various sampling techniques or graph coarsening techniques to alleviate the inconvenience caused during training. However, among these methods, some ignore the multi-granularity information in the graph structure, and the time complexity of some coarsening methods is still relatively high. In response to these issues, based on our previous work, in this paper, we propose a new framework called Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification. Specifically, this method first uses a multi-granularity granular-ball graph coarsening algorithm to coarsen the original graph to obtain many subgraphs. The time complexity of this stage is linear and much lower than that of the exiting graph coarsening methods. Then, subgraphs composed of these granular-balls are randomly sampled to form minibatches for training GCN. Our algorithm can adaptively and significantly reduce the scale of the original graph, thereby enhancing the training efficiency and scalability of GCN. Ultimately, the experimental results of node classification on multiple datasets demonstrate that the method proposed in this paper exhibits superior performance. The code is available at https://anonymous.4open.science/r/1-141D/.

IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xiaohui Zhou Β· Yijie Wang Β· Hongzuo Xu Β· Weixuan Liang Β· Xiaoli Li Β· Guansong Pang
1 April 2026 at 12:00
arXiv:2603.29183v1 Announce Type: cross Abstract: Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to identify both seen and unseen anomalies during testing. Current approaches rely on simple augmentation methods to generate pseudo anomalies that replicate unseen anomalies. Despite being promising in image data, these methods are found to be ineffective in time series data due to the failure to preserve its sequential nature, resulting in trivial or unrealistic anomaly patterns. They are further plagued when the training data is contaminated with unlabeled anomalies. This work introduces $\textbf{IMPACT}$, a novel framework that leverages $\underline{\textbf{i}}$nfluence $\underline{\textbf{m}}$odeling for o$\underline{\textbf{p}}$en-set time series $\underline{\textbf{a}}$nomaly dete$\underline{\textbf{ct}}$ion, to tackle these challenges. The key insight is to $\textbf{i)}$ learn an influence function that can accurately estimate the impact of individual training samples on the modeling, and then $\textbf{ii)}$ leverage these influence scores to generate semantically divergent yet realistic unseen anomalies for time series while repurposing high-influential samples as supervised anomalies for anomaly decontamination. Extensive experiments show that IMPACT significantly outperforms existing state-of-the-art methods, showing superior accuracy under varying OSAD settings and contamination rates.

Improving Ensemble Forecasts of Abnormally Deflecting Tropical Cyclones with Fused Atmosphere-Ocean-Terrain Data

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Qixiang Li Β· Shuwei Huo Β· Chong Wang Β· Xiaofeng Li Β· Yuan Zhou
1 April 2026 at 12:00
arXiv:2603.29200v1 Announce Type: cross Abstract: Deep learning-based tropical cyclone (TC) forecasting methods have demonstrated significant potential and application advantages, as they feature much lower computational cost and faster operation speed than numerical weather prediction models. However, existing deep learning methods still have key limitations: they can only process a single type of sequential trajectory data or homogeneous meteorological variables, and fail to achieve accurate forecasting of abnormal deflected TCs. To address these challenges, we present two groundbreaking contributions. First, we have constructed a multimodal and multi-source dataset named AOT-TCs for TC forecasting in the Northwest Pacific basin. As the first dataset of its kind, it innovatively integrates heterogeneous variables from the atmosphere, ocean, and land, thus obtaining a comprehensive and information-rich meteorological dataset. Second, based on the AOT-TCs dataset, we propose a forecasting model that can handle both normal and abnormally deflected TCs. This is the first TC forecasting model to adopt an explicit atmosphere-ocean-terrain coupling architecture, enabling it to effectively capture complex interactions across physical domains. Extensive experiments on all TC cases in the Northwest Pacific from 2017 to 2024 show that our model achieves state-of-the-art performance in TC forecasting: it not only significantly improves the forecasting accuracy of normal TCs but also breaks through the technical bottleneck in forecasting abnormally deflected TCs.

MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Guozhi Qiu Β· Zhiwei Chen Β· Zixu Li Β· Qinlei Huang Β· Zhiheng Fu Β· Xuemeng Song Β· Yupeng Hu
1 April 2026 at 12:00
arXiv:2603.29291v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) uses a reference image and a modification text as a query to retrieve a target image satisfying the requirement of ``modifying the reference image according to the text instructions''. However, existing CIR methods face two limitations: (1) frequency bias leading to ``Rare Sample Neglect'', and (2) susceptibility of similarity scores to interference from hard negative samples and noise. To address these limitations, we confront two key challenges: asymmetric rare semantic localization and robust similarity estimation under hard negative samples. To solve these challenges, we propose the Modification frEquentation-rarity baLance neTwork MELT. MELT assigns increased attention to rare modification semantics in multimodal contexts while applying diffusion-based denoising to hard negative samples with high similarity scores, enhancing multimodal fusion and matching. Extensive experiments on two CIR benchmarks validate the superior performance of MELT. Codes are available at https://github.com/luckylittlezhi/MELT.

Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Huan Zhang Β· Wei Cheng Β· Wei Hu
1 April 2026 at 12:00
arXiv:2603.29292v1 Announce Type: cross Abstract: Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine-tuning or preference optimization, both of which require costly external resources such as powerful teacher models or reliable test units. However, in real-world scenarios, it is much harder to obtain reference solutions and test oracles than problem descriptions and test inputs. In this paper, we tackle a challenging yet realistic question: Can a code language model improve itself without access to a superior teacher and a test oracle? To answer this, we propose ConSelf, a self-improving approach built upon two key ideas. First, we introduce code semantic entropy, a novel metric that measures problem-level uncertainty by assessing the functional diversity of program behaviors, enabling a curriculum construction with the most learnable problems. Second, we present consensus-driven direct preference optimization (Con-DPO), a preference-based fine-tuning method that weights each preference pair by its behavioral consensus, thereby mitigating the impact of noisy self-generated supervision. Experiments on various benchmarks and backbone LLMs demonstrate that ConSelf significantly outperforms baselines, validating the effectiveness of semantic entropy-based curriculum construction and consensus-driven optimization in improving code generation without external supervision.

Scaling Whole-Body Human Musculoskeletal Behavior Emulation for Specificity and Diversity

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yunyue Wei Β· Chenhui Zuo Β· Shanning Zhuang Β· Haixin Gong Β· Yaming Liu Β· Yanan Sui
1 April 2026 at 12:00
arXiv:2603.29332v1 Announce Type: cross Abstract: The embodied learning of human motor control requires whole-body neuro-actuated musculoskeletal dynamics, while the internal muscle-driven processes underlying movement remain inaccessible to direct measurement. Computational modeling offers an alternative, but inverse dynamics methods struggled to resolve redundant control from observed kinematics in the high-dimensional, over-actuated system. Forward imitation approaches based on deep reinforcement learning exhibited inadequate tracking performance due to the curse of dimensionality in both control and reward design. Here we introduce a large-scale parallel musculoskeletal computation framework for biomechanically grounded whole-body motion reproduction. By integrating large-scale parallel GPU simulation with adversarial reward aggregation and value-guided flow exploration, the MS-Emulator framework overcomes key optimization bottlenecks in high-dimensional reinforcement learning for musculoskeletal control, which accurately reproduces a broad repertoire of motions in a whole-body human musculoskeletal system actuated by approximately 700 muscles. It achieved high joint angle accuracy and body position alignment for highly dynamic tasks such as dance, cartwheel, and backflip. The framework was also used to explore the musculoskeletal control solution space, identifying distinct musculoskeletal control policies that converge to nearly identical external kinematic and mechanical measurements. This work establishes a tractable computational route to analyzing the specificity and diversity underlying human embodied control of movement. Project page: https://lnsgroup.cc/research/MS-Emulator.

Hallucination-aware intermediate representation edit in large vision-language models

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Wei Suo Β· Hanzu Zhang Β· Lijun Zhang Β· Ji Ma Β· Peng Wang Β· Yanning Zhang
1 April 2026 at 12:00
arXiv:2603.29405v1 Announce Type: cross Abstract: Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant hallucination issues, where outputs contradict visual facts. Recent research on hallucination mitigation has focused on retraining methods and Contrastive Decoding (CD) methods. While both methods perform well, retraining methods require substantial training resources, and CD methods introduce dual inference overhead. These factors hinder their practical applicability. To address the above issue, we propose a framework for dynamically detecting hallucination representations and performing hallucination-eliminating edits on these representations. With minimal additional computational cost, we achieve state-of-the-art performance on existing benchmarks. Extensive experiments demonstrate the effectiveness of our approach, highlighting its efficient and robust hallucination elimination capability and its powerful controllability over hallucinations. Code is available at https://github.com/ASGO-MM/HIRE

Hybrid Quantum-Classical Spatiotemporal Forecasting for 3D Cloud Fields

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Fu Wang Β· Qifeng Lu Β· Xinyu Long Β· Meng Zhang Β· Xiaofei Yang Β· Weijia Cao Β· Xiaowen Chu
1 April 2026 at 12:00
arXiv:2603.29407v1 Announce Type: cross Abstract: Accurate forecasting of three-dimensional (3D) cloud fields is important for atmospheric analysis and short-range numerical weather prediction, yet it remains challenging because cloud evolution involves cross-layer interactions, nonlocal dependencies, and multiscale spatiotemporal dynamics. Existing spatiotemporal prediction models based on convolutions, recurrence, or attention often rely on locality-biased representations and therefore struggle to preserve fine cloud structures in volumetric forecasting tasks. To address this issue, we propose QENO, a hybrid quantum-inspired spatiotemporal forecasting framework for 3D cloud fields. The proposed architecture consists of four components: a classical spatiotemporal encoder for compact latent representation, a topology-aware quantum enhancement block for modeling nonlocal couplings in latent space, a dynamic fusion temporal unit for integrating measurement-derived quantum features with recurrent memory, and a decoder for reconstructing future cloud volumes. Experiments on CMA-MESO 3D cloud fields show that QENO consistently outperforms representative baselines, including ConvLSTM, PredRNN++, Earthformer, TAU, and SimVP variants, in terms of MSE, MAE, RMSE, SSIM, and threshold-based detection metrics. In particular, QENO achieves an MSE of 0.2038, an RMSE of 0.4514, and an SSIM of 0.6291, while also maintaining a compact parameter budget. These results indicate that topology-aware hybrid quantum-classical feature modeling is a promising direction for 3D cloud structure forecasting and atmospheric Earth observation data analysis.
❌